重构：去除prefect

- Add NUCLEI_TEMPLATES_REPO_URL setting to allow runtime configuration of template repository URL
- Refactor install.sh mirror parameter handling to use boolean flag instead of URL string
- Replace hardcoded GitHub repository URL with Gitee mirror option for faster downloads in mainland China
- Update environment variable configuration to persist Nuclei repository URL in .env file
- Improve shell script variable quoting and conditional syntax for better reliability
- Simplify mirror detection logic by using USE_MIRROR boolean flag throughout installation process
- Add support for automatic Gitee mirror selection when --mirror flag is enabled

.github/workflows/docker-build.yml

@@ -19,7 +19,8 @@ permissions:
   contents: write
 
 jobs:
-  build:
+  # AMD64 构建（原生 x64 runner）
+  build-amd64:
     runs-on: ubuntu-latest
     strategy:
       matrix:
@@ -27,39 +28,30 @@ jobs:
           - image: xingrin-server
             dockerfile: docker/server/Dockerfile
             context: .
-            platforms: linux/amd64,linux/arm64
           - image: xingrin-frontend
             dockerfile: docker/frontend/Dockerfile
             context: .
-            platforms: linux/amd64  # ARM64 构建时 Next.js 在 QEMU 下会崩溃
           - image: xingrin-worker
             dockerfile: docker/worker/Dockerfile
             context: .
-            platforms: linux/amd64,linux/arm64
           - image: xingrin-nginx
             dockerfile: docker/nginx/Dockerfile
             context: .
-            platforms: linux/amd64,linux/arm64
           - image: xingrin-agent
             dockerfile: docker/agent/Dockerfile
             context: .
-            platforms: linux/amd64,linux/arm64
+          - image: xingrin-postgres
+            dockerfile: docker/postgres/Dockerfile
+            context: docker/postgres
 
     steps:
       - name: Checkout
         uses: actions/checkout@v4
 
-      - name: Free disk space (for large builds like worker)
+      - name: Free disk space
         run: |
-          echo "=== Before cleanup ==="
+          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL
-          df -h
-          sudo rm -rf /usr/share/dotnet
-          sudo rm -rf /usr/local/lib/android
-          sudo rm -rf /opt/ghc
-          sudo rm -rf /opt/hostedtoolcache/CodeQL
           sudo docker image prune -af
-          echo "=== After cleanup ==="
-          df -h
 
       - name: Generate SSL certificates for nginx build
         if: matrix.image == 'xingrin-nginx'
@@ -69,10 +61,6 @@ jobs:
             -keyout docker/nginx/ssl/privkey.pem \
             -out docker/nginx/ssl/fullchain.pem \
             -subj "/CN=localhost"
-          echo "SSL certificates generated for CI build"
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
 
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
@@ -83,7 +71,120 @@ jobs:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
-      - name: Get version from git tag
+      - name: Get version
+        id: version
+        run: |
+          if [[ $GITHUB_REF == refs/tags/* ]]; then
+            echo "VERSION=${GITHUB_REF#refs/tags/}" >> $GITHUB_OUTPUT
+          else
+            echo "VERSION=dev-$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Build and push AMD64
+        uses: docker/build-push-action@v5
+        with:
+          context: ${{ matrix.context }}
+          file: ${{ matrix.dockerfile }}
+          platforms: linux/amd64
+          push: true
+          tags: ${{ env.IMAGE_PREFIX }}/${{ matrix.image }}:${{ steps.version.outputs.VERSION }}-amd64
+          build-args: IMAGE_TAG=${{ steps.version.outputs.VERSION }}
+          cache-from: type=registry,ref=${{ env.IMAGE_PREFIX }}/${{ matrix.image }}:cache-amd64
+          cache-to: type=registry,ref=${{ env.IMAGE_PREFIX }}/${{ matrix.image }}:cache-amd64,mode=max
+          provenance: false
+          sbom: false
+
+  # ARM64 构建（原生 ARM64 runner）
+  build-arm64:
+    runs-on: ubuntu-22.04-arm
+    strategy:
+      matrix:
+        include:
+          - image: xingrin-server
+            dockerfile: docker/server/Dockerfile
+            context: .
+          - image: xingrin-frontend
+            dockerfile: docker/frontend/Dockerfile
+            context: .
+          - image: xingrin-worker
+            dockerfile: docker/worker/Dockerfile
+            context: .
+          - image: xingrin-nginx
+            dockerfile: docker/nginx/Dockerfile
+            context: .
+          - image: xingrin-agent
+            dockerfile: docker/agent/Dockerfile
+            context: .
+          - image: xingrin-postgres
+            dockerfile: docker/postgres/Dockerfile
+            context: docker/postgres
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Generate SSL certificates for nginx build
+        if: matrix.image == 'xingrin-nginx'
+        run: |
+          mkdir -p docker/nginx/ssl
+          openssl req -x509 -nodes -days 365 -newkey rsa:2048 \
+            -keyout docker/nginx/ssl/privkey.pem \
+            -out docker/nginx/ssl/fullchain.pem \
+            -subj "/CN=localhost"
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Get version
+        id: version
+        run: |
+          if [[ $GITHUB_REF == refs/tags/* ]]; then
+            echo "VERSION=${GITHUB_REF#refs/tags/}" >> $GITHUB_OUTPUT
+          else
+            echo "VERSION=dev-$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Build and push ARM64
+        uses: docker/build-push-action@v5
+        with:
+          context: ${{ matrix.context }}
+          file: ${{ matrix.dockerfile }}
+          platforms: linux/arm64
+          push: true
+          tags: ${{ env.IMAGE_PREFIX }}/${{ matrix.image }}:${{ steps.version.outputs.VERSION }}-arm64
+          build-args: IMAGE_TAG=${{ steps.version.outputs.VERSION }}
+          cache-from: type=registry,ref=${{ env.IMAGE_PREFIX }}/${{ matrix.image }}:cache-arm64
+          cache-to: type=registry,ref=${{ env.IMAGE_PREFIX }}/${{ matrix.image }}:cache-arm64,mode=max
+          provenance: false
+          sbom: false
+
+  # 合并多架构 manifest
+  merge-manifests:
+    runs-on: ubuntu-latest
+    needs: [build-amd64, build-arm64]
+    strategy:
+      matrix:
+        image:
+          - xingrin-server
+          - xingrin-frontend
+          - xingrin-worker
+          - xingrin-nginx
+          - xingrin-agent
+          - xingrin-postgres
+    steps:
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Get version
         id: version
         run: |
           if [[ $GITHUB_REF == refs/tags/* ]]; then
@@ -94,28 +195,27 @@ jobs:
             echo "IS_RELEASE=false" >> $GITHUB_OUTPUT
           fi
 
-      - name: Build and push
+      - name: Create and push multi-arch manifest
-        uses: docker/build-push-action@v5
+        run: |
-        with:
+          VERSION=${{ steps.version.outputs.VERSION }}
-          context: ${{ matrix.context }}
+          IMAGE=${{ env.IMAGE_PREFIX }}/${{ matrix.image }}
-          file: ${{ matrix.dockerfile }}
-          platforms: ${{ matrix.platforms }}
-          push: true
-          tags: |
-            ${{ env.IMAGE_PREFIX }}/${{ matrix.image }}:${{ steps.version.outputs.VERSION }}
-            ${{ steps.version.outputs.IS_RELEASE == 'true' && format('{0}/{1}:latest', env.IMAGE_PREFIX, matrix.image) || '' }}
-          build-args: |
-            IMAGE_TAG=${{ steps.version.outputs.VERSION }}
-          cache-from: type=gha,scope=${{ matrix.image }}
-          cache-to: type=gha,mode=max,scope=${{ matrix.image }}
-          provenance: false
-          sbom: false
           
-  # 所有镜像构建成功后，更新 VERSION 文件
+          docker manifest create ${IMAGE}:${VERSION} \
-  # 根据 tag 所在的分支更新对应分支的 VERSION 文件
+            ${IMAGE}:${VERSION}-amd64 \
+            ${IMAGE}:${VERSION}-arm64
+          docker manifest push ${IMAGE}:${VERSION}
+          
+          if [[ "${{ steps.version.outputs.IS_RELEASE }}" == "true" ]]; then
+            docker manifest create ${IMAGE}:latest \
+              ${IMAGE}:${VERSION}-amd64 \
+              ${IMAGE}:${VERSION}-arm64
+            docker manifest push ${IMAGE}:latest
+          fi
+
+  # 更新 VERSION 文件
   update-version:
     runs-on: ubuntu-latest
-    needs: build
+    needs: merge-manifests
     if: startsWith(github.ref, 'refs/tags/v')
     steps:
       - name: Checkout repository

.gitignore

@@ -64,6 +64,7 @@ backend/.env.local
 .coverage
 htmlcov/
 *.cover
+.hypothesis/
 
 # ============================
 # 后端 (Go) 相关

README.md

@@ -1,7 +1,7 @@
 <h1 align="center">XingRin - 星环</h1>
 
 <p align="center">
-  <b>🛡️ 攻击面管理平台 (ASM) | 自动化资产发现与漏洞扫描系统</b>
+  <b>攻击面管理平台 (ASM) | 自动化资产发现与漏洞扫描系统</b>
 </p>
 
 <p align="center">
@@ -12,22 +12,29 @@
 </p>
 
 <p align="center">
-  <a href="#-功能特性">功能特性</a> •
+  <a href="#功能特性">功能特性</a> •
-  <a href="#-快速开始">快速开始</a> •
+  <a href="#全局资产搜索">资产搜索</a> •
-  <a href="#-文档">文档</a> •
+  <a href="#快速开始">快速开始</a> •
-  <a href="#-技术栈">技术栈</a> •
+  <a href="#文档">文档</a> •
-  <a href="#-反馈与贡献">反馈与贡献</a>
+  <a href="#反馈与贡献">反馈与贡献</a>
 </p>
 
 <p align="center">
-  <sub>🔍 关键词: ASM | 攻击面管理 | 漏洞扫描 | 资产发现 | Bug Bounty | 渗透测试 | Nuclei | 子域名枚举 | EASM</sub>
+  <sub>关键词: ASM | 攻击面管理 | 漏洞扫描 | 资产发现 | 资产搜索 | Bug Bounty | 渗透测试 | Nuclei | 子域名枚举 | EASM</sub>
 </p>
 
 ---
 
+## 在线 Demo
+
+ **[https://xingrin.vercel.app/](https://xingrin.vercel.app/)**
+
+> 仅用于 UI 展示，未接入后端数据库
+
+---
 
 <p align="center">
-  <b>🎨 现代化 UI </b>
+  <b>现代化 UI</b>
 </p>
 
 <p align="center">
@@ -37,34 +44,49 @@
   <img src="docs/screenshots/quantum-rose.png" alt="Quantum Rose" width="24%">
 </p>
 
-## 📚 文档
+## 文档
 
-- [📖 技术文档](./docs/README.md) - 技术文档导航（🚧 持续完善中）
+- [技术文档](./docs/README.md) - 技术文档导航（持续完善中）
-- [🚀 快速开始](./docs/quick-start.md) - 一键安装和部署指南
+- [快速开始](./docs/quick-start.md) - 一键安装和部署指南
-- [🔄 版本管理](./docs/version-management.md) - Git Tag 驱动的自动化版本管理系统
+- [版本管理](./docs/version-management.md) - Git Tag 驱动的自动化版本管理系统
-- [📦 Nuclei 模板架构](./docs/nuclei-template-architecture.md) - 模板仓库的存储与同步
+- [Nuclei 模板架构](./docs/nuclei-template-architecture.md) - 模板仓库的存储与同步
-- [📖 字典文件架构](./docs/wordlist-architecture.md) - 字典文件的存储与同步
+- [字典文件架构](./docs/wordlist-architecture.md) - 字典文件的存储与同步
-- [🔍 扫描流程架构](./docs/scan-flow-architecture.md) - 完整扫描流程与工具编排
+- [扫描流程架构](./docs/scan-flow-architecture.md) - 完整扫描流程与工具编排
 
 
 ---
 
-## ✨ 功能特性
+## 功能特性
 
-### 🎯 目标与资产管理
+### 扫描能力
-- **组织管理** - 多层级目标组织，灵活分组
-- **目标管理** - 支持域名、IP目标类型
-- **资产发现** - 子域名、网站、端点、目录自动发现
-- **资产快照** - 扫描结果快照对比，追踪资产变化
 
-### 🔍 漏洞扫描
+| 功能 | 状态 | 工具 | 说明 |
-- **多引擎支持** - 集成 Nuclei 等主流扫描引擎
+|------|------|------|------|
-- **自定义流程** - YAML 配置扫描流程，灵活编排
+| 子域名扫描 | 已完成 | Subfinder, Amass, PureDNS | 被动收集 + 主动爆破，聚合 50+ 数据源 |
-- **定时扫描** - Cron 表达式配置，自动化周期扫描
+| 端口扫描 | 已完成 | Naabu | 自定义端口范围 |
+| 站点发现 | 已完成 | HTTPX | HTTP 探测，自动获取标题、状态码、技术栈 |
+| 指纹识别 | 已完成 | XingFinger | 2.7W+ 指纹规则，多源指纹库 |
+| URL 收集 | 已完成 | Waymore, Katana | 历史数据 + 主动爬取 |
+| 目录扫描 | 已完成 | FFUF | 高速爆破，智能字典 |
+| 漏洞扫描 | 已完成 | Nuclei, Dalfox | 9000+ POC 模板，XSS 检测 |
+| 站点截图 | 已完成 | Playwright | WebP 高压缩存储 |
 
-#### 扫描流程架构
+### 平台能力
 
-完整的扫描流程包括：子域名发现、端口扫描、站点发现、URL 收集、目录扫描、漏洞扫描等阶段
+| 功能 | 状态 | 说明 |
+|------|------|------|
+| 目标管理 | 已完成 | 多层级组织，支持域名/IP 目标 |
+| 资产快照 | 已完成 | 扫描结果对比，追踪资产变化 |
+| 黑名单过滤 | 已完成 | 全局 + Target 级，支持通配符/CIDR |
+| 定时任务 | 已完成 | Cron 表达式，自动化周期扫描 |
+| 分布式扫描 | 已完成 | 多 Worker 节点，负载感知调度 |
+| 全局搜索 | 已完成 | 表达式语法，多字段组合查询 |
+| 通知推送 | 已完成 | 企业微信、Telegram、Discord |
+| API 密钥管理 | 已完成 | 可视化配置各数据源 API Key |
+
+### 扫描流程架构
+
+完整的扫描流程包括：子域名发现、端口扫描、站点发现、指纹识别、URL 收集、目录扫描、漏洞扫描等阶段
 
 ```mermaid
 flowchart LR
@@ -75,13 +97,15 @@ flowchart LR
         SUB["子域名发现<br/>subfinder, amass, puredns"]
         PORT["端口扫描<br/>naabu"]
         SITE["站点识别<br/>httpx"]
-        SUB --> PORT --> SITE
+        FINGER["指纹识别<br/>xingfinger"]
+        SUB --> PORT --> SITE --> FINGER
     end
     
     subgraph STAGE2["阶段 2: 深度分析"]
         direction TB
         URL["URL 收集<br/>waymore, katana"]
         DIR["目录扫描<br/>ffuf"]
+        SCREENSHOT["站点截图<br/>playwright"]
     end
     
     subgraph STAGE3["阶段 3: 漏洞检测"]
@@ -91,7 +115,7 @@ flowchart LR
     FINISH["扫描完成"]
     
     START --> STAGE1
-    SITE --> STAGE2
+    FINGER --> STAGE2
     STAGE2 --> STAGE3
     STAGE3 --> FINISH
     
@@ -103,14 +127,16 @@ flowchart LR
     style SUB fill:#5dade2,stroke:#3498db,stroke-width:1px,color:#fff
     style PORT fill:#5dade2,stroke:#3498db,stroke-width:1px,color:#fff
     style SITE fill:#5dade2,stroke:#3498db,stroke-width:1px,color:#fff
+    style FINGER fill:#5dade2,stroke:#3498db,stroke-width:1px,color:#fff
     style URL fill:#bb8fce,stroke:#9b59b6,stroke-width:1px,color:#fff
     style DIR fill:#bb8fce,stroke:#9b59b6,stroke-width:1px,color:#fff
+    style SCREENSHOT fill:#bb8fce,stroke:#9b59b6,stroke-width:1px,color:#fff
     style VULN fill:#f0b27a,stroke:#e67e22,stroke-width:1px,color:#fff
 ```
 
 详细说明请查看 [扫描流程架构文档](./docs/scan-flow-architecture.md)
 
-### 🖥️ 分布式架构
+### 分布式架构
 - **多节点扫描** - 支持部署多个 Worker 节点，横向扩展扫描能力
 - **本地节点** - 零配置，安装即自动注册本地 Docker Worker
 - **远程节点** - SSH 一键部署远程 VPS 作为扫描节点
@@ -155,17 +181,43 @@ flowchart TB
     W3 -.心跳上报.-> REDIS
 ```
 
-### 📊 可视化界面
+### 全局资产搜索
+- **多类型搜索** - 支持 Website 和 Endpoint 两种资产类型
+- **表达式语法** - 支持 `=`（模糊）、`==`（精确）、`!=`（不等于）操作符
+- **逻辑组合** - 支持 `&&` (AND) 和 `||` (OR) 逻辑组合
+- **多字段查询** - 支持 host、url、title、tech、status、body、header 字段
+- **CSV 导出** - 流式导出全部搜索结果，无数量限制
+
+#### 搜索语法示例
+
+```bash
+# 基础搜索
+host="api"                    # host 包含 "api"
+status=="200"                 # 状态码精确等于 200
+tech="nginx"                  # 技术栈包含 nginx
+
+# 组合搜索
+host="api" && status=="200"   # host 包含 api 且状态码为 200
+tech="vue" || tech="react"    # 技术栈包含 vue 或 react
+
+# 复杂查询
+host="admin" && tech="php" && status=="200"
+url="/api/v1" && status!="404"
+```
+
+### 可视化界面
 - **数据统计** - 资产/漏洞统计仪表盘
 - **实时通知** - WebSocket 消息推送
+- **通知推送** - 实时企业微信，tg，discard消息推送服务
 
 ---
 
-## 📦 快速开始
+## 快速开始
 
 ### 环境要求
 
-- **操作系统**: Ubuntu 20.04+ / Debian 11+ （推荐）
+- **操作系统**: Ubuntu 20.04+ / Debian 11+ 
+- **系统架构**: AMD64 (x86_64) / ARM64 (aarch64)
 - **硬件**: 2核 4G 内存起步，20GB+ 磁盘空间
 
 ### 一键安装
@@ -178,18 +230,18 @@ cd xingrin
 # 安装并启动（生产模式）
 sudo ./install.sh
 
-# 🇨🇳 中国大陆用户推荐使用镜像加速
+# 中国大陆用户推荐使用镜像加速（第三方加速服务可能会失效，不保证长期可用）
 sudo ./install.sh --mirror
 ```
 
-> **💡 --mirror 参数说明**
+> **--mirror 参数说明**
 > - 自动配置 Docker 镜像加速（国内镜像源）
 > - 加速 Git 仓库克隆（Nuclei 模板等）
-> - 大幅提升安装速度，避免网络超时
 
 ### 访问服务
 
 - **Web 界面**: `https://ip:8083` 
+- **默认账号**: admin / admin（首次登录后请修改密码）
 
 ### 常用命令
 
@@ -207,22 +259,38 @@ sudo ./restart.sh
 sudo ./uninstall.sh
 ```
 
-## 🤝 反馈与贡献
+## 反馈与贡献
 
-- 🐛 **如果发现 Bug** 可以点击右边链接进行提交 [Issue](https://github.com/yyhuni/xingrin/issues)
+- **发现 Bug，有新想法，比如UI设计，功能设计等** 欢迎点击右边链接进行提交建议 [Issue](https://github.com/yyhuni/xingrin/issues) 或者公众号私信
-- 💡 **有新想法，比如UI设计，功能设计等** 欢迎点击右边链接进行提交建议 [Issue](https://github.com/yyhuni/xingrin/issues)
-- 🔧 **想参与开发？** 关注我公众号与我个人联系
 
-## 📧 联系
+## 联系
-- 目前版本就我个人使用，可能会有很多边界问题
+- 微信公众号: **塔罗安全学苑**
-- 如有问题，建议，其他，优先提交[Issue](https://github.com/yyhuni/xingrin/issues)，也可以直接给我的公众号发消息，我都会回复的
+- 微信群去公众号底下的菜单，有个交流群，点击就可以看到了，链接过期可以私信我拉你
-
-- 微信公众号: **洋洋的小黑屋**
 
 <img src="docs/wechat-qrcode.png" alt="微信公众号" width="200">
 
+### 关注公众号免费领取指纹库
 
-## ⚠️ 免责声明
+| 指纹库 | 数量 |
+|--------|------|
+| ehole.json | 21,977 |
+| ARL.yaml | 9,264 |
+| goby.json | 7,086 |
+| FingerprintHub.json | 3,147 |
+
+> 关注公众号回复「指纹」即可获取
+
+## 赞助支持
+
+如果这个项目对你有帮助，谢谢请我能喝杯蜜雪冰城，你的star和赞助是我免费更新的动力
+
+<p>
+  <img src="docs/wx_pay.jpg" alt="微信支付" width="200">
+  <img src="docs/zfb_pay.jpg" alt="支付宝" width="200">
+</p>
+
+
+## 免责声明
 
 **重要：请在使用前仔细阅读**
 
@@ -237,30 +305,29 @@ sudo ./uninstall.sh
 - 遵守所在地区的法律法规
 - 承担因滥用产生的一切后果
 
-## 🌟 Star History
+## Star History
 
-如果这个项目对你有帮助，请给一个 ⭐ Star 支持一下！
+如果这个项目对你有帮助，请给一个 Star 支持一下！
 
 [![Star History Chart](https://api.star-history.com/svg?repos=yyhuni/xingrin&type=Date)](https://star-history.com/#yyhuni/xingrin&Date)
 
-## 📄 许可证
+## 许可证
 
 本项目采用 [GNU General Public License v3.0](LICENSE) 许可证。
 
 ### 允许的用途
 
-- ✅ 个人学习和研究
+- 个人学习和研究
-- ✅ 商业和非商业使用
+- 商业和非商业使用
-- ✅ 修改和分发
+- 修改和分发
-- ✅ 专利使用
+- 专利使用
-- ✅ 私人使用
+- 私人使用
 
 ### 义务和限制
 
-- 📋 **开源义务**：分发时必须提供源代码
+- **开源义务**：分发时必须提供源代码
-- 📋 **相同许可**：衍生作品必须使用相同许可证
+- **相同许可**：衍生作品必须使用相同许可证
-- 📋 **版权声明**：必须保留原始版权和许可证声明
+- **版权声明**：必须保留原始版权和许可证声明
-- ❌ **责任免除**：不提供任何担保
+- **责任免除**：不提供任何担保
-- ❌ 未经授权的渗透测试
+- 未经授权的渗透测试
-- ❌ 任何违法行为
+- 任何违法行为
-

VERSION

@@ -1 +1 @@
-v1.1.14
+v1.5.12-dev

backend/.gitignore

@@ -7,6 +7,7 @@ __pycache__/
 *.egg-info/
 dist/
 build/
+.hypothesis/  # Hypothesis 属性测试缓存
 
 # 虚拟环境
 venv/

backend/apps/asset/apps.py

@@ -4,7 +4,3 @@ from django.apps import AppConfig
 class AssetConfig(AppConfig):
     default_auto_field = 'django.db.models.BigAutoField'
     name = 'apps.asset'
-    
-    def ready(self):
-        # 导入所有模型以确保Django发现并注册
-        from . import models

backend/apps/asset/dtos/asset/endpoint_dto.py

@@ -14,12 +14,13 @@ class EndpointDTO:
     status_code: Optional[int] = None
     content_length: Optional[int] = None
     webserver: Optional[str] = None
-    body_preview: Optional[str] = None
+    response_body: Optional[str] = None
     content_type: Optional[str] = None
     tech: Optional[List[str]] = None
     vhost: Optional[bool] = None
     location: Optional[str] = None
     matched_gf_patterns: Optional[List[str]] = None
+    response_headers: Optional[str] = None
     
     def __post_init__(self):
         if self.tech is None:

backend/apps/asset/dtos/asset/website_dto.py

@@ -17,9 +17,10 @@ class WebSiteDTO:
     webserver: str = ''
     content_type: str = ''
     tech: List[str] = None
-    body_preview: str = ''
+    response_body: str = ''
     vhost: Optional[bool] = None
     created_at: str = None
+    response_headers: str = ''
     
     def __post_init__(self):
         if self.tech is None:

backend/apps/asset/dtos/snapshot/endpoint_snapshot_dto.py

@@ -13,6 +13,7 @@ class EndpointSnapshotDTO:
     快照只属于 scan。
     """
     scan_id: int
+    target_id: int  # 必填，用于同步到资产表
     url: str
     host: str = ''  # 主机名（域名或IP地址）
     title: str = ''
@@ -22,10 +23,10 @@ class EndpointSnapshotDTO:
     webserver: str = ''
     content_type: str = ''
     tech: List[str] = None
-    body_preview: str = ''
+    response_body: str = ''
     vhost: Optional[bool] = None
     matched_gf_patterns: List[str] = None
-    target_id: Optional[int] = None  # 冗余字段，用于同步到资产表
+    response_headers: str = ''
     
     def __post_init__(self):
         if self.tech is None:
@@ -42,9 +43,6 @@ class EndpointSnapshotDTO:
         """
         from apps.asset.dtos.asset import EndpointDTO
         
-        if self.target_id is None:
-            raise ValueError("target_id 不能为 None，无法同步到资产表")
-        
         return EndpointDTO(
             target_id=self.target_id,
             url=self.url,
@@ -53,10 +51,11 @@ class EndpointSnapshotDTO:
             status_code=self.status_code,
             content_length=self.content_length,
             webserver=self.webserver,
-            body_preview=self.body_preview,
+            response_body=self.response_body,
             content_type=self.content_type,
             tech=self.tech if self.tech else [],
             vhost=self.vhost,
             location=self.location,
-            matched_gf_patterns=self.matched_gf_patterns if self.matched_gf_patterns else []
+            matched_gf_patterns=self.matched_gf_patterns if self.matched_gf_patterns else [],
+            response_headers=self.response_headers,
         )

backend/apps/asset/dtos/snapshot/website_snapshot_dto.py

@@ -13,18 +13,19 @@ class WebsiteSnapshotDTO:
     快照只属于 scan，target 信息通过 scan.target 获取。
     """
     scan_id: int
-    target_id: int  # 仅用于传递数据，不保存到数据库
+    target_id: int  # 必填，用于同步到资产表
     url: str
     host: str
     title: str = ''
-    status: Optional[int] = None
+    status_code: Optional[int] = None  # 统一命名：status -> status_code
     content_length: Optional[int] = None
     location: str = ''
-    web_server: str = ''
+    webserver: str = ''  # 统一命名：web_server -> webserver
     content_type: str = ''
     tech: List[str] = None
-    body_preview: str = ''
+    response_body: str = ''
     vhost: Optional[bool] = None
+    response_headers: str = ''
     
     def __post_init__(self):
         if self.tech is None:
@@ -44,12 +45,13 @@ class WebsiteSnapshotDTO:
             url=self.url,
             host=self.host,
             title=self.title,
-            status_code=self.status,
+            status_code=self.status_code,
             content_length=self.content_length,
             location=self.location,
-            webserver=self.web_server,
+            webserver=self.webserver,
             content_type=self.content_type,
             tech=self.tech if self.tech else [],
-            body_preview=self.body_preview,
+            response_body=self.response_body,
-            vhost=self.vhost
+            vhost=self.vhost,
+            response_headers=self.response_headers,
         )

backend/apps/asset/migrations/0001_initial.py

@@ -0,0 +1,345 @@
+# Generated by Django 5.2.7 on 2026-01-06 00:55
+
+import django.contrib.postgres.fields
+import django.contrib.postgres.indexes
+import django.core.validators
+import django.db.models.deletion
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = [
+        ('scan', '0001_initial'),
+        ('targets', '0001_initial'),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='AssetStatistics',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('total_targets', models.IntegerField(default=0, help_text='目标总数')),
+                ('total_subdomains', models.IntegerField(default=0, help_text='子域名总数')),
+                ('total_ips', models.IntegerField(default=0, help_text='IP地址总数')),
+                ('total_endpoints', models.IntegerField(default=0, help_text='端点总数')),
+                ('total_websites', models.IntegerField(default=0, help_text='网站总数')),
+                ('total_vulns', models.IntegerField(default=0, help_text='漏洞总数')),
+                ('total_assets', models.IntegerField(default=0, help_text='总资产数（子域名+IP+端点+网站）')),
+                ('prev_targets', models.IntegerField(default=0, help_text='上次目标总数')),
+                ('prev_subdomains', models.IntegerField(default=0, help_text='上次子域名总数')),
+                ('prev_ips', models.IntegerField(default=0, help_text='上次IP地址总数')),
+                ('prev_endpoints', models.IntegerField(default=0, help_text='上次端点总数')),
+                ('prev_websites', models.IntegerField(default=0, help_text='上次网站总数')),
+                ('prev_vulns', models.IntegerField(default=0, help_text='上次漏洞总数')),
+                ('prev_assets', models.IntegerField(default=0, help_text='上次总资产数')),
+                ('updated_at', models.DateTimeField(auto_now=True, help_text='最后更新时间')),
+            ],
+            options={
+                'verbose_name': '资产统计',
+                'verbose_name_plural': '资产统计',
+                'db_table': 'asset_statistics',
+            },
+        ),
+        migrations.CreateModel(
+            name='StatisticsHistory',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('date', models.DateField(help_text='统计日期', unique=True)),
+                ('total_targets', models.IntegerField(default=0, help_text='目标总数')),
+                ('total_subdomains', models.IntegerField(default=0, help_text='子域名总数')),
+                ('total_ips', models.IntegerField(default=0, help_text='IP地址总数')),
+                ('total_endpoints', models.IntegerField(default=0, help_text='端点总数')),
+                ('total_websites', models.IntegerField(default=0, help_text='网站总数')),
+                ('total_vulns', models.IntegerField(default=0, help_text='漏洞总数')),
+                ('total_assets', models.IntegerField(default=0, help_text='总资产数')),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('updated_at', models.DateTimeField(auto_now=True, help_text='更新时间')),
+            ],
+            options={
+                'verbose_name': '统计历史',
+                'verbose_name_plural': '统计历史',
+                'db_table': 'statistics_history',
+                'ordering': ['-date'],
+                'indexes': [models.Index(fields=['date'], name='statistics__date_1d29cd_idx')],
+            },
+        ),
+        migrations.CreateModel(
+            name='Directory',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('url', models.CharField(help_text='完整请求 URL', max_length=2000)),
+                ('status', models.IntegerField(blank=True, help_text='HTTP 响应状态码', null=True)),
+                ('content_length', models.BigIntegerField(blank=True, help_text='响应体字节大小（Content-Length 或实际长度）', null=True)),
+                ('words', models.IntegerField(blank=True, help_text='响应体中单词数量（按空格分割）', null=True)),
+                ('lines', models.IntegerField(blank=True, help_text='响应体行数（按换行符分割）', null=True)),
+                ('content_type', models.CharField(blank=True, default='', help_text='响应头 Content-Type 值', max_length=200)),
+                ('duration', models.BigIntegerField(blank=True, help_text='请求耗时（单位：纳秒）', null=True)),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('target', models.ForeignKey(help_text='所属的扫描目标', on_delete=django.db.models.deletion.CASCADE, related_name='directories', to='targets.target')),
+            ],
+            options={
+                'verbose_name': '目录',
+                'verbose_name_plural': '目录',
+                'db_table': 'directory',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['-created_at'], name='directory_created_2cef03_idx'), models.Index(fields=['target'], name='directory_target__e310c8_idx'), models.Index(fields=['url'], name='directory_url_ba40cd_idx'), models.Index(fields=['status'], name='directory_status_40bbe6_idx'), django.contrib.postgres.indexes.GinIndex(fields=['url'], name='directory_url_trgm_idx', opclasses=['gin_trgm_ops'])],
+                'constraints': [models.UniqueConstraint(fields=('target', 'url'), name='unique_directory_url_target')],
+            },
+        ),
+        migrations.CreateModel(
+            name='DirectorySnapshot',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('url', models.CharField(help_text='目录URL', max_length=2000)),
+                ('status', models.IntegerField(blank=True, help_text='HTTP状态码', null=True)),
+                ('content_length', models.BigIntegerField(blank=True, help_text='内容长度', null=True)),
+                ('words', models.IntegerField(blank=True, help_text='响应体中单词数量（按空格分割）', null=True)),
+                ('lines', models.IntegerField(blank=True, help_text='响应体行数（按换行符分割）', null=True)),
+                ('content_type', models.CharField(blank=True, default='', help_text='响应头 Content-Type 值', max_length=200)),
+                ('duration', models.BigIntegerField(blank=True, help_text='请求耗时（单位：纳秒）', null=True)),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('scan', models.ForeignKey(help_text='所属的扫描任务', on_delete=django.db.models.deletion.CASCADE, related_name='directory_snapshots', to='scan.scan')),
+            ],
+            options={
+                'verbose_name': '目录快照',
+                'verbose_name_plural': '目录快照',
+                'db_table': 'directory_snapshot',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['scan'], name='directory_s_scan_id_c45900_idx'), models.Index(fields=['url'], name='directory_s_url_b4b72b_idx'), models.Index(fields=['status'], name='directory_s_status_e9f57e_idx'), models.Index(fields=['content_type'], name='directory_s_content_45e864_idx'), models.Index(fields=['-created_at'], name='directory_s_created_eb9d27_idx'), django.contrib.postgres.indexes.GinIndex(fields=['url'], name='dir_snap_url_trgm', opclasses=['gin_trgm_ops'])],
+                'constraints': [models.UniqueConstraint(fields=('scan', 'url'), name='unique_directory_per_scan_snapshot')],
+            },
+        ),
+        migrations.CreateModel(
+            name='Endpoint',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('url', models.TextField(help_text='最终访问的完整URL')),
+                ('host', models.CharField(blank=True, default='', help_text='主机名（域名或IP地址）', max_length=253)),
+                ('location', models.TextField(blank=True, default='', help_text='重定向地址（HTTP 3xx 响应头 Location）')),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('title', models.TextField(blank=True, default='', help_text='网页标题（HTML <title> 标签内容）')),
+                ('webserver', models.TextField(blank=True, default='', help_text='服务器类型（HTTP 响应头 Server 值）')),
+                ('response_body', models.TextField(blank=True, default='', help_text='HTTP响应体')),
+                ('content_type', models.TextField(blank=True, default='', help_text='响应类型（HTTP Content-Type 响应头）')),
+                ('tech', django.contrib.postgres.fields.ArrayField(base_field=models.CharField(max_length=100), blank=True, default=list, help_text='技术栈（服务器/框架/语言等）', size=None)),
+                ('status_code', models.IntegerField(blank=True, help_text='HTTP状态码', null=True)),
+                ('content_length', models.IntegerField(blank=True, help_text='响应体大小（单位字节）', null=True)),
+                ('vhost', models.BooleanField(blank=True, help_text='是否支持虚拟主机', null=True)),
+                ('matched_gf_patterns', django.contrib.postgres.fields.ArrayField(base_field=models.CharField(max_length=100), blank=True, default=list, help_text='匹配的GF模式列表，用于识别敏感端点（如api, debug, config等）', size=None)),
+                ('response_headers', models.TextField(blank=True, default='', help_text='原始HTTP响应头')),
+                ('target', models.ForeignKey(help_text='所属的扫描目标（主关联字段，表示所属关系，不能为空）', on_delete=django.db.models.deletion.CASCADE, related_name='endpoints', to='targets.target')),
+            ],
+            options={
+                'verbose_name': '端点',
+                'verbose_name_plural': '端点',
+                'db_table': 'endpoint',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['-created_at'], name='endpoint_created_44fe9c_idx'), models.Index(fields=['target'], name='endpoint_target__7f9065_idx'), models.Index(fields=['url'], name='endpoint_url_30f66e_idx'), models.Index(fields=['host'], name='endpoint_host_5b4cc8_idx'), models.Index(fields=['status_code'], name='endpoint_status__5d4fdd_idx'), models.Index(fields=['title'], name='endpoint_title_29e26c_idx'), django.contrib.postgres.indexes.GinIndex(fields=['tech'], name='endpoint_tech_2bfa7c_gin'), django.contrib.postgres.indexes.GinIndex(fields=['response_headers'], name='endpoint_resp_headers_trgm_idx', opclasses=['gin_trgm_ops']), django.contrib.postgres.indexes.GinIndex(fields=['url'], name='endpoint_url_trgm_idx', opclasses=['gin_trgm_ops']), django.contrib.postgres.indexes.GinIndex(fields=['title'], name='endpoint_title_trgm_idx', opclasses=['gin_trgm_ops'])],
+                'constraints': [models.UniqueConstraint(fields=('url', 'target'), name='unique_endpoint_url_target')],
+            },
+        ),
+        migrations.CreateModel(
+            name='EndpointSnapshot',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('url', models.TextField(help_text='端点URL')),
+                ('host', models.CharField(blank=True, default='', help_text='主机名（域名或IP地址）', max_length=253)),
+                ('title', models.TextField(blank=True, default='', help_text='页面标题')),
+                ('status_code', models.IntegerField(blank=True, help_text='HTTP状态码', null=True)),
+                ('content_length', models.IntegerField(blank=True, help_text='内容长度', null=True)),
+                ('location', models.TextField(blank=True, default='', help_text='重定向位置')),
+                ('webserver', models.TextField(blank=True, default='', help_text='Web服务器')),
+                ('content_type', models.TextField(blank=True, default='', help_text='内容类型')),
+                ('tech', django.contrib.postgres.fields.ArrayField(base_field=models.CharField(max_length=100), blank=True, default=list, help_text='技术栈', size=None)),
+                ('response_body', models.TextField(blank=True, default='', help_text='HTTP响应体')),
+                ('vhost', models.BooleanField(blank=True, help_text='虚拟主机标志', null=True)),
+                ('matched_gf_patterns', django.contrib.postgres.fields.ArrayField(base_field=models.CharField(max_length=100), blank=True, default=list, help_text='匹配的GF模式列表', size=None)),
+                ('response_headers', models.TextField(blank=True, default='', help_text='原始HTTP响应头')),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('scan', models.ForeignKey(help_text='所属的扫描任务', on_delete=django.db.models.deletion.CASCADE, related_name='endpoint_snapshots', to='scan.scan')),
+            ],
+            options={
+                'verbose_name': '端点快照',
+                'verbose_name_plural': '端点快照',
+                'db_table': 'endpoint_snapshot',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['scan'], name='endpoint_sn_scan_id_6ac9a7_idx'), models.Index(fields=['url'], name='endpoint_sn_url_205160_idx'), models.Index(fields=['host'], name='endpoint_sn_host_577bfd_idx'), models.Index(fields=['title'], name='endpoint_sn_title_516a05_idx'), models.Index(fields=['status_code'], name='endpoint_sn_status__83efb0_idx'), models.Index(fields=['webserver'], name='endpoint_sn_webserv_66be83_idx'), models.Index(fields=['-created_at'], name='endpoint_sn_created_21fb5b_idx'), django.contrib.postgres.indexes.GinIndex(fields=['tech'], name='endpoint_sn_tech_0d0752_gin'), django.contrib.postgres.indexes.GinIndex(fields=['response_headers'], name='ep_snap_resp_hdr_trgm', opclasses=['gin_trgm_ops']), django.contrib.postgres.indexes.GinIndex(fields=['url'], name='ep_snap_url_trgm', opclasses=['gin_trgm_ops']), django.contrib.postgres.indexes.GinIndex(fields=['title'], name='ep_snap_title_trgm', opclasses=['gin_trgm_ops'])],
+                'constraints': [models.UniqueConstraint(fields=('scan', 'url'), name='unique_endpoint_per_scan_snapshot')],
+            },
+        ),
+        migrations.CreateModel(
+            name='HostPortMapping',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('host', models.CharField(help_text='主机名（域名或IP）', max_length=1000)),
+                ('ip', models.GenericIPAddressField(help_text='IP地址')),
+                ('port', models.IntegerField(help_text='端口号（1-65535）', validators=[django.core.validators.MinValueValidator(1, message='端口号必须大于等于1'), django.core.validators.MaxValueValidator(65535, message='端口号必须小于等于65535')])),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('target', models.ForeignKey(help_text='所属的扫描目标', on_delete=django.db.models.deletion.CASCADE, related_name='host_port_mappings', to='targets.target')),
+            ],
+            options={
+                'verbose_name': '主机端口映射',
+                'verbose_name_plural': '主机端口映射',
+                'db_table': 'host_port_mapping',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['target'], name='host_port_m_target__943e9b_idx'), models.Index(fields=['host'], name='host_port_m_host_f78363_idx'), models.Index(fields=['ip'], name='host_port_m_ip_2e6f02_idx'), models.Index(fields=['port'], name='host_port_m_port_9fb9ff_idx'), models.Index(fields=['host', 'ip'], name='host_port_m_host_3ce245_idx'), models.Index(fields=['-created_at'], name='host_port_m_created_11cd22_idx')],
+                'constraints': [models.UniqueConstraint(fields=('target', 'host', 'ip', 'port'), name='unique_target_host_ip_port')],
+            },
+        ),
+        migrations.CreateModel(
+            name='HostPortMappingSnapshot',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('host', models.CharField(help_text='主机名（域名或IP）', max_length=1000)),
+                ('ip', models.GenericIPAddressField(help_text='IP地址')),
+                ('port', models.IntegerField(help_text='端口号（1-65535）', validators=[django.core.validators.MinValueValidator(1, message='端口号必须大于等于1'), django.core.validators.MaxValueValidator(65535, message='端口号必须小于等于65535')])),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('scan', models.ForeignKey(help_text='所属的扫描任务（主关联）', on_delete=django.db.models.deletion.CASCADE, related_name='host_port_mapping_snapshots', to='scan.scan')),
+            ],
+            options={
+                'verbose_name': '主机端口映射快照',
+                'verbose_name_plural': '主机端口映射快照',
+                'db_table': 'host_port_mapping_snapshot',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['scan'], name='host_port_m_scan_id_50ba0b_idx'), models.Index(fields=['host'], name='host_port_m_host_e99054_idx'), models.Index(fields=['ip'], name='host_port_m_ip_54818c_idx'), models.Index(fields=['port'], name='host_port_m_port_ed7b48_idx'), models.Index(fields=['host', 'ip'], name='host_port_m_host_8a463a_idx'), models.Index(fields=['scan', 'host'], name='host_port_m_scan_id_426fdb_idx'), models.Index(fields=['-created_at'], name='host_port_m_created_fb28b8_idx')],
+                'constraints': [models.UniqueConstraint(fields=('scan', 'host', 'ip', 'port'), name='unique_scan_host_ip_port_snapshot')],
+            },
+        ),
+        migrations.CreateModel(
+            name='Subdomain',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('name', models.CharField(help_text='子域名名称', max_length=1000)),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('target', models.ForeignKey(help_text='所属的扫描目标（主关联字段，表示所属关系，不能为空）', on_delete=django.db.models.deletion.CASCADE, related_name='subdomains', to='targets.target')),
+            ],
+            options={
+                'verbose_name': '子域名',
+                'verbose_name_plural': '子域名',
+                'db_table': 'subdomain',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['-created_at'], name='subdomain_created_e187a8_idx'), models.Index(fields=['name', 'target'], name='subdomain_name_60e1d0_idx'), models.Index(fields=['target'], name='subdomain_target__e409f0_idx'), models.Index(fields=['name'], name='subdomain_name_d40ba7_idx'), django.contrib.postgres.indexes.GinIndex(fields=['name'], name='subdomain_name_trgm_idx', opclasses=['gin_trgm_ops'])],
+                'constraints': [models.UniqueConstraint(fields=('name', 'target'), name='unique_subdomain_name_target')],
+            },
+        ),
+        migrations.CreateModel(
+            name='SubdomainSnapshot',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('name', models.CharField(help_text='子域名名称', max_length=1000)),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('scan', models.ForeignKey(help_text='所属的扫描任务', on_delete=django.db.models.deletion.CASCADE, related_name='subdomain_snapshots', to='scan.scan')),
+            ],
+            options={
+                'verbose_name': '子域名快照',
+                'verbose_name_plural': '子域名快照',
+                'db_table': 'subdomain_snapshot',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['scan'], name='subdomain_s_scan_id_68c253_idx'), models.Index(fields=['name'], name='subdomain_s_name_2da42b_idx'), models.Index(fields=['-created_at'], name='subdomain_s_created_d2b48e_idx'), django.contrib.postgres.indexes.GinIndex(fields=['name'], name='subdomain_snap_name_trgm', opclasses=['gin_trgm_ops'])],
+                'constraints': [models.UniqueConstraint(fields=('scan', 'name'), name='unique_subdomain_per_scan_snapshot')],
+            },
+        ),
+        migrations.CreateModel(
+            name='Vulnerability',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('url', models.CharField(help_text='漏洞所在的URL', max_length=2000)),
+                ('vuln_type', models.CharField(help_text='漏洞类型（如 xss, sqli）', max_length=100)),
+                ('severity', models.CharField(choices=[('unknown', '未知'), ('info', '信息'), ('low', '低'), ('medium', '中'), ('high', '高'), ('critical', '危急')], default='unknown', help_text='严重性（未知/信息/低/中/高/危急）', max_length=20)),
+                ('source', models.CharField(blank=True, default='', help_text='来源工具（如 dalfox, nuclei, crlfuzz）', max_length=50)),
+                ('cvss_score', models.DecimalField(blank=True, decimal_places=1, help_text='CVSS 评分（0.0-10.0）', max_digits=3, null=True)),
+                ('description', models.TextField(blank=True, default='', help_text='漏洞描述')),
+                ('raw_output', models.JSONField(blank=True, default=dict, help_text='工具原始输出')),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('target', models.ForeignKey(help_text='所属的扫描目标', on_delete=django.db.models.deletion.CASCADE, related_name='vulnerabilities', to='targets.target')),
+            ],
+            options={
+                'verbose_name': '漏洞',
+                'verbose_name_plural': '漏洞',
+                'db_table': 'vulnerability',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['target'], name='vulnerabili_target__755a02_idx'), models.Index(fields=['vuln_type'], name='vulnerabili_vuln_ty_3010cd_idx'), models.Index(fields=['severity'], name='vulnerabili_severit_1a798b_idx'), models.Index(fields=['source'], name='vulnerabili_source_7c7552_idx'), models.Index(fields=['url'], name='vulnerabili_url_4dcc4d_idx'), models.Index(fields=['-created_at'], name='vulnerabili_created_e25ff7_idx')],
+            },
+        ),
+        migrations.CreateModel(
+            name='VulnerabilitySnapshot',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('url', models.CharField(help_text='漏洞所在的URL', max_length=2000)),
+                ('vuln_type', models.CharField(help_text='漏洞类型（如 xss, sqli）', max_length=100)),
+                ('severity', models.CharField(choices=[('unknown', '未知'), ('info', '信息'), ('low', '低'), ('medium', '中'), ('high', '高'), ('critical', '危急')], default='unknown', help_text='严重性（未知/信息/低/中/高/危急）', max_length=20)),
+                ('source', models.CharField(blank=True, default='', help_text='来源工具（如 dalfox, nuclei, crlfuzz）', max_length=50)),
+                ('cvss_score', models.DecimalField(blank=True, decimal_places=1, help_text='CVSS 评分（0.0-10.0）', max_digits=3, null=True)),
+                ('description', models.TextField(blank=True, default='', help_text='漏洞描述')),
+                ('raw_output', models.JSONField(blank=True, default=dict, help_text='工具原始输出')),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('scan', models.ForeignKey(help_text='所属的扫描任务', on_delete=django.db.models.deletion.CASCADE, related_name='vulnerability_snapshots', to='scan.scan')),
+            ],
+            options={
+                'verbose_name': '漏洞快照',
+                'verbose_name_plural': '漏洞快照',
+                'db_table': 'vulnerability_snapshot',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['scan'], name='vulnerabili_scan_id_7b81c9_idx'), models.Index(fields=['url'], name='vulnerabili_url_11a707_idx'), models.Index(fields=['vuln_type'], name='vulnerabili_vuln_ty_6b90ee_idx'), models.Index(fields=['severity'], name='vulnerabili_severit_4eae0d_idx'), models.Index(fields=['source'], name='vulnerabili_source_968b1f_idx'), models.Index(fields=['-created_at'], name='vulnerabili_created_53a12e_idx')],
+            },
+        ),
+        migrations.CreateModel(
+            name='WebSite',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('url', models.TextField(help_text='最终访问的完整URL')),
+                ('host', models.CharField(blank=True, default='', help_text='主机名（域名或IP地址）', max_length=253)),
+                ('location', models.TextField(blank=True, default='', help_text='重定向地址（HTTP 3xx 响应头 Location）')),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('title', models.TextField(blank=True, default='', help_text='网页标题（HTML <title> 标签内容）')),
+                ('webserver', models.TextField(blank=True, default='', help_text='服务器类型（HTTP 响应头 Server 值）')),
+                ('response_body', models.TextField(blank=True, default='', help_text='HTTP响应体')),
+                ('content_type', models.TextField(blank=True, default='', help_text='响应类型（HTTP Content-Type 响应头）')),
+                ('tech', django.contrib.postgres.fields.ArrayField(base_field=models.CharField(max_length=100), blank=True, default=list, help_text='技术栈（服务器/框架/语言等）', size=None)),
+                ('status_code', models.IntegerField(blank=True, help_text='HTTP状态码', null=True)),
+                ('content_length', models.IntegerField(blank=True, help_text='响应体大小（单位字节）', null=True)),
+                ('vhost', models.BooleanField(blank=True, help_text='是否支持虚拟主机', null=True)),
+                ('response_headers', models.TextField(blank=True, default='', help_text='原始HTTP响应头')),
+                ('target', models.ForeignKey(help_text='所属的扫描目标（主关联字段，表示所属关系，不能为空）', on_delete=django.db.models.deletion.CASCADE, related_name='websites', to='targets.target')),
+            ],
+            options={
+                'verbose_name': '站点',
+                'verbose_name_plural': '站点',
+                'db_table': 'website',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['-created_at'], name='website_created_c9cfd2_idx'), models.Index(fields=['url'], name='website_url_b18883_idx'), models.Index(fields=['host'], name='website_host_996b50_idx'), models.Index(fields=['target'], name='website_target__2a353b_idx'), models.Index(fields=['title'], name='website_title_c2775b_idx'), models.Index(fields=['status_code'], name='website_status__51663d_idx'), django.contrib.postgres.indexes.GinIndex(fields=['tech'], name='website_tech_e3f0cb_gin'), django.contrib.postgres.indexes.GinIndex(fields=['response_headers'], name='website_resp_headers_trgm_idx', opclasses=['gin_trgm_ops']), django.contrib.postgres.indexes.GinIndex(fields=['url'], name='website_url_trgm_idx', opclasses=['gin_trgm_ops']), django.contrib.postgres.indexes.GinIndex(fields=['title'], name='website_title_trgm_idx', opclasses=['gin_trgm_ops'])],
+                'constraints': [models.UniqueConstraint(fields=('url', 'target'), name='unique_website_url_target')],
+            },
+        ),
+        migrations.CreateModel(
+            name='WebsiteSnapshot',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('url', models.TextField(help_text='站点URL')),
+                ('host', models.CharField(blank=True, default='', help_text='主机名（域名或IP地址）', max_length=253)),
+                ('title', models.TextField(blank=True, default='', help_text='页面标题')),
+                ('status_code', models.IntegerField(blank=True, help_text='HTTP状态码', null=True)),
+                ('content_length', models.BigIntegerField(blank=True, help_text='内容长度', null=True)),
+                ('location', models.TextField(blank=True, default='', help_text='重定向位置')),
+                ('webserver', models.TextField(blank=True, default='', help_text='Web服务器')),
+                ('content_type', models.TextField(blank=True, default='', help_text='内容类型')),
+                ('tech', django.contrib.postgres.fields.ArrayField(base_field=models.CharField(max_length=100), blank=True, default=list, help_text='技术栈', size=None)),
+                ('response_body', models.TextField(blank=True, default='', help_text='HTTP响应体')),
+                ('vhost', models.BooleanField(blank=True, help_text='虚拟主机标志', null=True)),
+                ('response_headers', models.TextField(blank=True, default='', help_text='原始HTTP响应头')),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('scan', models.ForeignKey(help_text='所属的扫描任务', on_delete=django.db.models.deletion.CASCADE, related_name='website_snapshots', to='scan.scan')),
+            ],
+            options={
+                'verbose_name': '网站快照',
+                'verbose_name_plural': '网站快照',
+                'db_table': 'website_snapshot',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['scan'], name='website_sna_scan_id_26b6dc_idx'), models.Index(fields=['url'], name='website_sna_url_801a70_idx'), models.Index(fields=['host'], name='website_sna_host_348fe1_idx'), models.Index(fields=['title'], name='website_sna_title_b1a5ee_idx'), models.Index(fields=['-created_at'], name='website_sna_created_2c149a_idx'), django.contrib.postgres.indexes.GinIndex(fields=['tech'], name='website_sna_tech_3d6d2f_gin'), django.contrib.postgres.indexes.GinIndex(fields=['response_headers'], name='ws_snap_resp_hdr_trgm', opclasses=['gin_trgm_ops']), django.contrib.postgres.indexes.GinIndex(fields=['url'], name='ws_snap_url_trgm', opclasses=['gin_trgm_ops']), django.contrib.postgres.indexes.GinIndex(fields=['title'], name='ws_snap_title_trgm', opclasses=['gin_trgm_ops'])],
+                'constraints': [models.UniqueConstraint(fields=('scan', 'url'), name='unique_website_per_scan_snapshot')],
+            },
+        ),
+    ]

backend/apps/asset/migrations/0002_create_search_views.py

@@ -0,0 +1,104 @@
+"""
+创建资产搜索物化视图（使用 pg_ivm 增量维护）
+
+这些视图用于资产搜索功能，提供高性能的全文搜索能力。
+"""
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+    """创建资产搜索所需的增量物化视图"""
+
+    dependencies = [
+        ('asset', '0001_initial'),
+    ]
+
+    operations = [
+        # 1. 确保 pg_ivm 扩展已安装
+        migrations.RunSQL(
+            sql="CREATE EXTENSION IF NOT EXISTS pg_ivm;",
+            reverse_sql="DROP EXTENSION IF EXISTS pg_ivm;",
+        ),
+        
+        # 2. 创建 Website 搜索视图
+        # 注意：pg_ivm 不支持 ArrayField，所以 tech 字段需要从原表 JOIN 获取
+        migrations.RunSQL(
+            sql="""
+                SELECT pgivm.create_immv('asset_search_view', $$
+                    SELECT 
+                        w.id,
+                        w.url,
+                        w.host,
+                        w.title,
+                        w.status_code,
+                        w.response_headers,
+                        w.response_body,
+                        w.content_type,
+                        w.content_length,
+                        w.webserver,
+                        w.location,
+                        w.vhost,
+                        w.created_at,
+                        w.target_id
+                    FROM website w
+                $$);
+            """,
+            reverse_sql="DROP TABLE IF EXISTS asset_search_view CASCADE;",
+        ),
+        
+        # 3. 创建 Endpoint 搜索视图
+        migrations.RunSQL(
+            sql="""
+                SELECT pgivm.create_immv('endpoint_search_view', $$
+                    SELECT 
+                        e.id,
+                        e.url,
+                        e.host,
+                        e.title,
+                        e.status_code,
+                        e.response_headers,
+                        e.response_body,
+                        e.content_type,
+                        e.content_length,
+                        e.webserver,
+                        e.location,
+                        e.vhost,
+                        e.created_at,
+                        e.target_id
+                    FROM endpoint e
+                $$);
+            """,
+            reverse_sql="DROP TABLE IF EXISTS endpoint_search_view CASCADE;",
+        ),
+        
+        # 4. 为搜索视图创建索引（加速查询）
+        migrations.RunSQL(
+            sql=[
+                # Website 搜索视图索引
+                "CREATE INDEX IF NOT EXISTS asset_search_view_host_idx ON asset_search_view (host);",
+                "CREATE INDEX IF NOT EXISTS asset_search_view_url_idx ON asset_search_view (url);",
+                "CREATE INDEX IF NOT EXISTS asset_search_view_title_idx ON asset_search_view (title);",
+                "CREATE INDEX IF NOT EXISTS asset_search_view_status_idx ON asset_search_view (status_code);",
+                "CREATE INDEX IF NOT EXISTS asset_search_view_created_idx ON asset_search_view (created_at DESC);",
+                # Endpoint 搜索视图索引
+                "CREATE INDEX IF NOT EXISTS endpoint_search_view_host_idx ON endpoint_search_view (host);",
+                "CREATE INDEX IF NOT EXISTS endpoint_search_view_url_idx ON endpoint_search_view (url);",
+                "CREATE INDEX IF NOT EXISTS endpoint_search_view_title_idx ON endpoint_search_view (title);",
+                "CREATE INDEX IF NOT EXISTS endpoint_search_view_status_idx ON endpoint_search_view (status_code);",
+                "CREATE INDEX IF NOT EXISTS endpoint_search_view_created_idx ON endpoint_search_view (created_at DESC);",
+            ],
+            reverse_sql=[
+                "DROP INDEX IF EXISTS asset_search_view_host_idx;",
+                "DROP INDEX IF EXISTS asset_search_view_url_idx;",
+                "DROP INDEX IF EXISTS asset_search_view_title_idx;",
+                "DROP INDEX IF EXISTS asset_search_view_status_idx;",
+                "DROP INDEX IF EXISTS asset_search_view_created_idx;",
+                "DROP INDEX IF EXISTS endpoint_search_view_host_idx;",
+                "DROP INDEX IF EXISTS endpoint_search_view_url_idx;",
+                "DROP INDEX IF EXISTS endpoint_search_view_title_idx;",
+                "DROP INDEX IF EXISTS endpoint_search_view_status_idx;",
+                "DROP INDEX IF EXISTS endpoint_search_view_created_idx;",
+            ],
+        ),
+    ]

backend/apps/asset/migrations/0003_add_screenshot_models.py

@@ -0,0 +1,53 @@
+# Generated by Django 5.2.7 on 2026-01-07 02:21
+
+import django.db.models.deletion
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('asset', '0002_create_search_views'),
+        ('scan', '0001_initial'),
+        ('targets', '0001_initial'),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='Screenshot',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('url', models.TextField(help_text='截图对应的 URL')),
+                ('image', models.BinaryField(help_text='截图 WebP 二进制数据（压缩后）')),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('updated_at', models.DateTimeField(auto_now=True, help_text='更新时间')),
+                ('target', models.ForeignKey(help_text='所属目标', on_delete=django.db.models.deletion.CASCADE, related_name='screenshots', to='targets.target')),
+            ],
+            options={
+                'verbose_name': '截图',
+                'verbose_name_plural': '截图',
+                'db_table': 'screenshot',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['target'], name='screenshot_target__2f01f6_idx'), models.Index(fields=['-created_at'], name='screenshot_created_c0ad4b_idx')],
+                'constraints': [models.UniqueConstraint(fields=('target', 'url'), name='unique_screenshot_per_target')],
+            },
+        ),
+        migrations.CreateModel(
+            name='ScreenshotSnapshot',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('url', models.TextField(help_text='截图对应的 URL')),
+                ('image', models.BinaryField(help_text='截图 WebP 二进制数据（压缩后）')),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('scan', models.ForeignKey(help_text='所属的扫描任务', on_delete=django.db.models.deletion.CASCADE, related_name='screenshot_snapshots', to='scan.scan')),
+            ],
+            options={
+                'verbose_name': '截图快照',
+                'verbose_name_plural': '截图快照',
+                'db_table': 'screenshot_snapshot',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['scan'], name='screenshot__scan_id_fb8c4d_idx'), models.Index(fields=['-created_at'], name='screenshot__created_804117_idx')],
+                'constraints': [models.UniqueConstraint(fields=('scan', 'url'), name='unique_screenshot_per_scan_snapshot')],
+            },
+        ),
+    ]

backend/apps/asset/migrations/0004_add_status_code_to_screenshot.py

@@ -0,0 +1,23 @@
+# Generated by Django 5.2.7 on 2026-01-07 13:29
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('asset', '0003_add_screenshot_models'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='screenshot',
+            name='status_code',
+            field=models.SmallIntegerField(blank=True, help_text='HTTP 响应状态码', null=True),
+        ),
+        migrations.AddField(
+            model_name='screenshotsnapshot',
+            name='status_code',
+            field=models.SmallIntegerField(blank=True, help_text='HTTP 响应状态码', null=True),
+        ),
+    ]

backend/apps/asset/models/__init__.py

@@ -20,6 +20,12 @@ from .snapshot_models import (
     VulnerabilitySnapshot,
 )
 
+# 截图模型
+from .screenshot_models import (
+    Screenshot,
+    ScreenshotSnapshot,
+)
+
 # 统计模型
 from .statistics_models import AssetStatistics, StatisticsHistory
 
@@ -39,6 +45,9 @@ __all__ = [
     'HostPortMappingSnapshot',
     'EndpointSnapshot',
     'VulnerabilitySnapshot',
+    # 截图模型
+    'Screenshot',
+    'ScreenshotSnapshot',
     # 统计模型
     'AssetStatistics',
     'StatisticsHistory',

backend/apps/asset/models/asset_models.py

@@ -1,6 +1,7 @@
 
 from django.db import models
 from django.contrib.postgres.fields import ArrayField
+from django.contrib.postgres.indexes import GinIndex
 from django.core.validators import MinValueValidator, MaxValueValidator
 
 
@@ -34,6 +35,12 @@ class Subdomain(models.Model):
             models.Index(fields=['name', 'target']),  # 复合索引，优化 get_by_names_and_target_id 批量查询
             models.Index(fields=['target']),     # 优化从target_id快速查找下面的子域名
             models.Index(fields=['name']),            # 优化从name快速查找子域名，搜索场景
+            # pg_trgm GIN 索引，支持 LIKE '%keyword%' 模糊搜索
+            GinIndex(
+                name='subdomain_name_trgm_idx',
+                fields=['name'],
+                opclasses=['gin_trgm_ops']
+            ),
         ]
         constraints = [
             # 普通唯一约束：name + target 组合唯一
@@ -58,40 +65,35 @@ class Endpoint(models.Model):
         help_text='所属的扫描目标（主关联字段，表示所属关系，不能为空）'
     )
     
-    url = models.CharField(max_length=2000, help_text='最终访问的完整URL')
+    url = models.TextField(help_text='最终访问的完整URL')
     host = models.CharField(
         max_length=253,
         blank=True,
         default='',
         help_text='主机名（域名或IP地址）'
     )
-    location = models.CharField(
+    location = models.TextField(
-        max_length=1000,
         blank=True,
         default='',
         help_text='重定向地址（HTTP 3xx 响应头 Location）'
     )
     created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
-    title = models.CharField(
+    title = models.TextField(
-        max_length=1000,
         blank=True,
         default='',
         help_text='网页标题（HTML <title> 标签内容）'
     )
-    webserver = models.CharField(
+    webserver = models.TextField(
-        max_length=200,
         blank=True,
         default='',
         help_text='服务器类型（HTTP 响应头 Server 值）'
     )
-    body_preview = models.CharField(
+    response_body = models.TextField(
-        max_length=1000,
         blank=True,
         default='',
-        help_text='响应正文前N个字符（默认100个字符）'
+        help_text='HTTP响应体'
     )
-    content_type = models.CharField(
+    content_type = models.TextField(
-        max_length=200,
         blank=True,
         default='',
         help_text='响应类型（HTTP Content-Type 响应头）'
@@ -123,6 +125,11 @@ class Endpoint(models.Model):
         default=list,
         help_text='匹配的GF模式列表，用于识别敏感端点（如api, debug, config等）'
     )
+    response_headers = models.TextField(
+        blank=True,
+        default='',
+        help_text='原始HTTP响应头'
+    )
 
     class Meta:
         db_table = 'endpoint'
@@ -131,11 +138,28 @@ class Endpoint(models.Model):
         ordering = ['-created_at']
         indexes = [
             models.Index(fields=['-created_at']),
-            models.Index(fields=['target']),       # 优化从target_id快速查找下面的端点（主关联字段）
+            models.Index(fields=['target']),       # 优化从 target_id快速查找下面的端点（主关联字段）
             models.Index(fields=['url']),          # URL索引，优化查询性能
             models.Index(fields=['host']),         # host索引，优化根据主机名查询
             models.Index(fields=['status_code']),  # 状态码索引，优化筛选
             models.Index(fields=['title']),        # title索引，优化智能过滤搜索
+            GinIndex(fields=['tech']),             # GIN索引，优化 tech 数组字段的 __contains 查询
+            # pg_trgm GIN 索引，支持 LIKE '%keyword%' 模糊搜索
+            GinIndex(
+                name='endpoint_resp_headers_trgm_idx',
+                fields=['response_headers'],
+                opclasses=['gin_trgm_ops']
+            ),
+            GinIndex(
+                name='endpoint_url_trgm_idx',
+                fields=['url'],
+                opclasses=['gin_trgm_ops']
+            ),
+            GinIndex(
+                name='endpoint_title_trgm_idx',
+                fields=['title'],
+                opclasses=['gin_trgm_ops']
+            ),
         ]
         constraints = [
             # 普通唯一约束：url + target 组合唯一
@@ -160,40 +184,35 @@ class WebSite(models.Model):
         help_text='所属的扫描目标（主关联字段，表示所属关系，不能为空）'
     )
 
-    url = models.CharField(max_length=2000, help_text='最终访问的完整URL')
+    url = models.TextField(help_text='最终访问的完整URL')
     host = models.CharField(
         max_length=253,
         blank=True,
         default='',
         help_text='主机名（域名或IP地址）'
     )
-    location = models.CharField(
+    location = models.TextField(
-        max_length=1000,
         blank=True,
         default='',
         help_text='重定向地址（HTTP 3xx 响应头 Location）'
     )
     created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
-    title = models.CharField(
+    title = models.TextField(
-        max_length=1000,
         blank=True,
         default='',
         help_text='网页标题（HTML <title> 标签内容）'
     )
-    webserver = models.CharField(
+    webserver = models.TextField(
-        max_length=200,
         blank=True,
         default='',
         help_text='服务器类型（HTTP 响应头 Server 值）'
     )
-    body_preview = models.CharField(
+    response_body = models.TextField(
-        max_length=1000,
         blank=True,
         default='',
-        help_text='响应正文前N个字符（默认100个字符）'
+        help_text='HTTP响应体'
     )
-    content_type = models.CharField(
+    content_type = models.TextField(
-        max_length=200,
         blank=True,
         default='',
         help_text='响应类型（HTTP Content-Type 响应头）'
@@ -219,6 +238,11 @@ class WebSite(models.Model):
         blank=True,
         help_text='是否支持虚拟主机'
     )
+    response_headers = models.TextField(
+        blank=True,
+        default='',
+        help_text='原始HTTP响应头'
+    )
 
     class Meta:
         db_table = 'website'
@@ -229,9 +253,26 @@ class WebSite(models.Model):
             models.Index(fields=['-created_at']),
             models.Index(fields=['url']),  # URL索引，优化查询性能
             models.Index(fields=['host']),  # host索引，优化根据主机名查询
-            models.Index(fields=['target']),     # 优化从target_id快速查找下面的站点
+            models.Index(fields=['target']),     # 优化从 target_id快速查找下面的站点
             models.Index(fields=['title']),      # title索引，优化智能过滤搜索
             models.Index(fields=['status_code']),  # 状态码索引，优化智能过滤搜索
+            GinIndex(fields=['tech']),  # GIN索引，优化 tech 数组字段的 __contains 查询
+            # pg_trgm GIN 索引，支持 LIKE '%keyword%' 模糊搜索
+            GinIndex(
+                name='website_resp_headers_trgm_idx',
+                fields=['response_headers'],
+                opclasses=['gin_trgm_ops']
+            ),
+            GinIndex(
+                name='website_url_trgm_idx',
+                fields=['url'],
+                opclasses=['gin_trgm_ops']
+            ),
+            GinIndex(
+                name='website_title_trgm_idx',
+                fields=['title'],
+                opclasses=['gin_trgm_ops']
+            ),
         ]
         constraints = [
             # 普通唯一约束：url + target 组合唯一
@@ -308,6 +349,12 @@ class Directory(models.Model):
             models.Index(fields=['target']),     # 优化从target_id快速查找下面的目录
             models.Index(fields=['url']),        # URL索引，优化搜索和唯一约束
             models.Index(fields=['status']),     # 状态码索引，优化筛选
+            # pg_trgm GIN 索引，支持 LIKE '%keyword%' 模糊搜索
+            GinIndex(
+                name='directory_url_trgm_idx',
+                fields=['url'],
+                opclasses=['gin_trgm_ops']
+            ),
         ]
         constraints = [
             # 普通唯一约束：target + url 组合唯一

backend/apps/asset/models/screenshot_models.py

@@ -0,0 +1,80 @@
+from django.db import models
+
+
+class ScreenshotSnapshot(models.Model):
+    """
+    截图快照
+    
+    记录：某次扫描中捕获的网站截图
+    """
+
+    id = models.AutoField(primary_key=True)
+    scan = models.ForeignKey(
+        'scan.Scan',
+        on_delete=models.CASCADE,
+        related_name='screenshot_snapshots',
+        help_text='所属的扫描任务'
+    )
+    url = models.TextField(help_text='截图对应的 URL')
+    status_code = models.SmallIntegerField(null=True, blank=True, help_text='HTTP 响应状态码')
+    image = models.BinaryField(help_text='截图 WebP 二进制数据（压缩后）')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
+
+    class Meta:
+        db_table = 'screenshot_snapshot'
+        verbose_name = '截图快照'
+        verbose_name_plural = '截图快照'
+        ordering = ['-created_at']
+        indexes = [
+            models.Index(fields=['scan']),
+            models.Index(fields=['-created_at']),
+        ]
+        constraints = [
+            models.UniqueConstraint(
+                fields=['scan', 'url'],
+                name='unique_screenshot_per_scan_snapshot'
+            ),
+        ]
+
+    def __str__(self):
+        return f'{self.url} (Scan #{self.scan_id})'
+
+
+class Screenshot(models.Model):
+    """
+    截图资产
+    
+    存储：目标的最新截图（从快照同步）
+    """
+
+    id = models.AutoField(primary_key=True)
+    target = models.ForeignKey(
+        'targets.Target',
+        on_delete=models.CASCADE,
+        related_name='screenshots',
+        help_text='所属目标'
+    )
+    url = models.TextField(help_text='截图对应的 URL')
+    status_code = models.SmallIntegerField(null=True, blank=True, help_text='HTTP 响应状态码')
+    image = models.BinaryField(help_text='截图 WebP 二进制数据（压缩后）')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
+    updated_at = models.DateTimeField(auto_now=True, help_text='更新时间')
+
+    class Meta:
+        db_table = 'screenshot'
+        verbose_name = '截图'
+        verbose_name_plural = '截图'
+        ordering = ['-created_at']
+        indexes = [
+            models.Index(fields=['target']),
+            models.Index(fields=['-created_at']),
+        ]
+        constraints = [
+            models.UniqueConstraint(
+                fields=['target', 'url'],
+                name='unique_screenshot_per_target'
+            ),
+        ]
+
+    def __str__(self):
+        return f'{self.url} (Target #{self.target_id})'

backend/apps/asset/models/snapshot_models.py

@@ -1,5 +1,6 @@
 from django.db import models
 from django.contrib.postgres.fields import ArrayField
+from django.contrib.postgres.indexes import GinIndex
 from django.core.validators import MinValueValidator, MaxValueValidator
 
 
@@ -26,6 +27,12 @@ class SubdomainSnapshot(models.Model):
             models.Index(fields=['scan']),
             models.Index(fields=['name']),
             models.Index(fields=['-created_at']),
+            # pg_trgm GIN 索引，支持 LIKE '%keyword%' 模糊搜索
+            GinIndex(
+                name='subdomain_snap_name_trgm',
+                fields=['name'],
+                opclasses=['gin_trgm_ops']
+            ),
         ]
         constraints = [
             # 唯一约束：同一次扫描中，同一个子域名只能记录一次
@@ -54,22 +61,27 @@ class WebsiteSnapshot(models.Model):
     )
     
     # 扫描结果数据
-    url = models.CharField(max_length=2000, help_text='站点URL')
+    url = models.TextField(help_text='站点URL')
     host = models.CharField(max_length=253, blank=True, default='', help_text='主机名（域名或IP地址）')
-    title = models.CharField(max_length=500, blank=True, default='', help_text='页面标题')
+    title = models.TextField(blank=True, default='', help_text='页面标题')
-    status = models.IntegerField(null=True, blank=True, help_text='HTTP状态码')
+    status_code = models.IntegerField(null=True, blank=True, help_text='HTTP状态码')
     content_length = models.BigIntegerField(null=True, blank=True, help_text='内容长度')
-    location = models.CharField(max_length=1000, blank=True, default='', help_text='重定向位置')
+    location = models.TextField(blank=True, default='', help_text='重定向位置')
-    web_server = models.CharField(max_length=200, blank=True, default='', help_text='Web服务器')
+    webserver = models.TextField(blank=True, default='', help_text='Web服务器')
-    content_type = models.CharField(max_length=200, blank=True, default='', help_text='内容类型')
+    content_type = models.TextField(blank=True, default='', help_text='内容类型')
     tech = ArrayField(
         models.CharField(max_length=100),
         blank=True,
         default=list,
         help_text='技术栈'
     )
-    body_preview = models.TextField(blank=True, default='', help_text='响应体预览')
+    response_body = models.TextField(blank=True, default='', help_text='HTTP响应体')
     vhost = models.BooleanField(null=True, blank=True, help_text='虚拟主机标志')
+    response_headers = models.TextField(
+        blank=True,
+        default='',
+        help_text='原始HTTP响应头'
+    )
     created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
@@ -83,6 +95,23 @@ class WebsiteSnapshot(models.Model):
             models.Index(fields=['host']),  # host索引，优化根据主机名查询
             models.Index(fields=['title']),  # title索引，优化标题搜索
             models.Index(fields=['-created_at']),
+            GinIndex(fields=['tech']),  # GIN索引，优化数组字段查询
+            # pg_trgm GIN 索引，支持 LIKE '%keyword%' 模糊搜索
+            GinIndex(
+                name='ws_snap_resp_hdr_trgm',
+                fields=['response_headers'],
+                opclasses=['gin_trgm_ops']
+            ),
+            GinIndex(
+                name='ws_snap_url_trgm',
+                fields=['url'],
+                opclasses=['gin_trgm_ops']
+            ),
+            GinIndex(
+                name='ws_snap_title_trgm',
+                fields=['title'],
+                opclasses=['gin_trgm_ops']
+            ),
         ]
         constraints = [
             # 唯一约束：同一次扫描中，同一个URL只能记录一次
@@ -132,6 +161,12 @@ class DirectorySnapshot(models.Model):
             models.Index(fields=['status']),  # 状态码索引，优化筛选
             models.Index(fields=['content_type']),  # content_type索引，优化内容类型搜索
             models.Index(fields=['-created_at']),
+            # pg_trgm GIN 索引，支持 LIKE '%keyword%' 模糊搜索
+            GinIndex(
+                name='dir_snap_url_trgm',
+                fields=['url'],
+                opclasses=['gin_trgm_ops']
+            ),
         ]
         constraints = [
             # 唯一约束：同一次扫描中，同一个目录URL只能记录一次
@@ -232,26 +267,26 @@ class EndpointSnapshot(models.Model):
     )
     
     # 扫描结果数据
-    url = models.CharField(max_length=2000, help_text='端点URL')
+    url = models.TextField(help_text='端点URL')
     host = models.CharField(
         max_length=253,
         blank=True,
         default='',
         help_text='主机名（域名或IP地址）'
     )
-    title = models.CharField(max_length=1000, blank=True, default='', help_text='页面标题')
+    title = models.TextField(blank=True, default='', help_text='页面标题')
     status_code = models.IntegerField(null=True, blank=True, help_text='HTTP状态码')
     content_length = models.IntegerField(null=True, blank=True, help_text='内容长度')
-    location = models.CharField(max_length=1000, blank=True, default='', help_text='重定向位置')
+    location = models.TextField(blank=True, default='', help_text='重定向位置')
-    webserver = models.CharField(max_length=200, blank=True, default='', help_text='Web服务器')
+    webserver = models.TextField(blank=True, default='', help_text='Web服务器')
-    content_type = models.CharField(max_length=200, blank=True, default='', help_text='内容类型')
+    content_type = models.TextField(blank=True, default='', help_text='内容类型')
     tech = ArrayField(
         models.CharField(max_length=100),
         blank=True,
         default=list,
         help_text='技术栈'
     )
-    body_preview = models.CharField(max_length=1000, blank=True, default='', help_text='响应体预览')
+    response_body = models.TextField(blank=True, default='', help_text='HTTP响应体')
     vhost = models.BooleanField(null=True, blank=True, help_text='虚拟主机标志')
     matched_gf_patterns = ArrayField(
         models.CharField(max_length=100),
@@ -259,6 +294,11 @@ class EndpointSnapshot(models.Model):
         default=list,
         help_text='匹配的GF模式列表'
     )
+    response_headers = models.TextField(
+        blank=True,
+        default='',
+        help_text='原始HTTP响应头'
+    )
     created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
@@ -274,6 +314,23 @@ class EndpointSnapshot(models.Model):
             models.Index(fields=['status_code']),  # 状态码索引，优化筛选
             models.Index(fields=['webserver']),  # webserver索引，优化服务器搜索
             models.Index(fields=['-created_at']),
+            GinIndex(fields=['tech']),  # GIN索引，优化数组字段查询
+            # pg_trgm GIN 索引，支持 LIKE '%keyword%' 模糊搜索
+            GinIndex(
+                name='ep_snap_resp_hdr_trgm',
+                fields=['response_headers'],
+                opclasses=['gin_trgm_ops']
+            ),
+            GinIndex(
+                name='ep_snap_url_trgm',
+                fields=['url'],
+                opclasses=['gin_trgm_ops']
+            ),
+            GinIndex(
+                name='ep_snap_title_trgm',
+                fields=['title'],
+                opclasses=['gin_trgm_ops']
+            ),
         ]
         constraints = [
             # 唯一约束：同一次扫描中，同一个URL只能记录一次

backend/apps/asset/repositories/asset/endpoint_repository.py

@@ -48,12 +48,13 @@ class DjangoEndpointRepository:
                     status_code=item.status_code,
                     content_length=item.content_length,
                     webserver=item.webserver or '',
-                    body_preview=item.body_preview or '',
+                    response_body=item.response_body or '',
                     content_type=item.content_type or '',
                     tech=item.tech if item.tech else [],
                     vhost=item.vhost,
                     location=item.location or '',
-                    matched_gf_patterns=item.matched_gf_patterns if item.matched_gf_patterns else []
+                    matched_gf_patterns=item.matched_gf_patterns if item.matched_gf_patterns else [],
+                    response_headers=item.response_headers if item.response_headers else ''
                 )
                 for item in unique_items
             ]
@@ -65,8 +66,8 @@ class DjangoEndpointRepository:
                     unique_fields=['url', 'target'],
                     update_fields=[
                         'host', 'title', 'status_code', 'content_length',
-                        'webserver', 'body_preview', 'content_type', 'tech',
+                        'webserver', 'response_body', 'content_type', 'tech',
-                        'vhost', 'location', 'matched_gf_patterns'
+                        'vhost', 'location', 'matched_gf_patterns', 'response_headers'
                     ],
                     batch_size=1000
                 )
@@ -138,12 +139,13 @@ class DjangoEndpointRepository:
                     status_code=item.status_code,
                     content_length=item.content_length,
                     webserver=item.webserver or '',
-                    body_preview=item.body_preview or '',
+                    response_body=item.response_body or '',
                     content_type=item.content_type or '',
                     tech=item.tech if item.tech else [],
                     vhost=item.vhost,
                     location=item.location or '',
-                    matched_gf_patterns=item.matched_gf_patterns if item.matched_gf_patterns else []
+                    matched_gf_patterns=item.matched_gf_patterns if item.matched_gf_patterns else [],
+                    response_headers=item.response_headers if item.response_headers else ''
                 )
                 for item in unique_items
             ]
@@ -183,7 +185,7 @@ class DjangoEndpointRepository:
             .values(
                 'url', 'host', 'location', 'title', 'status_code',
                 'content_length', 'content_type', 'webserver', 'tech',
-                'body_preview', 'vhost', 'matched_gf_patterns', 'created_at'
+                'response_body', 'response_headers', 'vhost', 'matched_gf_patterns', 'created_at'
             )
             .order_by('url')
         )

backend/apps/asset/repositories/asset/website_repository.py

@@ -49,12 +49,13 @@ class DjangoWebSiteRepository:
                     location=item.location or '',
                     title=item.title or '',
                     webserver=item.webserver or '',
-                    body_preview=item.body_preview or '',
+                    response_body=item.response_body or '',
                     content_type=item.content_type or '',
                     tech=item.tech if item.tech else [],
                     status_code=item.status_code,
                     content_length=item.content_length,
-                    vhost=item.vhost
+                    vhost=item.vhost,
+                    response_headers=item.response_headers if item.response_headers else ''
                 )
                 for item in unique_items
             ]
@@ -66,8 +67,8 @@ class DjangoWebSiteRepository:
                     unique_fields=['url', 'target'],
                     update_fields=[
                         'host', 'location', 'title', 'webserver',
-                        'body_preview', 'content_type', 'tech',
+                        'response_body', 'content_type', 'tech',
-                        'status_code', 'content_length', 'vhost'
+                        'status_code', 'content_length', 'vhost', 'response_headers'
                     ],
                     batch_size=1000
                 )
@@ -132,12 +133,13 @@ class DjangoWebSiteRepository:
                     location=item.location or '',
                     title=item.title or '',
                     webserver=item.webserver or '',
-                    body_preview=item.body_preview or '',
+                    response_body=item.response_body or '',
                     content_type=item.content_type or '',
                     tech=item.tech if item.tech else [],
                     status_code=item.status_code,
                     content_length=item.content_length,
-                    vhost=item.vhost
+                    vhost=item.vhost,
+                    response_headers=item.response_headers if item.response_headers else ''
                 )
                 for item in unique_items
             ]
@@ -177,7 +179,7 @@ class DjangoWebSiteRepository:
             .values(
                 'url', 'host', 'location', 'title', 'status_code',
                 'content_length', 'content_type', 'webserver', 'tech',
-                'body_preview', 'vhost', 'created_at'
+                'response_body', 'response_headers', 'vhost', 'created_at'
             )
             .order_by('url')
         )

backend/apps/asset/repositories/snapshot/endpoint_snapshot_repository.py

@@ -44,6 +44,7 @@ class DjangoEndpointSnapshotRepository:
                 snapshots.append(EndpointSnapshot(
                     scan_id=item.scan_id,
                     url=item.url,
+                    host=item.host if item.host else '',
                     title=item.title,
                     status_code=item.status_code,
                     content_length=item.content_length,
@@ -51,9 +52,10 @@ class DjangoEndpointSnapshotRepository:
                     webserver=item.webserver,
                     content_type=item.content_type,
                     tech=item.tech if item.tech else [],
-                    body_preview=item.body_preview,
+                    response_body=item.response_body,
                     vhost=item.vhost,
-                    matched_gf_patterns=item.matched_gf_patterns if item.matched_gf_patterns else []
+                    matched_gf_patterns=item.matched_gf_patterns if item.matched_gf_patterns else [],
+                    response_headers=item.response_headers if item.response_headers else ''
                 ))
             
             # 批量创建（忽略冲突，基于唯一约束去重）
@@ -100,7 +102,7 @@ class DjangoEndpointSnapshotRepository:
             .values(
                 'url', 'host', 'location', 'title', 'status_code',
                 'content_length', 'content_type', 'webserver', 'tech',
-                'body_preview', 'vhost', 'matched_gf_patterns', 'created_at'
+                'response_body', 'response_headers', 'vhost', 'matched_gf_patterns', 'created_at'
             )
             .order_by('url')
         )

backend/apps/asset/repositories/snapshot/host_port_mapping_snapshot_repository.py

@@ -195,3 +195,32 @@ class DjangoHostPortMappingSnapshotRepository:
         
         for row in qs.iterator(chunk_size=batch_size):
             yield row
+
+    def iter_unique_host_ports_by_scan(
+        self,
+        scan_id: int,
+        batch_size: int = 1000
+    ) -> Iterator[dict]:
+        """
+        流式获取扫描下的唯一 host:port 组合（去重）
+        
+        用于生成 URL 时避免重复，同一个 host:port 可能对应多个 IP，
+        但生成 URL 时只需要一个。
+        
+        Args:
+            scan_id: 扫描 ID
+            batch_size: 每批数据量
+        
+        Yields:
+            {'host': 'example.com', 'port': 80}
+        """
+        qs = (
+            HostPortMappingSnapshot.objects
+            .filter(scan_id=scan_id)
+            .values('host', 'port')
+            .distinct()
+            .order_by('host', 'port')
+        )
+        
+        for row in qs.iterator(chunk_size=batch_size):
+            yield row

backend/apps/asset/repositories/snapshot/website_snapshot_repository.py

@@ -46,14 +46,15 @@ class DjangoWebsiteSnapshotRepository:
                     url=item.url,
                     host=item.host,
                     title=item.title,
-                    status=item.status,
+                    status_code=item.status_code,
                     content_length=item.content_length,
                     location=item.location,
-                    web_server=item.web_server,
+                    webserver=item.webserver,
                     content_type=item.content_type,
                     tech=item.tech if item.tech else [],
-                    body_preview=item.body_preview,
+                    response_body=item.response_body,
-                    vhost=item.vhost
+                    vhost=item.vhost,
+                    response_headers=item.response_headers if item.response_headers else ''
                 ))
             
             # 批量创建（忽略冲突，基于唯一约束去重）
@@ -98,26 +99,12 @@ class DjangoWebsiteSnapshotRepository:
             WebsiteSnapshot.objects
             .filter(scan_id=scan_id)
             .values(
-                'url', 'host', 'location', 'title', 'status',
+                'url', 'host', 'location', 'title', 'status_code',
-                'content_length', 'content_type', 'web_server', 'tech',
+                'content_length', 'content_type', 'webserver', 'tech',
-                'body_preview', 'vhost', 'created_at'
+                'response_body', 'response_headers', 'vhost', 'created_at'
             )
             .order_by('url')
         )
         
         for row in qs.iterator(chunk_size=batch_size):
-            # 重命名字段以匹配 CSV 表头
+            yield row
-            yield {
-                'url': row['url'],
-                'host': row['host'],
-                'location': row['location'],
-                'title': row['title'],
-                'status_code': row['status'],
-                'content_length': row['content_length'],
-                'content_type': row['content_type'],
-                'webserver': row['web_server'],
-                'tech': row['tech'],
-                'body_preview': row['body_preview'],
-                'vhost': row['vhost'],
-                'created_at': row['created_at'],
-            }

backend/apps/asset/serializers.py

@@ -7,6 +7,7 @@ from .models.snapshot_models import (
     EndpointSnapshot,
     VulnerabilitySnapshot,
 )
+from .models.screenshot_models import Screenshot, ScreenshotSnapshot
 
 
 # 注意：IPAddress 和 Port 模型已被重构为 HostPortMapping
@@ -67,9 +68,10 @@ class SubdomainListSerializer(serializers.ModelSerializer):
 
 
 class WebSiteSerializer(serializers.ModelSerializer):
-    """站点序列化器"""
+    """站点序列化器（目标详情页）"""
     
     subdomain = serializers.CharField(source='subdomain.name', allow_blank=True, default='')
+    responseHeaders = serializers.CharField(source='response_headers', read_only=True)  # 原始HTTP响应头
     
     class Meta:
         model = WebSite
@@ -83,9 +85,10 @@ class WebSiteSerializer(serializers.ModelSerializer):
             'content_type',
             'status_code',
             'content_length',
-            'body_preview',
+            'response_body',
             'tech',
             'vhost',
+            'responseHeaders',  # HTTP响应头
             'subdomain',
             'created_at',
         ]
@@ -140,6 +143,7 @@ class EndpointListSerializer(serializers.ModelSerializer):
         source='matched_gf_patterns',
         read_only=True,
     )
+    responseHeaders = serializers.CharField(source='response_headers', read_only=True)  # 原始HTTP响应头
 
     class Meta:
         model = Endpoint
@@ -152,9 +156,10 @@ class EndpointListSerializer(serializers.ModelSerializer):
             'content_length',
             'content_type',
             'webserver',
-            'body_preview',
+            'response_body',
             'tech',
             'vhost',
+            'responseHeaders',  # HTTP响应头
             'gfPatterns',
             'created_at',
         ]
@@ -213,8 +218,7 @@ class WebsiteSnapshotSerializer(serializers.ModelSerializer):
     """网站快照序列化器（用于扫描历史）"""
     
     subdomain_name = serializers.CharField(source='subdomain.name', read_only=True)
-    webserver = serializers.CharField(source='web_server', read_only=True)  # 映射字段名
+    responseHeaders = serializers.CharField(source='response_headers', read_only=True)  # 原始HTTP响应头
-    status_code = serializers.IntegerField(source='status', read_only=True)  # 映射字段名
     
     class Meta:
         model = WebsiteSnapshot
@@ -223,13 +227,14 @@ class WebsiteSnapshotSerializer(serializers.ModelSerializer):
             'url',
             'location',
             'title',
-            'webserver',  # 使用映射后的字段名
+            'webserver',
             'content_type',
-            'status_code',  # 使用映射后的字段名
+            'status_code',
             'content_length',
-            'body_preview',
+            'response_body',
             'tech',
             'vhost',
+            'responseHeaders',  # HTTP响应头
             'subdomain_name',
             'created_at',
         ]
@@ -264,6 +269,7 @@ class EndpointSnapshotSerializer(serializers.ModelSerializer):
         source='matched_gf_patterns',
         read_only=True,
     )
+    responseHeaders = serializers.CharField(source='response_headers', read_only=True)  # 原始HTTP响应头
 
     class Meta:
         model = EndpointSnapshot
@@ -277,10 +283,31 @@ class EndpointSnapshotSerializer(serializers.ModelSerializer):
             'content_type',
             'status_code',
             'content_length',
-            'body_preview',
+            'response_body',
             'tech',
             'vhost',
+            'responseHeaders',  # HTTP响应头
             'gfPatterns',
             'created_at',
         ]
         read_only_fields = fields
+
+
+# ==================== 截图序列化器 ====================
+
+class ScreenshotListSerializer(serializers.ModelSerializer):
+    """截图资产列表序列化器（不包含 image 字段）"""
+    
+    class Meta:
+        model = Screenshot
+        fields = ['id', 'url', 'status_code', 'created_at', 'updated_at']
+        read_only_fields = fields
+
+
+class ScreenshotSnapshotListSerializer(serializers.ModelSerializer):
+    """截图快照列表序列化器（不包含 image 字段）"""
+    
+    class Meta:
+        model = ScreenshotSnapshot
+        fields = ['id', 'url', 'status_code', 'created_at']
+        read_only_fields = fields

backend/apps/asset/services/asset/endpoint_service.py

@@ -27,7 +27,8 @@ class EndpointService:
         'url': 'url',
         'host': 'host',
         'title': 'title',
-        'status': 'status_code',
+        'status_code': 'status_code',
+        'tech': 'tech',
     }
     
     def __init__(self):
@@ -115,7 +116,7 @@ class EndpointService:
         """获取目标下的所有端点"""
         queryset = self.repo.get_by_target(target_id)
         if filter_query:
-            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING, json_array_fields=['tech'])
         return queryset
     
     def count_endpoints_by_target(self, target_id: int) -> int:
@@ -134,7 +135,7 @@ class EndpointService:
         """获取所有端点（全局查询）"""
         queryset = self.repo.get_all()
         if filter_query:
-            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING, json_array_fields=['tech'])
         return queryset
     
     def iter_endpoint_urls_by_target(self, target_id: int, chunk_size: int = 1000) -> Iterator[str]:

backend/apps/asset/services/asset/website_service.py

@@ -19,7 +19,8 @@ class WebSiteService:
         'url': 'url',
         'host': 'host',
         'title': 'title',
-        'status': 'status_code',
+        'status_code': 'status_code',
+        'tech': 'tech',
     }
     
     def __init__(self, repository=None):
@@ -107,14 +108,14 @@ class WebSiteService:
         """获取目标下的所有网站"""
         queryset = self.repo.get_by_target(target_id)
         if filter_query:
-            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING, json_array_fields=['tech'])
         return queryset
     
     def get_all(self, filter_query: Optional[str] = None):
         """获取所有网站"""
         queryset = self.repo.get_all()
         if filter_query:
-            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING, json_array_fields=['tech'])
         return queryset
     
     def get_by_url(self, url: str, target_id: int) -> int:

backend/apps/asset/services/playwright_screenshot_service.py

@@ -0,0 +1,186 @@
+"""
+Playwright 截图服务
+
+使用 Playwright 异步批量捕获网站截图
+"""
+import asyncio
+import logging
+from typing import Optional, AsyncGenerator
+
+logger = logging.getLogger(__name__)
+
+
+class PlaywrightScreenshotService:
+    """Playwright 截图服务 - 异步多 Page 并发截图"""
+    
+    # 内置默认值（不暴露给用户）
+    DEFAULT_VIEWPORT_WIDTH = 1920
+    DEFAULT_VIEWPORT_HEIGHT = 1080
+    DEFAULT_TIMEOUT = 30000  # 毫秒
+    DEFAULT_JPEG_QUALITY = 85
+    
+    def __init__(
+        self,
+        viewport_width: int = DEFAULT_VIEWPORT_WIDTH,
+        viewport_height: int = DEFAULT_VIEWPORT_HEIGHT,
+        timeout: int = DEFAULT_TIMEOUT,
+        concurrency: int = 5
+    ):
+        """
+        初始化 Playwright 截图服务
+        
+        Args:
+            viewport_width: 视口宽度（像素）
+            viewport_height: 视口高度（像素）
+            timeout: 页面加载超时时间（毫秒）
+            concurrency: 并发截图数
+        """
+        self.viewport_width = viewport_width
+        self.viewport_height = viewport_height
+        self.timeout = timeout
+        self.concurrency = concurrency
+    
+    async def capture_screenshot(self, url: str, page) -> tuple[Optional[bytes], Optional[int]]:
+        """
+        捕获单个 URL 的截图
+        
+        Args:
+            url: 目标 URL
+            page: Playwright Page 对象
+        
+        Returns:
+            (screenshot_bytes, status_code) 元组
+            - screenshot_bytes: JPEG 格式的截图字节数据，失败返回 None
+            - status_code: HTTP 响应状态码，失败返回 None
+        """
+        status_code = None
+        try:
+            # 尝试加载页面，即使返回错误状态码也继续截图
+            try:
+                response = await page.goto(url, timeout=self.timeout, wait_until='networkidle')
+                if response:
+                    status_code = response.status
+            except Exception as goto_error:
+                # 页面加载失败（4xx/5xx 或其他错误），但页面可能已部分渲染
+                # 仍然尝试截图以捕获错误页面
+                logger.debug("页面加载异常但尝试截图: %s, 错误: %s", url, str(goto_error)[:50])
+            
+            # 尝试截图（即使 goto 失败）
+            screenshot_bytes = await page.screenshot(
+                type='jpeg',
+                quality=self.DEFAULT_JPEG_QUALITY,
+                full_page=False
+            )
+            return (screenshot_bytes, status_code)
+        except asyncio.TimeoutError:
+            logger.warning("截图超时: %s", url)
+            return (None, None)
+        except Exception as e:
+            logger.warning("截图失败: %s, 错误: %s", url, str(e)[:100])
+            return (None, None)
+    
+    async def _capture_with_semaphore(
+        self,
+        url: str,
+        context,
+        semaphore: asyncio.Semaphore
+    ) -> tuple[str, Optional[bytes], Optional[int]]:
+        """
+        使用信号量控制并发的截图任务
+        
+        Args:
+            url: 目标 URL
+            context: Playwright BrowserContext
+            semaphore: 并发控制信号量
+        
+        Returns:
+            (url, screenshot_bytes, status_code) 元组
+        """
+        async with semaphore:
+            page = await context.new_page()
+            try:
+                screenshot_bytes, status_code = await self.capture_screenshot(url, page)
+                return (url, screenshot_bytes, status_code)
+            finally:
+                await page.close()
+    
+    async def capture_batch(
+        self,
+        urls: list[str]
+    ) -> AsyncGenerator[tuple[str, Optional[bytes], Optional[int]], None]:
+        """
+        批量捕获截图（异步生成器）
+        
+        使用单个 BrowserContext + 多 Page 并发模式
+        通过 Semaphore 控制并发数
+        
+        Args:
+            urls: URL 列表
+        
+        Yields:
+            (url, screenshot_bytes, status_code) 元组
+        """
+        if not urls:
+            return
+        
+        from playwright.async_api import async_playwright
+        
+        async with async_playwright() as p:
+            # 启动浏览器（headless 模式）
+            browser = await p.chromium.launch(
+                headless=True,
+                args=[
+                    '--no-sandbox',
+                    '--disable-setuid-sandbox',
+                    '--disable-dev-shm-usage',
+                    '--disable-gpu'
+                ]
+            )
+            
+            try:
+                # 创建单个 context
+                context = await browser.new_context(
+                    viewport={
+                        'width': self.viewport_width,
+                        'height': self.viewport_height
+                    },
+                    ignore_https_errors=True,
+                    user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
+                )
+                
+                # 使用 Semaphore 控制并发
+                semaphore = asyncio.Semaphore(self.concurrency)
+                
+                # 创建所有任务
+                tasks = [
+                    self._capture_with_semaphore(url, context, semaphore)
+                    for url in urls
+                ]
+                
+                # 使用 as_completed 实现流式返回
+                for coro in asyncio.as_completed(tasks):
+                    result = await coro
+                    yield result
+                
+                await context.close()
+                
+            finally:
+                await browser.close()
+    
+    async def capture_batch_collect(
+        self,
+        urls: list[str]
+    ) -> list[tuple[str, Optional[bytes], Optional[int]]]:
+        """
+        批量捕获截图（收集所有结果）
+        
+        Args:
+            urls: URL 列表
+        
+        Returns:
+            [(url, screenshot_bytes, status_code), ...] 列表
+        """
+        results = []
+        async for result in self.capture_batch(urls):
+            results.append(result)
+        return results

backend/apps/asset/services/screenshot_service.py

@@ -0,0 +1,187 @@
+"""
+截图服务
+
+负责截图的压缩、保存和同步
+"""
+import io
+import logging
+import os
+from typing import Optional
+
+from PIL import Image
+
+logger = logging.getLogger(__name__)
+
+
+class ScreenshotService:
+    """截图服务 - 负责压缩、保存和同步"""
+    
+    def __init__(self, max_width: int = 800, target_kb: int = 100):
+        """
+        初始化截图服务
+        
+        Args:
+            max_width: 最大宽度（像素）
+            target_kb: 目标文件大小（KB）
+        """
+        self.max_width = max_width
+        self.target_kb = target_kb
+    
+    def compress_screenshot(self, image_path: str) -> Optional[bytes]:
+        """
+        压缩截图为 WebP 格式
+        
+        Args:
+            image_path: PNG 截图文件路径
+        
+        Returns:
+            压缩后的 WebP 二进制数据，失败返回 None
+        """
+        if not os.path.exists(image_path):
+            logger.warning(f"截图文件不存在: {image_path}")
+            return None
+        
+        try:
+            with Image.open(image_path) as img:
+                return self._compress_image(img)
+        except Exception as e:
+            logger.error(f"压缩截图失败: {image_path}, 错误: {e}")
+            return None
+    
+    def compress_from_bytes(self, image_bytes: bytes) -> Optional[bytes]:
+        """
+        从字节数据压缩截图为 WebP 格式
+        
+        Args:
+            image_bytes: JPEG/PNG 图片字节数据
+        
+        Returns:
+            压缩后的 WebP 二进制数据，失败返回 None
+        """
+        if not image_bytes:
+            return None
+        
+        try:
+            img = Image.open(io.BytesIO(image_bytes))
+            return self._compress_image(img)
+        except Exception as e:
+            logger.error(f"从字节压缩截图失败: {e}")
+            return None
+    
+    def _compress_image(self, img: Image.Image) -> Optional[bytes]:
+        """
+        压缩 PIL Image 对象为 WebP 格式
+        
+        Args:
+            img: PIL Image 对象
+        
+        Returns:
+            压缩后的 WebP 二进制数据
+        """
+        try:
+            if img.mode in ('RGBA', 'P'):
+                img = img.convert('RGB')
+            
+            width, height = img.size
+            if width > self.max_width:
+                ratio = self.max_width / width
+                new_size = (self.max_width, int(height * ratio))
+                img = img.resize(new_size, Image.Resampling.LANCZOS)
+            
+            quality = 80
+            while quality >= 10:
+                buffer = io.BytesIO()
+                img.save(buffer, format='WEBP', quality=quality, method=6)
+                if len(buffer.getvalue()) <= self.target_kb * 1024:
+                    return buffer.getvalue()
+                quality -= 10
+            
+            return buffer.getvalue()
+        except Exception as e:
+            logger.error(f"压缩图片失败: {e}")
+            return None
+    
+    def save_screenshot_snapshot(
+        self,
+        scan_id: int,
+        url: str,
+        image_data: bytes,
+        status_code: int | None = None
+    ) -> bool:
+        """
+        保存截图快照到 ScreenshotSnapshot 表
+        
+        Args:
+            scan_id: 扫描 ID
+            url: 截图对应的 URL
+            image_data: 压缩后的图片二进制数据
+            status_code: HTTP 响应状态码
+        
+        Returns:
+            是否保存成功
+        """
+        from apps.asset.models import ScreenshotSnapshot
+        
+        try:
+            ScreenshotSnapshot.objects.update_or_create(
+                scan_id=scan_id,
+                url=url,
+                defaults={'image': image_data, 'status_code': status_code}
+            )
+            return True
+        except Exception as e:
+            logger.error(f"保存截图快照失败: scan_id={scan_id}, url={url}, 错误: {e}")
+            return False
+    
+    def sync_screenshots_to_asset(self, scan_id: int, target_id: int) -> int:
+        """
+        将扫描的截图快照同步到资产表
+        
+        Args:
+            scan_id: 扫描 ID
+            target_id: 目标 ID
+        
+        Returns:
+            同步的截图数量
+        """
+        from apps.asset.models import Screenshot, ScreenshotSnapshot
+        
+        # 使用 iterator() 避免 QuerySet 缓存大量 BinaryField 数据导致内存飙升
+        # chunk_size=50: 每次只加载 50 条记录，处理完后释放内存
+        snapshots = ScreenshotSnapshot.objects.filter(scan_id=scan_id).iterator(chunk_size=50)
+        count = 0
+        
+        for snapshot in snapshots:
+            try:
+                Screenshot.objects.update_or_create(
+                    target_id=target_id,
+                    url=snapshot.url,
+                    defaults={
+                        'image': snapshot.image,
+                        'status_code': snapshot.status_code
+                    }
+                )
+                count += 1
+            except Exception as e:
+                logger.error(f"同步截图到资产表失败: url={snapshot.url}, 错误: {e}")
+        
+        logger.info(f"同步截图完成: scan_id={scan_id}, target_id={target_id}, 数量={count}")
+        return count
+    
+    def process_and_save_screenshot(self, scan_id: int, url: str, image_path: str) -> bool:
+        """
+        处理并保存截图（压缩 + 保存快照）
+        
+        Args:
+            scan_id: 扫描 ID
+            url: 截图对应的 URL
+            image_path: PNG 截图文件路径
+        
+        Returns:
+            是否处理成功
+        """
+        image_data = self.compress_screenshot(image_path)
+        if image_data is None:
+            return False
+        
+        return self.save_screenshot_snapshot(scan_id, url, image_data)

backend/apps/asset/services/search_service.py

@@ -0,0 +1,477 @@
+"""
+资产搜索服务
+
+提供资产搜索的核心业务逻辑：
+- 从物化视图查询数据
+- 支持表达式语法解析
+- 支持 =（模糊）、==（精确）、!=（不等于）操作符
+- 支持 && (AND) 和 || (OR) 逻辑组合
+- 支持 Website 和 Endpoint 两种资产类型
+"""
+
+import logging
+import re
+from typing import Optional, List, Dict, Any, Tuple, Literal, Iterator
+
+from django.db import connection
+
+logger = logging.getLogger(__name__)
+
+# 支持的字段映射（前端字段名 -> 数据库字段名）
+FIELD_MAPPING = {
+    'host': 'host',
+    'url': 'url',
+    'title': 'title',
+    'tech': 'tech',
+    'status': 'status_code',
+    'body': 'response_body',
+    'header': 'response_headers',
+}
+
+# 数组类型字段
+ARRAY_FIELDS = {'tech'}
+
+# 资产类型到视图名的映射
+VIEW_MAPPING = {
+    'website': 'asset_search_view',
+    'endpoint': 'endpoint_search_view',
+}
+
+# 资产类型到原表名的映射（用于 JOIN 获取数组字段）
+# ⚠️ 重要：pg_ivm 不支持 ArrayField，所有数组字段必须从原表 JOIN 获取
+TABLE_MAPPING = {
+    'website': 'website',
+    'endpoint': 'endpoint',
+}
+
+# 有效的资产类型
+VALID_ASSET_TYPES = {'website', 'endpoint'}
+
+# Website 查询字段（v=视图，t=原表）
+# ⚠️ 注意：t.tech 从原表获取，因为 pg_ivm 不支持 ArrayField
+WEBSITE_SELECT_FIELDS = """
+    v.id,
+    v.url,
+    v.host,
+    v.title,
+    t.tech,  -- ArrayField，从 website 表 JOIN 获取
+    v.status_code,
+    v.response_headers,
+    v.response_body,
+    v.content_type,
+    v.content_length,
+    v.webserver,
+    v.location,
+    v.vhost,
+    v.created_at,
+    v.target_id
+"""
+
+# Endpoint 查询字段
+# ⚠️ 注意：t.tech 和 t.matched_gf_patterns 从原表获取，因为 pg_ivm 不支持 ArrayField
+ENDPOINT_SELECT_FIELDS = """
+    v.id,
+    v.url,
+    v.host,
+    v.title,
+    t.tech,  -- ArrayField，从 endpoint 表 JOIN 获取
+    v.status_code,
+    v.response_headers,
+    v.response_body,
+    v.content_type,
+    v.content_length,
+    v.webserver,
+    v.location,
+    v.vhost,
+    t.matched_gf_patterns,  -- ArrayField，从 endpoint 表 JOIN 获取
+    v.created_at,
+    v.target_id
+"""
+
+
+class SearchQueryParser:
+    """
+    搜索查询解析器
+    
+    支持语法：
+    - field="value"     模糊匹配（ILIKE %value%）
+    - field=="value"    精确匹配
+    - field!="value"    不等于
+    - &&                AND 连接
+    - ||                OR 连接
+    - ()                分组（暂不支持嵌套）
+    
+    示例：
+    - host="api" && tech="nginx"
+    - tech="vue" || tech="react"
+    - status=="200" && host!="test"
+    """
+    
+    # 匹配单个条件: field="value" 或 field=="value" 或 field!="value"
+    CONDITION_PATTERN = re.compile(r'(\w+)\s*(==|!=|=)\s*"([^"]*)"')
+    
+    @classmethod
+    def parse(cls, query: str) -> Tuple[str, List[Any]]:
+        """
+        解析查询字符串，返回 SQL WHERE 子句和参数
+        
+        Args:
+            query: 搜索查询字符串
+        
+        Returns:
+            (where_clause, params) 元组
+        """
+        if not query or not query.strip():
+            return "1=1", []
+        
+        query = query.strip()
+        
+        # 检查是否包含操作符语法，如果不包含则作为 host 模糊搜索
+        if not cls.CONDITION_PATTERN.search(query):
+            # 裸文本，默认作为 host 模糊搜索（v 是视图别名）
+            return "v.host ILIKE %s", [f"%{query}%"]
+        
+        # 按 || 分割为 OR 组
+        or_groups = cls._split_by_or(query)
+        
+        if len(or_groups) == 1:
+            # 没有 OR，直接解析 AND 条件
+            return cls._parse_and_group(or_groups[0])
+        
+        # 多个 OR 组
+        or_clauses = []
+        all_params = []
+        
+        for group in or_groups:
+            clause, params = cls._parse_and_group(group)
+            if clause and clause != "1=1":
+                or_clauses.append(f"({clause})")
+                all_params.extend(params)
+        
+        if not or_clauses:
+            return "1=1", []
+        
+        return " OR ".join(or_clauses), all_params
+    
+    @classmethod
+    def _split_by_or(cls, query: str) -> List[str]:
+        """按 || 分割查询，但忽略引号内的 ||"""
+        parts = []
+        current = ""
+        in_quotes = False
+        i = 0
+        
+        while i < len(query):
+            char = query[i]
+            
+            if char == '"':
+                in_quotes = not in_quotes
+                current += char
+            elif not in_quotes and i + 1 < len(query) and query[i:i+2] == '||':
+                if current.strip():
+                    parts.append(current.strip())
+                current = ""
+                i += 1  # 跳过第二个 |
+            else:
+                current += char
+            
+            i += 1
+        
+        if current.strip():
+            parts.append(current.strip())
+        
+        return parts if parts else [query]
+    
+    @classmethod
+    def _parse_and_group(cls, group: str) -> Tuple[str, List[Any]]:
+        """解析 AND 组（用 && 连接的条件）"""
+        # 移除外层括号
+        group = group.strip()
+        if group.startswith('(') and group.endswith(')'):
+            group = group[1:-1].strip()
+        
+        # 按 && 分割
+        parts = cls._split_by_and(group)
+        
+        and_clauses = []
+        all_params = []
+        
+        for part in parts:
+            clause, params = cls._parse_condition(part.strip())
+            if clause:
+                and_clauses.append(clause)
+                all_params.extend(params)
+        
+        if not and_clauses:
+            return "1=1", []
+        
+        return " AND ".join(and_clauses), all_params
+    
+    @classmethod
+    def _split_by_and(cls, query: str) -> List[str]:
+        """按 && 分割查询，但忽略引号内的 &&"""
+        parts = []
+        current = ""
+        in_quotes = False
+        i = 0
+        
+        while i < len(query):
+            char = query[i]
+            
+            if char == '"':
+                in_quotes = not in_quotes
+                current += char
+            elif not in_quotes and i + 1 < len(query) and query[i:i+2] == '&&':
+                if current.strip():
+                    parts.append(current.strip())
+                current = ""
+                i += 1  # 跳过第二个 &
+            else:
+                current += char
+            
+            i += 1
+        
+        if current.strip():
+            parts.append(current.strip())
+        
+        return parts if parts else [query]
+    
+    @classmethod
+    def _parse_condition(cls, condition: str) -> Tuple[Optional[str], List[Any]]:
+        """
+        解析单个条件
+        
+        Returns:
+            (sql_clause, params) 或 (None, []) 如果解析失败
+        """
+        # 移除括号
+        condition = condition.strip()
+        if condition.startswith('(') and condition.endswith(')'):
+            condition = condition[1:-1].strip()
+        
+        match = cls.CONDITION_PATTERN.match(condition)
+        if not match:
+            logger.warning(f"无法解析条件: {condition}")
+            return None, []
+        
+        field, operator, value = match.groups()
+        field = field.lower()
+        
+        # 验证字段
+        if field not in FIELD_MAPPING:
+            logger.warning(f"未知字段: {field}")
+            return None, []
+        
+        db_field = FIELD_MAPPING[field]
+        is_array = field in ARRAY_FIELDS
+        
+        # 根据操作符生成 SQL
+        if operator == '=':
+            # 模糊匹配
+            return cls._build_like_condition(db_field, value, is_array)
+        elif operator == '==':
+            # 精确匹配
+            return cls._build_exact_condition(db_field, value, is_array)
+        elif operator == '!=':
+            # 不等于
+            return cls._build_not_equal_condition(db_field, value, is_array)
+        
+        return None, []
+    
+    @classmethod
+    def _build_like_condition(cls, field: str, value: str, is_array: bool) -> Tuple[str, List[Any]]:
+        """构建模糊匹配条件"""
+        if is_array:
+            # 数组字段：检查数组中是否有元素包含该值（从原表 t 获取）
+            return f"EXISTS (SELECT 1 FROM unnest(t.{field}) AS elem WHERE elem ILIKE %s)", [f"%{value}%"]
+        elif field == 'status_code':
+            # 状态码是整数，模糊匹配转为精确匹配
+            try:
+                return f"v.{field} = %s", [int(value)]
+            except ValueError:
+                return f"v.{field}::text ILIKE %s", [f"%{value}%"]
+        else:
+            return f"v.{field} ILIKE %s", [f"%{value}%"]
+    
+    @classmethod
+    def _build_exact_condition(cls, field: str, value: str, is_array: bool) -> Tuple[str, List[Any]]:
+        """构建精确匹配条件"""
+        if is_array:
+            # 数组字段：检查数组中是否包含该精确值（从原表 t 获取）
+            return f"%s = ANY(t.{field})", [value]
+        elif field == 'status_code':
+            # 状态码是整数
+            try:
+                return f"v.{field} = %s", [int(value)]
+            except ValueError:
+                return f"v.{field}::text = %s", [value]
+        else:
+            return f"v.{field} = %s", [value]
+    
+    @classmethod
+    def _build_not_equal_condition(cls, field: str, value: str, is_array: bool) -> Tuple[str, List[Any]]:
+        """构建不等于条件"""
+        if is_array:
+            # 数组字段：检查数组中不包含该值（从原表 t 获取）
+            return f"NOT (%s = ANY(t.{field}))", [value]
+        elif field == 'status_code':
+            try:
+                return f"(v.{field} IS NULL OR v.{field} != %s)", [int(value)]
+            except ValueError:
+                return f"(v.{field} IS NULL OR v.{field}::text != %s)", [value]
+        else:
+            return f"(v.{field} IS NULL OR v.{field} != %s)", [value]
+
+
+AssetType = Literal['website', 'endpoint']
+
+
+class AssetSearchService:
+    """资产搜索服务"""
+    
+    def search(
+        self, 
+        query: str, 
+        asset_type: AssetType = 'website',
+        limit: Optional[int] = None
+    ) -> List[Dict[str, Any]]:
+        """
+        搜索资产
+        
+        Args:
+            query: 搜索查询字符串
+            asset_type: 资产类型 ('website' 或 'endpoint')
+            limit: 最大返回数量（可选）
+        
+        Returns:
+            List[Dict]: 搜索结果列表
+        """
+        where_clause, params = SearchQueryParser.parse(query)
+        
+        # 根据资产类型选择视图、原表和字段
+        view_name = VIEW_MAPPING.get(asset_type, 'asset_search_view')
+        table_name = TABLE_MAPPING.get(asset_type, 'website')
+        select_fields = ENDPOINT_SELECT_FIELDS if asset_type == 'endpoint' else WEBSITE_SELECT_FIELDS
+        
+        # JOIN 原表获取数组字段（tech, matched_gf_patterns）
+        sql = f"""
+            SELECT {select_fields}
+            FROM {view_name} v
+            JOIN {table_name} t ON v.id = t.id
+            WHERE {where_clause}
+            ORDER BY v.created_at DESC
+        """
+        
+        # 添加 LIMIT
+        if limit is not None and limit > 0:
+            sql += f" LIMIT {int(limit)}"
+        
+        try:
+            with connection.cursor() as cursor:
+                cursor.execute(sql, params)
+                columns = [col[0] for col in cursor.description]
+                results = []
+                
+                for row in cursor.fetchall():
+                    result = dict(zip(columns, row))
+                    results.append(result)
+                
+                return results
+        except Exception as e:
+            logger.error(f"搜索查询失败: {e}, SQL: {sql}, params: {params}")
+            raise
+    
+    def count(self, query: str, asset_type: AssetType = 'website', statement_timeout_ms: int = 300000) -> int:
+        """
+        统计搜索结果数量
+        
+        Args:
+            query: 搜索查询字符串
+            asset_type: 资产类型 ('website' 或 'endpoint')
+            statement_timeout_ms: SQL 语句超时时间（毫秒），默认 5 分钟
+        
+        Returns:
+            int: 结果总数
+        """
+        where_clause, params = SearchQueryParser.parse(query)
+        
+        # 根据资产类型选择视图和原表
+        view_name = VIEW_MAPPING.get(asset_type, 'asset_search_view')
+        table_name = TABLE_MAPPING.get(asset_type, 'website')
+        
+        # JOIN 原表以支持数组字段查询
+        sql = f"SELECT COUNT(*) FROM {view_name} v JOIN {table_name} t ON v.id = t.id WHERE {where_clause}"
+        
+        try:
+            with connection.cursor() as cursor:
+                # 为导出设置更长的超时时间（仅影响当前会话）
+                cursor.execute(f"SET LOCAL statement_timeout = {statement_timeout_ms}")
+                cursor.execute(sql, params)
+                return cursor.fetchone()[0]
+        except Exception as e:
+            logger.error(f"统计查询失败: {e}")
+            raise
+    
+    def search_iter(
+        self, 
+        query: str, 
+        asset_type: AssetType = 'website',
+        batch_size: int = 1000,
+        statement_timeout_ms: int = 300000
+    ) -> Iterator[Dict[str, Any]]:
+        """
+        流式搜索资产（使用分批查询，内存友好）
+        
+        Args:
+            query: 搜索查询字符串
+            asset_type: 资产类型 ('website' 或 'endpoint')
+            batch_size: 每批获取的数量
+            statement_timeout_ms: SQL 语句超时时间（毫秒），默认 5 分钟
+        
+        Yields:
+            Dict: 单条搜索结果
+        """
+        where_clause, params = SearchQueryParser.parse(query)
+        
+        # 根据资产类型选择视图、原表和字段
+        view_name = VIEW_MAPPING.get(asset_type, 'asset_search_view')
+        table_name = TABLE_MAPPING.get(asset_type, 'website')
+        select_fields = ENDPOINT_SELECT_FIELDS if asset_type == 'endpoint' else WEBSITE_SELECT_FIELDS
+        
+        # 使用 OFFSET/LIMIT 分批查询（Django 不支持命名游标）
+        offset = 0
+        
+        try:
+            while True:
+                # JOIN 原表获取数组字段
+                sql = f"""
+                    SELECT {select_fields}
+                    FROM {view_name} v
+                    JOIN {table_name} t ON v.id = t.id
+                    WHERE {where_clause}
+                    ORDER BY v.created_at DESC
+                    LIMIT {batch_size} OFFSET {offset}
+                """
+                
+                with connection.cursor() as cursor:
+                    # 为导出设置更长的超时时间（仅影响当前会话）
+                    cursor.execute(f"SET LOCAL statement_timeout = {statement_timeout_ms}")
+                    cursor.execute(sql, params)
+                    columns = [col[0] for col in cursor.description]
+                    rows = cursor.fetchall()
+                
+                if not rows:
+                    break
+                
+                for row in rows:
+                    yield dict(zip(columns, row))
+                
+                # 如果返回的行数少于 batch_size，说明已经是最后一批
+                if len(rows) < batch_size:
+                    break
+                
+                offset += batch_size
+                
+        except Exception as e:
+            logger.error(f"流式搜索查询失败: {e}, SQL: {sql}, params: {params}")
+            raise

backend/apps/asset/services/snapshot/endpoint_snapshots_service.py

@@ -1,11 +1,11 @@
 """Endpoint Snapshots Service - 业务逻辑层"""
 
 import logging
-from typing import List, Iterator
+from typing import Iterator, List, Optional
 
+from apps.asset.dtos.snapshot import EndpointSnapshotDTO
 from apps.asset.repositories.snapshot import DjangoEndpointSnapshotRepository
 from apps.asset.services.asset import EndpointService
-from apps.asset.dtos.snapshot import EndpointSnapshotDTO
 
 logger = logging.getLogger(__name__)
 
@@ -13,6 +13,16 @@ logger = logging.getLogger(__name__)
 class EndpointSnapshotsService:
     """端点快照服务 - 统一管理快照和资产同步"""
 
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'url': 'url',
+        'host': 'host',
+        'title': 'title',
+        'status_code': 'status_code',
+        'webserver': 'webserver',
+        'tech': 'tech',
+    }
+
     def __init__(self):
         self.snapshot_repo = DjangoEndpointSnapshotRepository()
         self.asset_service = EndpointService()
@@ -46,38 +56,29 @@ class EndpointSnapshotsService:
             logger.debug("保存端点快照并同步到资产表 - 数量: %d", len(items))
 
             # 步骤 1: 保存到快照表
-            logger.debug("步骤 1: 保存到快照表")
             self.snapshot_repo.save_snapshots(items)
 
-            # 步骤 2: 转换为资产 DTO 并保存到资产表
+            # 步骤 2: 转换为资产 DTO 并保存到资产表（upsert）
-            # 使用 upsert：新记录插入，已存在的记录更新
-            logger.debug("步骤 2: 同步到资产表（通过 Service 层）")
             asset_items = [item.to_asset_dto() for item in items]
-            
             self.asset_service.bulk_upsert(asset_items)
 
             logger.info("端点快照和资产数据保存成功 - 数量: %d", len(items))
 
         except Exception as e:
-            logger.error(
+            logger.error("保存端点快照失败 - 数量: %d, 错误: %s", len(items), str(e), exc_info=True)
-                "保存端点快照失败 - 数量: %d, 错误: %s",
-                len(items),
-                str(e),
-                exc_info=True
-            )
             raise
 
-    # 智能过滤字段映射
+    def get_by_scan(self, scan_id: int, filter_query: Optional[str] = None):
-    FILTER_FIELD_MAPPING = {
+        """
-        'url': 'url',
+        获取指定扫描的端点快照
-        'host': 'host',
-        'title': 'title',
-        'status': 'status_code',
-        'webserver': 'webserver',
-        'tech': 'tech',
-    }
 
-    def get_by_scan(self, scan_id: int, filter_query: str = None):
+        Args:
+            scan_id: 扫描 ID
+            filter_query: 过滤查询字符串
+
+        Returns:
+            QuerySet: 端点快照查询集
+        """
         from apps.common.utils.filter_utils import apply_filters
 
         queryset = self.snapshot_repo.get_by_scan(scan_id)
@@ -85,8 +86,16 @@ class EndpointSnapshotsService:
             queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
         return queryset
 
-    def get_all(self, filter_query: str = None):
+    def get_all(self, filter_query: Optional[str] = None):
-        """获取所有端点快照"""
+        """
+        获取所有端点快照
+
+        Args:
+            filter_query: 过滤查询字符串
+
+        Returns:
+            QuerySet: 端点快照查询集
+        """
         from apps.common.utils.filter_utils import apply_filters
 
         queryset = self.snapshot_repo.get_all()
@@ -95,7 +104,7 @@ class EndpointSnapshotsService:
         return queryset
 
     def iter_endpoint_urls_by_scan(self, scan_id: int, chunk_size: int = 1000) -> Iterator[str]:
-        """流式获取某次扫描下的所有端点 URL。"""
+        """流式获取某次扫描下的所有端点 URL"""
         queryset = self.snapshot_repo.get_by_scan(scan_id)
         for snapshot in queryset.iterator(chunk_size=chunk_size):
             yield snapshot.url

backend/apps/asset/services/snapshot/host_port_mapping_snapshots_service.py

@@ -91,3 +91,25 @@ class HostPortMappingSnapshotsService:
             原始数据字典 {ip, host, port, created_at}
         """
         return self.snapshot_repo.iter_raw_data_for_export(scan_id=scan_id)
+
+    def iter_unique_host_ports_by_scan(
+        self,
+        scan_id: int,
+        batch_size: int = 1000
+    ) -> Iterator[dict]:
+        """
+        流式获取扫描下的唯一 host:port 组合（去重）
+        
+        用于生成 URL 时避免重复。
+        
+        Args:
+            scan_id: 扫描 ID
+            batch_size: 每批数据量
+        
+        Yields:
+            {'host': 'example.com', 'port': 80}
+        """
+        return self.snapshot_repo.iter_unique_host_ports_by_scan(
+            scan_id=scan_id,
+            batch_size=batch_size
+        )

backend/apps/asset/services/snapshot/website_snapshots_service.py

@@ -73,8 +73,8 @@ class WebsiteSnapshotsService:
         'url': 'url',
         'host': 'host',
         'title': 'title',
-        'status': 'status',
+        'status_code': 'status_code',
-        'webserver': 'web_server',
+        'webserver': 'webserver',
         'tech': 'tech',
     }
     

backend/apps/asset/urls.py

@@ -10,19 +10,28 @@ from .views import (
     DirectoryViewSet,
     VulnerabilityViewSet,
     AssetStatisticsViewSet,
+    AssetSearchView,
+    AssetSearchExportView,
+    EndpointViewSet,
+    HostPortMappingViewSet,
+    ScreenshotViewSet,
 )
 
 # 创建 DRF 路由器
 router = DefaultRouter()
 
 # 注册 ViewSet
-# 注意：IPAddress 模型已被重构为 HostPortMapping，相关路由已移除
 router.register(r'subdomains', SubdomainViewSet, basename='subdomain')
 router.register(r'websites', WebSiteViewSet, basename='website')
 router.register(r'directories', DirectoryViewSet, basename='directory')
+router.register(r'endpoints', EndpointViewSet, basename='endpoint')
+router.register(r'ip-addresses', HostPortMappingViewSet, basename='ip-address')
 router.register(r'vulnerabilities', VulnerabilityViewSet, basename='vulnerability')
+router.register(r'screenshots', ScreenshotViewSet, basename='screenshot')
 router.register(r'statistics', AssetStatisticsViewSet, basename='asset-statistics')
 
 urlpatterns = [
     path('assets/', include(router.urls)),
+    path('assets/search/', AssetSearchView.as_view(), name='asset-search'),
+    path('assets/search/export/', AssetSearchExportView.as_view(), name='asset-search-export'),
 ]

backend/apps/asset/views/__init__.py

@@ -0,0 +1,44 @@
+"""
+Asset 应用视图模块
+
+重新导出所有视图类以保持向后兼容
+"""
+
+from .asset_views import (
+    AssetStatisticsViewSet,
+    SubdomainViewSet,
+    WebSiteViewSet,
+    DirectoryViewSet,
+    EndpointViewSet,
+    HostPortMappingViewSet,
+    VulnerabilityViewSet,
+    SubdomainSnapshotViewSet,
+    WebsiteSnapshotViewSet,
+    DirectorySnapshotViewSet,
+    EndpointSnapshotViewSet,
+    HostPortMappingSnapshotViewSet,
+    VulnerabilitySnapshotViewSet,
+    ScreenshotViewSet,
+    ScreenshotSnapshotViewSet,
+)
+from .search_views import AssetSearchView, AssetSearchExportView
+
+__all__ = [
+    'AssetStatisticsViewSet',
+    'SubdomainViewSet',
+    'WebSiteViewSet',
+    'DirectoryViewSet',
+    'EndpointViewSet',
+    'HostPortMappingViewSet',
+    'VulnerabilityViewSet',
+    'SubdomainSnapshotViewSet',
+    'WebsiteSnapshotViewSet',
+    'DirectorySnapshotViewSet',
+    'EndpointSnapshotViewSet',
+    'HostPortMappingSnapshotViewSet',
+    'VulnerabilitySnapshotViewSet',
+    'ScreenshotViewSet',
+    'ScreenshotSnapshotViewSet',
+    'AssetSearchView',
+    'AssetSearchExportView',
+]

backend/apps/asset/views/asset_views.py

@@ -2,23 +2,24 @@ import logging
 from rest_framework import viewsets, status, filters
 from rest_framework.decorators import action
 from rest_framework.response import Response
+from apps.common.response_helpers import success_response, error_response
+from apps.common.error_codes import ErrorCodes
 from rest_framework.request import Request
 from rest_framework.exceptions import NotFound, ValidationError as DRFValidationError
 from django.core.exceptions import ValidationError, ObjectDoesNotExist
 from django.db import DatabaseError, IntegrityError, OperationalError
-from django.http import StreamingHttpResponse
 
-from .serializers import (
+from ..serializers import (
     SubdomainListSerializer, WebSiteSerializer, DirectorySerializer, 
     VulnerabilitySerializer, EndpointListSerializer, IPAddressAggregatedSerializer,
     SubdomainSnapshotSerializer, WebsiteSnapshotSerializer, DirectorySnapshotSerializer,
     EndpointSnapshotSerializer, VulnerabilitySnapshotSerializer
 )
-from .services import (
+from ..services import (
     SubdomainService, WebSiteService, DirectoryService, 
     VulnerabilityService, AssetStatisticsService, EndpointService, HostPortMappingService
 )
-from .services.snapshot import (
+from ..services.snapshot import (
     SubdomainSnapshotsService, WebsiteSnapshotsService, DirectorySnapshotsService,
     EndpointSnapshotsService, HostPortMappingSnapshotsService, VulnerabilitySnapshotsService
 )
@@ -57,7 +58,7 @@ class AssetStatisticsViewSet(viewsets.ViewSet):
         """
         try:
             stats = self.service.get_statistics()
-            return Response({
+            return success_response(data={
                 'totalTargets': stats['total_targets'],
                 'totalSubdomains': stats['total_subdomains'],
                 'totalIps': stats['total_ips'],
@@ -80,9 +81,10 @@ class AssetStatisticsViewSet(viewsets.ViewSet):
             })
         except (DatabaseError, OperationalError) as e:
             logger.exception("获取资产统计数据失败")
-            return Response(
+            return error_response(
-                {'error': '获取统计数据失败'},
+                code=ErrorCodes.SERVER_ERROR,
-                status=status.HTTP_500_INTERNAL_SERVER_ERROR
+                message='Failed to get statistics',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
             )
 
     @action(detail=False, methods=['get'], url_path='history')
@@ -107,12 +109,13 @@ class AssetStatisticsViewSet(viewsets.ViewSet):
             days = min(max(days, 1), 90)  # 限制在 1-90 天
             
             history = self.service.get_statistics_history(days=days)
-            return Response(history)
+            return success_response(data=history)
         except (DatabaseError, OperationalError) as e:
             logger.exception("获取统计历史数据失败")
-            return Response(
+            return error_response(
-                {'error': '获取历史数据失败'},
+                code=ErrorCodes.SERVER_ERROR,
-                status=status.HTTP_500_INTERNAL_SERVER_ERROR
+                message='Failed to get history data',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
             )
 
 
@@ -164,45 +167,50 @@ class SubdomainViewSet(viewsets.ModelViewSet):
         
         响应:
         {
-            "message": "批量创建完成",
+            "data": {
-            "createdCount": 10,
+                "createdCount": 10,
-            "skippedCount": 2,
+                "skippedCount": 2,
-            "invalidCount": 1,
+                "invalidCount": 1,
-            "mismatchedCount": 1,
+                "mismatchedCount": 1,
-            "totalReceived": 14
+                "totalReceived": 14
+            }
         }
         """
         from apps.targets.models import Target
         
         target_pk = self.kwargs.get('target_pk')
         if not target_pk:
-            return Response(
+            return error_response(
-                {'error': '必须在目标下批量创建子域名'},
+                code=ErrorCodes.VALIDATION_ERROR,
-                status=status.HTTP_400_BAD_REQUEST
+                message='Must create subdomains under a target',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         # 获取目标
         try:
             target = Target.objects.get(pk=target_pk)
         except Target.DoesNotExist:
-            return Response(
+            return error_response(
-                {'error': '目标不存在'},
+                code=ErrorCodes.NOT_FOUND,
-                status=status.HTTP_404_NOT_FOUND
+                message='Target not found',
+                status_code=status.HTTP_404_NOT_FOUND
             )
         
         # 验证目标类型必须为域名
         if target.type != Target.TargetType.DOMAIN:
-            return Response(
+            return error_response(
-                {'error': '只有域名类型的目标支持导入子域名'},
+                code=ErrorCodes.VALIDATION_ERROR,
-                status=status.HTTP_400_BAD_REQUEST
+                message='Only domain type targets support subdomain import',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         # 获取请求体中的子域名列表
         subdomains = request.data.get('subdomains', [])
         if not subdomains or not isinstance(subdomains, list):
-            return Response(
+            return error_response(
-                {'error': '请求体不能为空或格式错误'},
+                code=ErrorCodes.VALIDATION_ERROR,
-                status=status.HTTP_400_BAD_REQUEST
+                message='Request body cannot be empty or invalid format',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         # 调用 service 层处理
@@ -214,19 +222,19 @@ class SubdomainViewSet(viewsets.ModelViewSet):
             )
         except Exception as e:
             logger.exception("批量创建子域名失败")
-            return Response(
+            return error_response(
-                {'error': '服务器内部错误'},
+                code=ErrorCodes.SERVER_ERROR,
-                status=status.HTTP_500_INTERNAL_SERVER_ERROR
+                message='Server internal error',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
             )
         
-        return Response({
+        return success_response(data={
-            'message': '批量创建完成',
             'createdCount': result.created_count,
             'skippedCount': result.skipped_count,
             'invalidCount': result.invalid_count,
             'mismatchedCount': result.mismatched_count,
             'totalReceived': result.total_received,
-        }, status=status.HTTP_200_OK)
+        })
 
     @action(detail=False, methods=['get'], url_path='export')
     def export(self, request, **kwargs):
@@ -234,7 +242,7 @@ class SubdomainViewSet(viewsets.ModelViewSet):
         
         CSV 列：name, created_at
         """
-        from apps.common.utils import generate_csv_rows, format_datetime
+        from apps.common.utils import create_csv_export_response, format_datetime
         
         target_pk = self.kwargs.get('target_pk')
         if not target_pk:
@@ -245,12 +253,41 @@ class SubdomainViewSet(viewsets.ModelViewSet):
         headers = ['name', 'created_at']
         formatters = {'created_at': format_datetime}
         
-        response = StreamingHttpResponse(
+        return create_csv_export_response(
-            generate_csv_rows(data_iterator, headers, formatters),
+            data_iterator=data_iterator,
-            content_type='text/csv; charset=utf-8'
+            headers=headers,
+            filename=f"target-{target_pk}-subdomains.csv",
+            field_formatters=formatters
         )
-        response['Content-Disposition'] = f'attachment; filename="target-{target_pk}-subdomains.csv"'
+
-        return response
+    @action(detail=False, methods=['post'], url_path='bulk-delete')
+    def bulk_delete(self, request, **kwargs):
+        """批量删除子域名
+        
+        POST /api/assets/subdomains/bulk-delete/
+        
+        请求体: {"ids": [1, 2, 3]}
+        响应: {"deletedCount": 3}
+        """
+        ids = request.data.get('ids', [])
+        if not ids or not isinstance(ids, list):
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='ids is required and must be a list',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
+        
+        try:
+            from ..models import Subdomain
+            deleted_count, _ = Subdomain.objects.filter(id__in=ids).delete()
+            return success_response(data={'deletedCount': deleted_count})
+        except Exception as e:
+            logger.exception("批量删除子域名失败")
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Failed to delete subdomains',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )
 
 
 class WebSiteViewSet(viewsets.ModelViewSet):
@@ -265,6 +302,7 @@ class WebSiteViewSet(viewsets.ModelViewSet):
     - host="example"     主机名模糊匹配
     - title="login"      标题模糊匹配
     - status="200,301"   状态码多值匹配
+    - tech="nginx"       技术栈匹配（数组字段）
     - 多条件空格分隔     AND 关系
     """
     
@@ -299,35 +337,38 @@ class WebSiteViewSet(viewsets.ModelViewSet):
         
         响应:
         {
-            "message": "批量创建完成",
+            "data": {
-            "createdCount": 10,
+                "createdCount": 10
-            "mismatchedCount": 2
+            }
         }
         """
         from apps.targets.models import Target
         
         target_pk = self.kwargs.get('target_pk')
         if not target_pk:
-            return Response(
+            return error_response(
-                {'error': '必须在目标下批量创建网站'},
+                code=ErrorCodes.VALIDATION_ERROR,
-                status=status.HTTP_400_BAD_REQUEST
+                message='Must create websites under a target',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         # 获取目标
         try:
             target = Target.objects.get(pk=target_pk)
         except Target.DoesNotExist:
-            return Response(
+            return error_response(
-                {'error': '目标不存在'},
+                code=ErrorCodes.NOT_FOUND,
-                status=status.HTTP_404_NOT_FOUND
+                message='Target not found',
+                status_code=status.HTTP_404_NOT_FOUND
             )
         
         # 获取请求体中的 URL 列表
         urls = request.data.get('urls', [])
         if not urls or not isinstance(urls, list):
-            return Response(
+            return error_response(
-                {'error': '请求体不能为空或格式错误'},
+                code=ErrorCodes.VALIDATION_ERROR,
-                status=status.HTTP_400_BAD_REQUEST
+                message='Request body cannot be empty or invalid format',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         # 调用 service 层处理
@@ -340,23 +381,23 @@ class WebSiteViewSet(viewsets.ModelViewSet):
             )
         except Exception as e:
             logger.exception("批量创建网站失败")
-            return Response(
+            return error_response(
-                {'error': '服务器内部错误'},
+                code=ErrorCodes.SERVER_ERROR,
-                status=status.HTTP_500_INTERNAL_SERVER_ERROR
+                message='Server internal error',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
             )
         
-        return Response({
+        return success_response(data={
-            'message': '批量创建完成',
             'createdCount': created_count,
-        }, status=status.HTTP_200_OK)
+        })
 
     @action(detail=False, methods=['get'], url_path='export')
     def export(self, request, **kwargs):
         """导出网站为 CSV 格式
         
-        CSV 列：url, host, location, title, status_code, content_length, content_type, webserver, tech, body_preview, vhost, created_at
+        CSV 列：url, host, location, title, status_code, content_length, content_type, webserver, tech, response_body, response_headers, vhost, created_at
         """
-        from apps.common.utils import generate_csv_rows, format_datetime, format_list_field
+        from apps.common.utils import create_csv_export_response, format_datetime, format_list_field
         
         target_pk = self.kwargs.get('target_pk')
         if not target_pk:
@@ -367,19 +408,48 @@ class WebSiteViewSet(viewsets.ModelViewSet):
         headers = [
             'url', 'host', 'location', 'title', 'status_code',
             'content_length', 'content_type', 'webserver', 'tech',
-            'body_preview', 'vhost', 'created_at'
+            'response_body', 'response_headers', 'vhost', 'created_at'
         ]
         formatters = {
             'created_at': format_datetime,
             'tech': lambda x: format_list_field(x, separator=','),
         }
         
-        response = StreamingHttpResponse(
+        return create_csv_export_response(
-            generate_csv_rows(data_iterator, headers, formatters),
+            data_iterator=data_iterator,
-            content_type='text/csv; charset=utf-8'
+            headers=headers,
+            filename=f"target-{target_pk}-websites.csv",
+            field_formatters=formatters
         )
-        response['Content-Disposition'] = f'attachment; filename="target-{target_pk}-websites.csv"'
+
-        return response
+    @action(detail=False, methods=['post'], url_path='bulk-delete')
+    def bulk_delete(self, request, **kwargs):
+        """批量删除网站
+        
+        POST /api/assets/websites/bulk-delete/
+        
+        请求体: {"ids": [1, 2, 3]}
+        响应: {"deletedCount": 3}
+        """
+        ids = request.data.get('ids', [])
+        if not ids or not isinstance(ids, list):
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='ids is required and must be a list',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
+        
+        try:
+            from ..models import WebSite
+            deleted_count, _ = WebSite.objects.filter(id__in=ids).delete()
+            return success_response(data={'deletedCount': deleted_count})
+        except Exception as e:
+            logger.exception("批量删除网站失败")
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Failed to delete websites',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )
 
 
 class DirectoryViewSet(viewsets.ModelViewSet):
@@ -426,35 +496,38 @@ class DirectoryViewSet(viewsets.ModelViewSet):
         
         响应:
         {
-            "message": "批量创建完成",
+            "data": {
-            "createdCount": 10,
+                "createdCount": 10
-            "mismatchedCount": 2
+            }
         }
         """
         from apps.targets.models import Target
         
         target_pk = self.kwargs.get('target_pk')
         if not target_pk:
-            return Response(
+            return error_response(
-                {'error': '必须在目标下批量创建目录'},
+                code=ErrorCodes.VALIDATION_ERROR,
-                status=status.HTTP_400_BAD_REQUEST
+                message='Must create directories under a target',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         # 获取目标
         try:
             target = Target.objects.get(pk=target_pk)
         except Target.DoesNotExist:
-            return Response(
+            return error_response(
-                {'error': '目标不存在'},
+                code=ErrorCodes.NOT_FOUND,
-                status=status.HTTP_404_NOT_FOUND
+                message='Target not found',
+                status_code=status.HTTP_404_NOT_FOUND
             )
         
         # 获取请求体中的 URL 列表
         urls = request.data.get('urls', [])
         if not urls or not isinstance(urls, list):
-            return Response(
+            return error_response(
-                {'error': '请求体不能为空或格式错误'},
+                code=ErrorCodes.VALIDATION_ERROR,
-                status=status.HTTP_400_BAD_REQUEST
+                message='Request body cannot be empty or invalid format',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         # 调用 service 层处理
@@ -467,15 +540,15 @@ class DirectoryViewSet(viewsets.ModelViewSet):
             )
         except Exception as e:
             logger.exception("批量创建目录失败")
-            return Response(
+            return error_response(
-                {'error': '服务器内部错误'},
+                code=ErrorCodes.SERVER_ERROR,
-                status=status.HTTP_500_INTERNAL_SERVER_ERROR
+                message='Server internal error',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
             )
         
-        return Response({
+        return success_response(data={
-            'message': '批量创建完成',
             'createdCount': created_count,
-        }, status=status.HTTP_200_OK)
+        })
 
     @action(detail=False, methods=['get'], url_path='export')
     def export(self, request, **kwargs):
@@ -483,7 +556,7 @@ class DirectoryViewSet(viewsets.ModelViewSet):
         
         CSV 列：url, status, content_length, words, lines, content_type, duration, created_at
         """
-        from apps.common.utils import generate_csv_rows, format_datetime
+        from apps.common.utils import create_csv_export_response, format_datetime
         
         target_pk = self.kwargs.get('target_pk')
         if not target_pk:
@@ -499,12 +572,41 @@ class DirectoryViewSet(viewsets.ModelViewSet):
             'created_at': format_datetime,
         }
         
-        response = StreamingHttpResponse(
+        return create_csv_export_response(
-            generate_csv_rows(data_iterator, headers, formatters),
+            data_iterator=data_iterator,
-            content_type='text/csv; charset=utf-8'
+            headers=headers,
+            filename=f"target-{target_pk}-directories.csv",
+            field_formatters=formatters
         )
-        response['Content-Disposition'] = f'attachment; filename="target-{target_pk}-directories.csv"'
+
-        return response
+    @action(detail=False, methods=['post'], url_path='bulk-delete')
+    def bulk_delete(self, request, **kwargs):
+        """批量删除目录
+        
+        POST /api/assets/directories/bulk-delete/
+        
+        请求体: {"ids": [1, 2, 3]}
+        响应: {"deletedCount": 3}
+        """
+        ids = request.data.get('ids', [])
+        if not ids or not isinstance(ids, list):
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='ids is required and must be a list',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
+        
+        try:
+            from ..models import Directory
+            deleted_count, _ = Directory.objects.filter(id__in=ids).delete()
+            return success_response(data={'deletedCount': deleted_count})
+        except Exception as e:
+            logger.exception("批量删除目录失败")
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Failed to delete directories',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )
 
 
 class EndpointViewSet(viewsets.ModelViewSet):
@@ -519,6 +621,7 @@ class EndpointViewSet(viewsets.ModelViewSet):
     - host="example"     主机名模糊匹配
     - title="login"      标题模糊匹配
     - status="200,301"   状态码多值匹配
+    - tech="nginx"       技术栈匹配（数组字段）
     - 多条件空格分隔     AND 关系
     """
     
@@ -553,35 +656,38 @@ class EndpointViewSet(viewsets.ModelViewSet):
         
         响应:
         {
-            "message": "批量创建完成",
+            "data": {
-            "createdCount": 10,
+                "createdCount": 10
-            "mismatchedCount": 2
+            }
         }
         """
         from apps.targets.models import Target
         
         target_pk = self.kwargs.get('target_pk')
         if not target_pk:
-            return Response(
+            return error_response(
-                {'error': '必须在目标下批量创建端点'},
+                code=ErrorCodes.VALIDATION_ERROR,
-                status=status.HTTP_400_BAD_REQUEST
+                message='Must create endpoints under a target',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         # 获取目标
         try:
             target = Target.objects.get(pk=target_pk)
         except Target.DoesNotExist:
-            return Response(
+            return error_response(
-                {'error': '目标不存在'},
+                code=ErrorCodes.NOT_FOUND,
-                status=status.HTTP_404_NOT_FOUND
+                message='Target not found',
+                status_code=status.HTTP_404_NOT_FOUND
             )
         
         # 获取请求体中的 URL 列表
         urls = request.data.get('urls', [])
         if not urls or not isinstance(urls, list):
-            return Response(
+            return error_response(
-                {'error': '请求体不能为空或格式错误'},
+                code=ErrorCodes.VALIDATION_ERROR,
-                status=status.HTTP_400_BAD_REQUEST
+                message='Request body cannot be empty or invalid format',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         # 调用 service 层处理
@@ -594,23 +700,23 @@ class EndpointViewSet(viewsets.ModelViewSet):
             )
         except Exception as e:
             logger.exception("批量创建端点失败")
-            return Response(
+            return error_response(
-                {'error': '服务器内部错误'},
+                code=ErrorCodes.SERVER_ERROR,
-                status=status.HTTP_500_INTERNAL_SERVER_ERROR
+                message='Server internal error',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
             )
         
-        return Response({
+        return success_response(data={
-            'message': '批量创建完成',
             'createdCount': created_count,
-        }, status=status.HTTP_200_OK)
+        })
 
     @action(detail=False, methods=['get'], url_path='export')
     def export(self, request, **kwargs):
         """导出端点为 CSV 格式
         
-        CSV 列：url, host, location, title, status_code, content_length, content_type, webserver, tech, body_preview, vhost, matched_gf_patterns, created_at
+        CSV 列：url, host, location, title, status_code, content_length, content_type, webserver, tech, response_body, response_headers, vhost, matched_gf_patterns, created_at
         """
-        from apps.common.utils import generate_csv_rows, format_datetime, format_list_field
+        from apps.common.utils import create_csv_export_response, format_datetime, format_list_field
         
         target_pk = self.kwargs.get('target_pk')
         if not target_pk:
@@ -621,7 +727,7 @@ class EndpointViewSet(viewsets.ModelViewSet):
         headers = [
             'url', 'host', 'location', 'title', 'status_code',
             'content_length', 'content_type', 'webserver', 'tech',
-            'body_preview', 'vhost', 'matched_gf_patterns', 'created_at'
+            'response_body', 'response_headers', 'vhost', 'matched_gf_patterns', 'created_at'
         ]
         formatters = {
             'created_at': format_datetime,
@@ -629,12 +735,41 @@ class EndpointViewSet(viewsets.ModelViewSet):
             'matched_gf_patterns': lambda x: format_list_field(x, separator=','),
         }
         
-        response = StreamingHttpResponse(
+        return create_csv_export_response(
-            generate_csv_rows(data_iterator, headers, formatters),
+            data_iterator=data_iterator,
-            content_type='text/csv; charset=utf-8'
+            headers=headers,
+            filename=f"target-{target_pk}-endpoints.csv",
+            field_formatters=formatters
         )
-        response['Content-Disposition'] = f'attachment; filename="target-{target_pk}-endpoints.csv"'
+
-        return response
+    @action(detail=False, methods=['post'], url_path='bulk-delete')
+    def bulk_delete(self, request, **kwargs):
+        """批量删除端点
+        
+        POST /api/assets/endpoints/bulk-delete/
+        
+        请求体: {"ids": [1, 2, 3]}
+        响应: {"deletedCount": 3}
+        """
+        ids = request.data.get('ids', [])
+        if not ids or not isinstance(ids, list):
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='ids is required and must be a list',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
+        
+        try:
+            from ..models import Endpoint
+            deleted_count, _ = Endpoint.objects.filter(id__in=ids).delete()
+            return success_response(data={'deletedCount': deleted_count})
+        except Exception as e:
+            logger.exception("批量删除端点失败")
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Failed to delete endpoints',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )
 
 
 class HostPortMappingViewSet(viewsets.ModelViewSet):
@@ -687,7 +822,7 @@ class HostPortMappingViewSet(viewsets.ModelViewSet):
         
         CSV 列：ip, host, port, created_at
         """
-        from apps.common.utils import generate_csv_rows, format_datetime
+        from apps.common.utils import create_csv_export_response, format_datetime
         
         target_pk = self.kwargs.get('target_pk')
         if not target_pk:
@@ -702,14 +837,44 @@ class HostPortMappingViewSet(viewsets.ModelViewSet):
             'created_at': format_datetime
         }
         
-        # 生成流式响应
+        return create_csv_export_response(
-        response = StreamingHttpResponse(
+            data_iterator=data_iterator,
-            generate_csv_rows(data_iterator, headers, formatters),
+            headers=headers,
-            content_type='text/csv; charset=utf-8'
+            filename=f"target-{target_pk}-ip-addresses.csv",
+            field_formatters=formatters
         )
-        response['Content-Disposition'] = f'attachment; filename="target-{target_pk}-ip-addresses.csv"'
 
-        return response
+    @action(detail=False, methods=['post'], url_path='bulk-delete')
+    def bulk_delete(self, request, **kwargs):
+        """批量删除 IP 地址映射
+        
+        POST /api/assets/ip-addresses/bulk-delete/
+        
+        请求体: {"ips": ["192.168.1.1", "10.0.0.1"]}
+        响应: {"deletedCount": 3}
+        
+        注意：由于 IP 地址是聚合显示的，删除时传入 IP 列表，
+        会删除该 IP 下的所有 host:port 映射记录
+        """
+        ips = request.data.get('ips', [])
+        if not ips or not isinstance(ips, list):
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='ips is required and must be a list',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
+        
+        try:
+            from ..models import HostPortMapping
+            deleted_count, _ = HostPortMapping.objects.filter(ip__in=ips).delete()
+            return success_response(data={'deletedCount': deleted_count})
+        except Exception as e:
+            logger.exception("批量删除 IP 地址映射失败")
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Failed to delete ip addresses',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )
 
 
 class VulnerabilityViewSet(viewsets.ModelViewSet):
@@ -781,7 +946,7 @@ class SubdomainSnapshotViewSet(viewsets.ModelViewSet):
         
         CSV 列：name, created_at
         """
-        from apps.common.utils import generate_csv_rows, format_datetime
+        from apps.common.utils import create_csv_export_response, format_datetime
         
         scan_pk = self.kwargs.get('scan_pk')
         if not scan_pk:
@@ -792,12 +957,12 @@ class SubdomainSnapshotViewSet(viewsets.ModelViewSet):
         headers = ['name', 'created_at']
         formatters = {'created_at': format_datetime}
         
-        response = StreamingHttpResponse(
+        return create_csv_export_response(
-            generate_csv_rows(data_iterator, headers, formatters),
+            data_iterator=data_iterator,
-            content_type='text/csv; charset=utf-8'
+            headers=headers,
+            filename=f"scan-{scan_pk}-subdomains.csv",
+            field_formatters=formatters
         )
-        response['Content-Disposition'] = f'attachment; filename="scan-{scan_pk}-subdomains.csv"'
-        return response
 
 
 class WebsiteSnapshotViewSet(viewsets.ModelViewSet):
@@ -833,9 +998,9 @@ class WebsiteSnapshotViewSet(viewsets.ModelViewSet):
     def export(self, request, **kwargs):
         """导出网站快照为 CSV 格式
         
-        CSV 列：url, host, location, title, status_code, content_length, content_type, webserver, tech, body_preview, vhost, created_at
+        CSV 列：url, host, location, title, status_code, content_length, content_type, webserver, tech, response_body, response_headers, vhost, created_at
         """
-        from apps.common.utils import generate_csv_rows, format_datetime, format_list_field
+        from apps.common.utils import create_csv_export_response, format_datetime, format_list_field
         
         scan_pk = self.kwargs.get('scan_pk')
         if not scan_pk:
@@ -846,19 +1011,19 @@ class WebsiteSnapshotViewSet(viewsets.ModelViewSet):
         headers = [
             'url', 'host', 'location', 'title', 'status_code',
             'content_length', 'content_type', 'webserver', 'tech',
-            'body_preview', 'vhost', 'created_at'
+            'response_body', 'response_headers', 'vhost', 'created_at'
         ]
         formatters = {
             'created_at': format_datetime,
             'tech': lambda x: format_list_field(x, separator=','),
         }
         
-        response = StreamingHttpResponse(
+        return create_csv_export_response(
-            generate_csv_rows(data_iterator, headers, formatters),
+            data_iterator=data_iterator,
-            content_type='text/csv; charset=utf-8'
+            headers=headers,
+            filename=f"scan-{scan_pk}-websites.csv",
+            field_formatters=formatters
         )
-        response['Content-Disposition'] = f'attachment; filename="scan-{scan_pk}-websites.csv"'
-        return response
 
 
 class DirectorySnapshotViewSet(viewsets.ModelViewSet):
@@ -893,7 +1058,7 @@ class DirectorySnapshotViewSet(viewsets.ModelViewSet):
         
         CSV 列：url, status, content_length, words, lines, content_type, duration, created_at
         """
-        from apps.common.utils import generate_csv_rows, format_datetime
+        from apps.common.utils import create_csv_export_response, format_datetime
         
         scan_pk = self.kwargs.get('scan_pk')
         if not scan_pk:
@@ -909,12 +1074,12 @@ class DirectorySnapshotViewSet(viewsets.ModelViewSet):
             'created_at': format_datetime,
         }
         
-        response = StreamingHttpResponse(
+        return create_csv_export_response(
-            generate_csv_rows(data_iterator, headers, formatters),
+            data_iterator=data_iterator,
-            content_type='text/csv; charset=utf-8'
+            headers=headers,
+            filename=f"scan-{scan_pk}-directories.csv",
+            field_formatters=formatters
         )
-        response['Content-Disposition'] = f'attachment; filename="scan-{scan_pk}-directories.csv"'
-        return response
 
 
 class EndpointSnapshotViewSet(viewsets.ModelViewSet):
@@ -950,9 +1115,9 @@ class EndpointSnapshotViewSet(viewsets.ModelViewSet):
     def export(self, request, **kwargs):
         """导出端点快照为 CSV 格式
         
-        CSV 列：url, host, location, title, status_code, content_length, content_type, webserver, tech, body_preview, vhost, matched_gf_patterns, created_at
+        CSV 列：url, host, location, title, status_code, content_length, content_type, webserver, tech, response_body, response_headers, vhost, matched_gf_patterns, created_at
         """
-        from apps.common.utils import generate_csv_rows, format_datetime, format_list_field
+        from apps.common.utils import create_csv_export_response, format_datetime, format_list_field
         
         scan_pk = self.kwargs.get('scan_pk')
         if not scan_pk:
@@ -963,7 +1128,7 @@ class EndpointSnapshotViewSet(viewsets.ModelViewSet):
         headers = [
             'url', 'host', 'location', 'title', 'status_code',
             'content_length', 'content_type', 'webserver', 'tech',
-            'body_preview', 'vhost', 'matched_gf_patterns', 'created_at'
+            'response_body', 'response_headers', 'vhost', 'matched_gf_patterns', 'created_at'
         ]
         formatters = {
             'created_at': format_datetime,
@@ -971,12 +1136,12 @@ class EndpointSnapshotViewSet(viewsets.ModelViewSet):
             'matched_gf_patterns': lambda x: format_list_field(x, separator=','),
         }
         
-        response = StreamingHttpResponse(
+        return create_csv_export_response(
-            generate_csv_rows(data_iterator, headers, formatters),
+            data_iterator=data_iterator,
-            content_type='text/csv; charset=utf-8'
+            headers=headers,
+            filename=f"scan-{scan_pk}-endpoints.csv",
+            field_formatters=formatters
         )
-        response['Content-Disposition'] = f'attachment; filename="scan-{scan_pk}-endpoints.csv"'
-        return response
 
 
 class HostPortMappingSnapshotViewSet(viewsets.ModelViewSet):
@@ -1011,7 +1176,7 @@ class HostPortMappingSnapshotViewSet(viewsets.ModelViewSet):
         
         CSV 列：ip, host, port, created_at
         """
-        from apps.common.utils import generate_csv_rows, format_datetime
+        from apps.common.utils import create_csv_export_response, format_datetime
         
         scan_pk = self.kwargs.get('scan_pk')
         if not scan_pk:
@@ -1026,14 +1191,12 @@ class HostPortMappingSnapshotViewSet(viewsets.ModelViewSet):
             'created_at': format_datetime
         }
         
-        # 生成流式响应
+        return create_csv_export_response(
-        response = StreamingHttpResponse(
+            data_iterator=data_iterator,
-            generate_csv_rows(data_iterator, headers, formatters),
+            headers=headers,
-            content_type='text/csv; charset=utf-8'
+            filename=f"scan-{scan_pk}-ip-addresses.csv",
+            field_formatters=formatters
         )
-        response['Content-Disposition'] = f'attachment; filename="scan-{scan_pk}-ip-addresses.csv"'
-        
-        return response
 
 
 class VulnerabilitySnapshotViewSet(viewsets.ModelViewSet):
@@ -1062,3 +1225,162 @@ class VulnerabilitySnapshotViewSet(viewsets.ModelViewSet):
         if scan_pk:
             return self.service.get_by_scan(scan_pk, filter_query=filter_query)
         return self.service.get_all(filter_query=filter_query)
+
+
+# ==================== 截图 ViewSet ====================
+
+class ScreenshotViewSet(viewsets.ModelViewSet):
+    """截图资产 ViewSet
+    
+    支持两种访问方式：
+    1. 嵌套路由：GET /api/targets/{target_pk}/screenshots/
+    2. 独立路由：GET /api/screenshots/（全局查询）
+    
+    支持智能过滤语法（filter 参数）：
+    - url="example"      URL 模糊匹配
+    """
+    
+    from ..serializers import ScreenshotListSerializer
+    
+    serializer_class = ScreenshotListSerializer
+    pagination_class = BasePagination
+    filter_backends = [filters.OrderingFilter]
+    ordering = ['-created_at']
+    
+    def get_queryset(self):
+        """根据是否有 target_pk 参数决定查询范围"""
+        from ..models import Screenshot
+        
+        target_pk = self.kwargs.get('target_pk')
+        filter_query = self.request.query_params.get('filter', None)
+        
+        queryset = Screenshot.objects.all()
+        if target_pk:
+            queryset = queryset.filter(target_id=target_pk)
+        
+        if filter_query:
+            # 简单的 URL 模糊匹配
+            queryset = queryset.filter(url__icontains=filter_query)
+        
+        return queryset.order_by('-created_at')
+    
+    @action(detail=True, methods=['get'], url_path='image')
+    def image(self, request, pk=None, **kwargs):
+        """获取截图图片
+        
+        GET /api/assets/screenshots/{id}/image/
+        
+        返回 WebP 格式的图片二进制数据
+        """
+        from django.http import HttpResponse
+        from ..models import Screenshot
+        
+        try:
+            screenshot = Screenshot.objects.get(pk=pk)
+            if not screenshot.image:
+                return error_response(
+                    code=ErrorCodes.NOT_FOUND,
+                    message='Screenshot image not found',
+                    status_code=status.HTTP_404_NOT_FOUND
+                )
+            
+            response = HttpResponse(screenshot.image, content_type='image/webp')
+            response['Content-Disposition'] = f'inline; filename="screenshot_{pk}.webp"'
+            return response
+        except Screenshot.DoesNotExist:
+            return error_response(
+                code=ErrorCodes.NOT_FOUND,
+                message='Screenshot not found',
+                status_code=status.HTTP_404_NOT_FOUND
+            )
+    
+    @action(detail=False, methods=['post'], url_path='bulk-delete')
+    def bulk_delete(self, request, **kwargs):
+        """批量删除截图
+        
+        POST /api/assets/screenshots/bulk-delete/
+        
+        请求体: {"ids": [1, 2, 3]}
+        响应: {"deletedCount": 3}
+        """
+        ids = request.data.get('ids', [])
+        if not ids or not isinstance(ids, list):
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='ids is required and must be a list',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
+        
+        try:
+            from ..models import Screenshot
+            deleted_count, _ = Screenshot.objects.filter(id__in=ids).delete()
+            return success_response(data={'deletedCount': deleted_count})
+        except Exception as e:
+            logger.exception("批量删除截图失败")
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Failed to delete screenshots',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )
+
+
+class ScreenshotSnapshotViewSet(viewsets.ModelViewSet):
+    """截图快照 ViewSet - 嵌套路由：GET /api/scans/{scan_pk}/screenshots/
+    
+    支持智能过滤语法（filter 参数）：
+    - url="example"      URL 模糊匹配
+    """
+    
+    from ..serializers import ScreenshotSnapshotListSerializer
+    
+    serializer_class = ScreenshotSnapshotListSerializer
+    pagination_class = BasePagination
+    filter_backends = [filters.OrderingFilter]
+    ordering = ['-created_at']
+    
+    def get_queryset(self):
+        """根据 scan_pk 参数查询"""
+        from ..models import ScreenshotSnapshot
+        
+        scan_pk = self.kwargs.get('scan_pk')
+        filter_query = self.request.query_params.get('filter', None)
+        
+        queryset = ScreenshotSnapshot.objects.all()
+        if scan_pk:
+            queryset = queryset.filter(scan_id=scan_pk)
+        
+        if filter_query:
+            # 简单的 URL 模糊匹配
+            queryset = queryset.filter(url__icontains=filter_query)
+        
+        return queryset.order_by('-created_at')
+    
+    @action(detail=True, methods=['get'], url_path='image')
+    def image(self, request, pk=None, **kwargs):
+        """获取截图快照图片
+        
+        GET /api/scans/{scan_pk}/screenshots/{id}/image/
+        
+        返回 WebP 格式的图片二进制数据
+        """
+        from django.http import HttpResponse
+        from ..models import ScreenshotSnapshot
+        
+        try:
+            screenshot = ScreenshotSnapshot.objects.get(pk=pk)
+            if not screenshot.image:
+                return error_response(
+                    code=ErrorCodes.NOT_FOUND,
+                    message='Screenshot image not found',
+                    status_code=status.HTTP_404_NOT_FOUND
+                )
+            
+            response = HttpResponse(screenshot.image, content_type='image/webp')
+            response['Content-Disposition'] = f'inline; filename="screenshot_snapshot_{pk}.webp"'
+            return response
+        except ScreenshotSnapshot.DoesNotExist:
+            return error_response(
+                code=ErrorCodes.NOT_FOUND,
+                message='Screenshot snapshot not found',
+                status_code=status.HTTP_404_NOT_FOUND
+            )

backend/apps/asset/views/search_views.py

@@ -0,0 +1,361 @@
+"""
+资产搜索 API 视图
+
+提供资产搜索的 REST API 接口：
+- GET /api/assets/search/ - 搜索资产
+- GET /api/assets/search/export/ - 导出搜索结果为 CSV
+
+搜索语法：
+- field="value"     模糊匹配（ILIKE %value%）
+- field=="value"    精确匹配
+- field!="value"    不等于
+- &&                AND 连接
+- ||                OR 连接
+
+支持的字段：
+- host: 主机名
+- url: URL
+- title: 标题
+- tech: 技术栈
+- status: 状态码
+- body: 响应体
+- header: 响应头
+
+支持的资产类型：
+- website: 站点（默认）
+- endpoint: 端点
+"""
+
+import logging
+import json
+from datetime import datetime
+from urllib.parse import urlparse, urlunparse
+from rest_framework import status
+from rest_framework.views import APIView
+from rest_framework.request import Request
+from django.db import connection
+
+from apps.common.response_helpers import success_response, error_response
+from apps.common.error_codes import ErrorCodes
+from apps.asset.services.search_service import AssetSearchService, VALID_ASSET_TYPES
+
+logger = logging.getLogger(__name__)
+
+
+class AssetSearchView(APIView):
+    """
+    资产搜索 API
+    
+    GET /api/assets/search/
+    
+    Query Parameters:
+        q: 搜索查询表达式
+        asset_type: 资产类型 ('website' 或 'endpoint'，默认 'website')
+        page: 页码（从 1 开始，默认 1）
+        pageSize: 每页数量（默认 10，最大 100）
+    
+    示例查询：
+        ?q=host="api" && tech="nginx"
+        ?q=tech="vue" || tech="react"&asset_type=endpoint
+        ?q=status=="200" && host!="test"
+    
+    Response:
+        {
+            "results": [...],
+            "total": 100,
+            "page": 1,
+            "pageSize": 10,
+            "totalPages": 10,
+            "assetType": "website"
+        }
+    """
+    
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        self.service = AssetSearchService()
+    
+    def _parse_headers(self, headers_data) -> dict:
+        """解析响应头为字典"""
+        if not headers_data:
+            return {}
+        try:
+            return json.loads(headers_data)
+        except (json.JSONDecodeError, TypeError):
+            result = {}
+            for line in str(headers_data).split('\n'):
+                if ':' in line:
+                    key, value = line.split(':', 1)
+                    result[key.strip()] = value.strip()
+            return result
+    
+    def _format_result(self, result: dict, vulnerabilities_by_url: dict, asset_type: str) -> dict:
+        """格式化单个搜索结果"""
+        url = result.get('url', '')
+        vulns = vulnerabilities_by_url.get(url, [])
+        
+        # 基础字段（Website 和 Endpoint 共有）
+        formatted = {
+            'id': result.get('id'),
+            'url': url,
+            'host': result.get('host', ''),
+            'title': result.get('title', ''),
+            'technologies': result.get('tech', []) or [],
+            'statusCode': result.get('status_code'),
+            'contentLength': result.get('content_length'),
+            'contentType': result.get('content_type', ''),
+            'webserver': result.get('webserver', ''),
+            'location': result.get('location', ''),
+            'vhost': result.get('vhost'),
+            'responseHeaders': self._parse_headers(result.get('response_headers')),
+            'responseBody': result.get('response_body', ''),
+            'createdAt': result.get('created_at').isoformat() if result.get('created_at') else None,
+            'targetId': result.get('target_id'),
+        }
+        
+        # Website 特有字段：漏洞关联
+        if asset_type == 'website':
+            formatted['vulnerabilities'] = [
+                {
+                    'id': v.get('id'),
+                    'name': v.get('vuln_type', ''),
+                    'vulnType': v.get('vuln_type', ''),
+                    'severity': v.get('severity', 'info'),
+                }
+                for v in vulns
+            ]
+        
+        # Endpoint 特有字段
+        if asset_type == 'endpoint':
+            formatted['matchedGfPatterns'] = result.get('matched_gf_patterns', []) or []
+        
+        return formatted
+    
+    def _get_vulnerabilities_by_url_prefix(self, website_urls: list) -> dict:
+        """
+        根据 URL 前缀批量查询漏洞数据
+        
+        漏洞 URL 是 website URL 的子路径，使用前缀匹配：
+        - website.url: https://example.com/path?query=1
+        - vulnerability.url: https://example.com/path/api/users
+        
+        Args:
+            website_urls: website URL 列表，格式为 [(url, target_id), ...]
+        
+        Returns:
+            dict: {website_url: [vulnerability_list]}
+        """
+        if not website_urls:
+            return {}
+        
+        try:
+            with connection.cursor() as cursor:
+                # 构建 OR 条件：每个 website URL（去掉查询参数）作为前缀匹配
+                conditions = []
+                params = []
+                url_mapping = {}  # base_url -> original_url
+                
+                for url, target_id in website_urls:
+                    if not url or target_id is None:
+                        continue
+                    # 使用 urlparse 去掉查询参数和片段，只保留 scheme://netloc/path
+                    parsed = urlparse(url)
+                    base_url = urlunparse((parsed.scheme, parsed.netloc, parsed.path, '', '', ''))
+                    url_mapping[base_url] = url
+                    conditions.append("(v.url LIKE %s AND v.target_id = %s)")
+                    params.extend([base_url + '%', target_id])
+                
+                if not conditions:
+                    return {}
+                
+                where_clause = " OR ".join(conditions)
+                
+                sql = f"""
+                    SELECT v.id, v.vuln_type, v.severity, v.url, v.target_id
+                    FROM vulnerability v
+                    WHERE {where_clause}
+                    ORDER BY 
+                        CASE v.severity 
+                            WHEN 'critical' THEN 1 
+                            WHEN 'high' THEN 2 
+                            WHEN 'medium' THEN 3 
+                            WHEN 'low' THEN 4 
+                            ELSE 5 
+                        END
+                """
+                cursor.execute(sql, params)
+                
+                # 获取所有漏洞
+                all_vulns = []
+                for row in cursor.fetchall():
+                    all_vulns.append({
+                        'id': row[0],
+                        'vuln_type': row[1],
+                        'name': row[1],
+                        'severity': row[2],
+                        'url': row[3],
+                        'target_id': row[4],
+                    })
+                
+                # 按原始 website URL 分组（用于返回结果）
+                result = {url: [] for url, _ in website_urls}
+                for vuln in all_vulns:
+                    vuln_url = vuln['url']
+                    # 找到匹配的 website URL（最长前缀匹配）
+                    for website_url, target_id in website_urls:
+                        parsed = urlparse(website_url)
+                        base_url = urlunparse((parsed.scheme, parsed.netloc, parsed.path, '', '', ''))
+                        if vuln_url.startswith(base_url) and vuln['target_id'] == target_id:
+                            result[website_url].append(vuln)
+                            break
+                
+                return result
+        except Exception as e:
+            logger.error(f"批量查询漏洞失败: {e}")
+            return {}
+    
+    def get(self, request: Request):
+        """搜索资产"""
+        # 获取搜索查询
+        query = request.query_params.get('q', '').strip()
+        
+        if not query:
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Search query (q) is required',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
+        
+        # 获取并验证资产类型
+        asset_type = request.query_params.get('asset_type', 'website').strip().lower()
+        if asset_type not in VALID_ASSET_TYPES:
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message=f'Invalid asset_type. Must be one of: {", ".join(VALID_ASSET_TYPES)}',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
+        
+        # 获取分页参数
+        try:
+            page = int(request.query_params.get('page', 1))
+            page_size = int(request.query_params.get('pageSize', 10))
+        except (ValueError, TypeError):
+            page = 1
+            page_size = 10
+        
+        # 限制分页参数
+        page = max(1, page)
+        page_size = min(max(1, page_size), 100)
+        
+        # 获取总数和搜索结果
+        total = self.service.count(query, asset_type)
+        total_pages = (total + page_size - 1) // page_size if total > 0 else 1
+        offset = (page - 1) * page_size
+        
+        all_results = self.service.search(query, asset_type)
+        results = all_results[offset:offset + page_size]
+        
+        # 批量查询漏洞数据（仅 Website 类型需要）
+        vulnerabilities_by_url = {}
+        if asset_type == 'website':
+            website_urls = [(r.get('url'), r.get('target_id')) for r in results if r.get('url') and r.get('target_id')]
+            vulnerabilities_by_url = self._get_vulnerabilities_by_url_prefix(website_urls) if website_urls else {}
+        
+        # 格式化结果
+        formatted_results = [self._format_result(r, vulnerabilities_by_url, asset_type) for r in results]
+        
+        return success_response(data={
+            'results': formatted_results,
+            'total': total,
+            'page': page,
+            'pageSize': page_size,
+            'totalPages': total_pages,
+            'assetType': asset_type,
+        })
+
+
+class AssetSearchExportView(APIView):
+    """
+    资产搜索导出 API
+    
+    GET /api/assets/search/export/
+    
+    Query Parameters:
+        q: 搜索查询表达式
+        asset_type: 资产类型 ('website' 或 'endpoint'，默认 'website')
+    
+    Response:
+        CSV 文件（带 Content-Length，支持浏览器显示下载进度）
+    """
+    
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        self.service = AssetSearchService()
+    
+    def _get_headers_and_formatters(self, asset_type: str):
+        """获取 CSV 表头和格式化器"""
+        from apps.common.utils import format_datetime, format_list_field
+        
+        if asset_type == 'website':
+            headers = ['url', 'host', 'title', 'status_code', 'content_type', 'content_length', 
+                      'webserver', 'location', 'tech', 'vhost', 'created_at']
+        else:
+            headers = ['url', 'host', 'title', 'status_code', 'content_type', 'content_length',
+                      'webserver', 'location', 'tech', 'matched_gf_patterns', 'vhost', 'created_at']
+        
+        formatters = {
+            'created_at': format_datetime,
+            'tech': lambda x: format_list_field(x, separator='; '),
+            'matched_gf_patterns': lambda x: format_list_field(x, separator='; '),
+            'vhost': lambda x: 'true' if x else ('false' if x is False else ''),
+        }
+        
+        return headers, formatters
+    
+    def get(self, request: Request):
+        """导出搜索结果为 CSV（带 Content-Length，支持下载进度显示）"""
+        from apps.common.utils import create_csv_export_response
+        
+        # 获取搜索查询
+        query = request.query_params.get('q', '').strip()
+        
+        if not query:
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Search query (q) is required',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
+        
+        # 获取并验证资产类型
+        asset_type = request.query_params.get('asset_type', 'website').strip().lower()
+        if asset_type not in VALID_ASSET_TYPES:
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message=f'Invalid asset_type. Must be one of: {", ".join(VALID_ASSET_TYPES)}',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
+        
+        # 检查是否有结果（快速检查，避免空导出）
+        total = self.service.count(query, asset_type)
+        if total == 0:
+            return error_response(
+                code=ErrorCodes.NOT_FOUND,
+                message='No results to export',
+                status_code=status.HTTP_404_NOT_FOUND
+            )
+        
+        # 获取表头和格式化器
+        headers, formatters = self._get_headers_and_formatters(asset_type)
+        
+        # 生成文件名
+        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
+        filename = f'search_{asset_type}_{timestamp}.csv'
+        
+        # 使用通用导出工具
+        data_iterator = self.service.search_iter(query, asset_type)
+        return create_csv_export_response(
+            data_iterator=data_iterator,
+            headers=headers,
+            filename=filename,
+            field_formatters=formatters,
+            show_progress=True  # 显示下载进度
+        )

backend/apps/common/container_bootstrap.py

@@ -40,8 +40,14 @@ def fetch_config_and_setup_django():
     print(f"[CONFIG] 正在从配置中心获取配置: {config_url}")
     print(f"[CONFIG] IS_LOCAL={is_local}")
     try:
+        # 构建请求头（包含 Worker API Key）
+        headers = {}
+        worker_api_key = os.environ.get("WORKER_API_KEY", "")
+        if worker_api_key:
+            headers["X-Worker-API-Key"] = worker_api_key
+        
         # verify=False: 远程 Worker 通过 HTTPS 访问时可能使用自签名证书
-        resp = requests.get(config_url, timeout=10, verify=False)
+        resp = requests.get(config_url, headers=headers, timeout=10, verify=False)
         resp.raise_for_status()
         config = resp.json()
         
@@ -57,28 +63,17 @@ def fetch_config_and_setup_django():
         os.environ.setdefault("DB_USER", db_user)
         os.environ.setdefault("DB_PASSWORD", config['db']['password'])
         
-        # Redis 配置
-        os.environ.setdefault("REDIS_URL", config['redisUrl'])
-        
         # 日志配置
         os.environ.setdefault("LOG_DIR", config['paths']['logs'])
         os.environ.setdefault("LOG_LEVEL", config['logging']['level'])
         os.environ.setdefault("ENABLE_COMMAND_LOGGING", str(config['logging']['enableCommandLogging']).lower())
         os.environ.setdefault("DEBUG", str(config['debug']))
         
-        # Git 加速配置（用于 Git clone 加速）
-        git_mirror = config.get('gitMirror', '')
-        if git_mirror:
-            os.environ.setdefault("GIT_MIRROR", git_mirror)
-        
         print(f"[CONFIG] ✓ 配置获取成功")
         print(f"[CONFIG]   DB_HOST: {db_host}")
         print(f"[CONFIG]   DB_PORT: {db_port}")
         print(f"[CONFIG]   DB_NAME: {db_name}")
         print(f"[CONFIG]   DB_USER: {db_user}")
-        print(f"[CONFIG]   REDIS_URL: {config['redisUrl']}")
-        if git_mirror:
-            print(f"[CONFIG]   GIT_MIRROR: {git_mirror}")
         
     except Exception as e:
         print(f"[ERROR] 获取配置失败: {config_url} - {e}", file=sys.stderr)

backend/apps/common/django_setup.py

@@ -1,16 +1,16 @@
 """
-Prefect Flow Django 环境初始化模块
+Django 环境初始化模块
 
-在所有 Prefect Flow 文件开头导入此模块即可自动配置 Django 环境
+在所有 Worker 脚本开头导入此模块即可自动配置 Django 环境。
 """
 
 import os
 import sys
 
 
-def setup_django_for_prefect():
+def setup_django():
     """
-    为 Prefect Flow 配置 Django 环境
+    配置 Django 环境
 
     此函数会：
     1. 添加项目根目录到 Python 路径
@@ -19,8 +19,8 @@ def setup_django_for_prefect():
     4. 关闭旧的数据库连接，确保使用新连接
 
     使用方式：
-        from apps.common.prefect_django_setup import setup_django_for_prefect
+        from apps.common.django_setup import setup_django
-        setup_django_for_prefect()
+        setup_django()
     """
     # 获取项目根目录（backend 目录）
     current_dir = os.path.dirname(os.path.abspath(__file__))
@@ -59,4 +59,4 @@ def close_old_db_connections():
 
 
 # 自动执行初始化（导入即生效）
-setup_django_for_prefect()
+setup_django()

backend/apps/common/error_codes.py

@@ -0,0 +1,31 @@
+"""
+标准化错误码定义
+
+采用简化方案（参考 Stripe、GitHub 等大厂做法）：
+- 只定义 5-10 个通用错误码
+- 未知错误使用通用错误码
+- 错误码格式：大写字母和下划线组成
+"""
+
+
+class ErrorCodes:
+    """标准化错误码
+    
+    只定义通用错误码，其他错误使用通用消息。
+    这是 Stripe、GitHub 等大厂的标准做法。
+    
+    错误码格式规范：
+    - 使用大写字母和下划线
+    - 简洁明了，易于理解
+    - 前端通过错误码映射到 i18n 键
+    """
+    
+    # 通用错误码（8 个）
+    VALIDATION_ERROR = 'VALIDATION_ERROR'      # 输入验证失败
+    NOT_FOUND = 'NOT_FOUND'                    # 资源未找到
+    PERMISSION_DENIED = 'PERMISSION_DENIED'    # 权限不足
+    SERVER_ERROR = 'SERVER_ERROR'              # 服务器内部错误
+    BAD_REQUEST = 'BAD_REQUEST'                # 请求格式错误
+    CONFLICT = 'CONFLICT'                      # 资源冲突（如重复创建）
+    UNAUTHORIZED = 'UNAUTHORIZED'              # 未认证
+    RATE_LIMITED = 'RATE_LIMITED'              # 请求过于频繁

backend/apps/common/exception_handlers.py

@@ -0,0 +1,49 @@
+"""
+自定义异常处理器
+
+统一处理 DRF 异常，确保错误响应格式一致
+"""
+
+from rest_framework.views import exception_handler
+from rest_framework import status
+from rest_framework.exceptions import AuthenticationFailed, NotAuthenticated
+
+from apps.common.response_helpers import error_response
+from apps.common.error_codes import ErrorCodes
+
+
+def custom_exception_handler(exc, context):
+    """
+    自定义异常处理器
+    
+    处理认证相关异常，返回统一格式的错误响应
+    """
+    # 先调用 DRF 默认的异常处理器
+    response = exception_handler(exc, context)
+    
+    if response is not None:
+        # 处理 401 未认证错误
+        if response.status_code == status.HTTP_401_UNAUTHORIZED:
+            return error_response(
+                code=ErrorCodes.UNAUTHORIZED,
+                message='Authentication required',
+                status_code=status.HTTP_401_UNAUTHORIZED
+            )
+        
+        # 处理 403 权限不足错误
+        if response.status_code == status.HTTP_403_FORBIDDEN:
+            return error_response(
+                code=ErrorCodes.PERMISSION_DENIED,
+                message='Permission denied',
+                status_code=status.HTTP_403_FORBIDDEN
+            )
+    
+    # 处理 NotAuthenticated 和 AuthenticationFailed 异常
+    if isinstance(exc, (NotAuthenticated, AuthenticationFailed)):
+        return error_response(
+            code=ErrorCodes.UNAUTHORIZED,
+            message='Authentication required',
+            status_code=status.HTTP_401_UNAUTHORIZED
+        )
+    
+    return response

backend/apps/common/migrations/0001_initial.py

@@ -0,0 +1,34 @@
+# Generated by Django 5.2.7 on 2026-01-06 00:55
+
+import django.db.models.deletion
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = [
+        ('targets', '0001_initial'),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='BlacklistRule',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('pattern', models.CharField(help_text='规则模式，如 *.gov, 10.0.0.0/8, 192.168.1.1', max_length=255)),
+                ('rule_type', models.CharField(choices=[('domain', '域名'), ('ip', 'IP地址'), ('cidr', 'CIDR范围'), ('keyword', '关键词')], help_text='规则类型：domain, ip, cidr', max_length=20)),
+                ('scope', models.CharField(choices=[('global', '全局规则'), ('target', 'Target规则')], db_index=True, help_text='作用域：global 或 target', max_length=20)),
+                ('description', models.CharField(blank=True, default='', help_text='规则描述', max_length=500)),
+                ('created_at', models.DateTimeField(auto_now_add=True)),
+                ('target', models.ForeignKey(blank=True, help_text='关联的 Target（仅 scope=target 时有值）', null=True, on_delete=django.db.models.deletion.CASCADE, related_name='blacklist_rules', to='targets.target')),
+            ],
+            options={
+                'db_table': 'blacklist_rule',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['scope', 'rule_type'], name='blacklist_r_scope_6ff77f_idx'), models.Index(fields=['target', 'scope'], name='blacklist_r_target__191441_idx')],
+                'constraints': [models.UniqueConstraint(fields=('pattern', 'scope', 'target'), name='unique_blacklist_rule')],
+            },
+        ),
+    ]

backend/apps/common/models/__init__.py

@@ -0,0 +1,4 @@
+"""Common models"""
+from apps.common.models.blacklist import BlacklistRule
+
+__all__ = ['BlacklistRule']

backend/apps/common/models/blacklist.py

@@ -0,0 +1,71 @@
+"""黑名单规则模型"""
+from django.db import models
+
+
+class BlacklistRule(models.Model):
+    """黑名单规则模型
+    
+    用于存储黑名单过滤规则，支持域名、IP、CIDR 三种类型。
+    支持两层作用域：全局规则和 Target 级规则。
+    """
+    
+    class RuleType(models.TextChoices):
+        DOMAIN = 'domain', '域名'
+        IP = 'ip', 'IP地址'
+        CIDR = 'cidr', 'CIDR范围'
+        KEYWORD = 'keyword', '关键词'
+    
+    class Scope(models.TextChoices):
+        GLOBAL = 'global', '全局规则'
+        TARGET = 'target', 'Target规则'
+    
+    id = models.AutoField(primary_key=True)
+    pattern = models.CharField(
+        max_length=255, 
+        help_text='规则模式，如 *.gov, 10.0.0.0/8, 192.168.1.1'
+    )
+    rule_type = models.CharField(
+        max_length=20, 
+        choices=RuleType.choices,
+        help_text='规则类型：domain, ip, cidr'
+    )
+    scope = models.CharField(
+        max_length=20, 
+        choices=Scope.choices, 
+        db_index=True,
+        help_text='作用域：global 或 target'
+    )
+    target = models.ForeignKey(
+        'targets.Target',
+        on_delete=models.CASCADE,
+        null=True, 
+        blank=True,
+        related_name='blacklist_rules',
+        help_text='关联的 Target（仅 scope=target 时有值）'
+    )
+    description = models.CharField(
+        max_length=500, 
+        blank=True, 
+        default='', 
+        help_text='规则描述'
+    )
+    created_at = models.DateTimeField(auto_now_add=True)
+    
+    class Meta:
+        db_table = 'blacklist_rule'
+        indexes = [
+            models.Index(fields=['scope', 'rule_type']),
+            models.Index(fields=['target', 'scope']),
+        ]
+        constraints = [
+            models.UniqueConstraint(
+                fields=['pattern', 'scope', 'target'],
+                name='unique_blacklist_rule'
+            ),
+        ]
+        ordering = ['-created_at']
+    
+    def __str__(self):
+        if self.scope == self.Scope.TARGET and self.target:
+            return f"[{self.scope}:{self.target_id}] {self.pattern}"
+        return f"[{self.scope}] {self.pattern}"

backend/apps/common/permissions.py

@@ -0,0 +1,80 @@
+"""
+集中式权限管理
+
+实现三类端点的认证逻辑：
+1. 公开端点（无需认证）：登录、登出、获取当前用户状态
+2. Worker 端点（API Key 认证）：注册、配置、心跳、回调、资源同步
+3. 业务端点（Session 认证）：其他所有 API
+"""
+
+import re
+import logging
+from django.conf import settings
+from rest_framework.permissions import BasePermission
+
+logger = logging.getLogger(__name__)
+
+# 公开端点白名单（无需任何认证）
+PUBLIC_ENDPOINTS = [
+    r'^/api/auth/login/$',
+    r'^/api/auth/logout/$',
+    r'^/api/auth/me/$',
+]
+
+# Worker API 端点（需要 API Key 认证）
+# 包括：注册、配置、心跳、回调、资源同步（字典下载）
+WORKER_ENDPOINTS = [
+    r'^/api/workers/register/$',
+    r'^/api/workers/config/$',
+    r'^/api/workers/\d+/heartbeat/$',
+    r'^/api/callbacks/',
+    # 资源同步端点（Worker 需要下载字典文件）
+    r'^/api/wordlists/download/$',
+    # 注意：指纹导出 API 使用 Session 认证（前端用户导出用）
+    # Worker 通过数据库直接获取指纹数据，不需要 HTTP API
+]
+
+
+class IsAuthenticatedOrPublic(BasePermission):
+    """
+    自定义权限类：
+    - 白名单内的端点公开访问
+    - Worker 端点需要 API Key 认证
+    - 其他端点需要 Session 认证
+    """
+    
+    def has_permission(self, request, view):
+        path = request.path
+        
+        # 检查是否在公开白名单内
+        for pattern in PUBLIC_ENDPOINTS:
+            if re.match(pattern, path):
+                return True
+        
+        # 检查是否是 Worker 端点
+        for pattern in WORKER_ENDPOINTS:
+            if re.match(pattern, path):
+                return self._check_worker_api_key(request)
+        
+        # 其他路径需要 Session 认证
+        return request.user and request.user.is_authenticated
+    
+    def _check_worker_api_key(self, request):
+        """验证 Worker API Key"""
+        api_key = request.headers.get('X-Worker-API-Key')
+        expected_key = getattr(settings, 'WORKER_API_KEY', None)
+        
+        if not expected_key:
+            # 未配置 API Key 时，拒绝所有 Worker 请求
+            logger.warning("WORKER_API_KEY 未配置，拒绝 Worker 请求")
+            return False
+        
+        if not api_key:
+            logger.warning(f"Worker 请求缺少 X-Worker-API-Key Header: {request.path}")
+            return False
+        
+        if api_key != expected_key:
+            logger.warning(f"Worker API Key 无效: {request.path}")
+            return False
+        
+        return True

backend/apps/common/response_helpers.py

@@ -0,0 +1,88 @@
+"""
+标准化 API 响应辅助函数
+
+遵循行业标准（RFC 9457 Problem Details）和大厂实践（Google、Stripe、GitHub）：
+- 成功响应只包含数据，不包含 message 字段
+- 错误响应使用机器可读的错误码，前端映射到 i18n 消息
+"""
+from typing import Any, Dict, List, Optional, Union
+
+from rest_framework import status
+from rest_framework.response import Response
+
+
+def success_response(
+    data: Optional[Union[Dict[str, Any], List[Any]]] = None,
+    status_code: int = status.HTTP_200_OK
+) -> Response:
+    """
+    标准化成功响应
+    
+    直接返回数据，不做包装，符合 Stripe/GitHub 等大厂标准。
+    
+    Args:
+        data: 响应数据（dict 或 list）
+        status_code: HTTP 状态码，默认 200
+    
+    Returns:
+        Response: DRF Response 对象
+    
+    Examples:
+        # 单个资源
+        >>> success_response(data={'id': 1, 'name': 'Test'})
+        {'id': 1, 'name': 'Test'}
+        
+        # 操作结果
+        >>> success_response(data={'count': 3, 'scans': [...]})
+        {'count': 3, 'scans': [...]}
+        
+        # 创建资源
+        >>> success_response(data={'id': 1}, status_code=201)
+    """
+    # 注意：不能使用 data or {}，因为空列表 [] 会被转换为 {}
+    if data is None:
+        data = {}
+    return Response(data, status=status_code)
+
+
+def error_response(
+    code: str,
+    message: Optional[str] = None,
+    details: Optional[List[Dict[str, Any]]] = None,
+    status_code: int = status.HTTP_400_BAD_REQUEST
+) -> Response:
+    """
+    标准化错误响应
+    
+    Args:
+        code: 错误码（如 'VALIDATION_ERROR', 'NOT_FOUND'）
+              格式：大写字母和下划线组成
+        message: 开发者调试信息（非用户显示）
+        details: 详细错误信息（如字段级验证错误）
+        status_code: HTTP 状态码，默认 400
+    
+    Returns:
+        Response: DRF Response 对象
+    
+    Examples:
+        # 简单错误
+        >>> error_response(code='NOT_FOUND', status_code=404)
+        {'error': {'code': 'NOT_FOUND'}}
+        
+        # 带调试信息
+        >>> error_response(
+        ...     code='VALIDATION_ERROR',
+        ...     message='Invalid input data',
+        ...     details=[{'field': 'name', 'message': 'Required'}]
+        ... )
+        {'error': {'code': 'VALIDATION_ERROR', 'message': '...', 'details': [...]}}
+    """
+    error_body: Dict[str, Any] = {'code': code}
+    
+    if message:
+        error_body['message'] = message
+    
+    if details:
+        error_body['details'] = details
+    
+    return Response({'error': error_body}, status=status_code)

backend/apps/common/serializers/__init__.py

@@ -0,0 +1,12 @@
+"""Common serializers"""
+from .blacklist_serializers import (
+    BlacklistRuleSerializer,
+    GlobalBlacklistRuleSerializer,
+    TargetBlacklistRuleSerializer,
+)
+
+__all__ = [
+    'BlacklistRuleSerializer',
+    'GlobalBlacklistRuleSerializer',
+    'TargetBlacklistRuleSerializer',
+]

backend/apps/common/serializers/blacklist_serializers.py

@@ -0,0 +1,68 @@
+"""黑名单规则序列化器"""
+from rest_framework import serializers
+
+from apps.common.models import BlacklistRule
+from apps.common.utils import detect_rule_type
+
+
+class BlacklistRuleSerializer(serializers.ModelSerializer):
+    """黑名单规则序列化器"""
+    
+    class Meta:
+        model = BlacklistRule
+        fields = [
+            'id',
+            'pattern',
+            'rule_type',
+            'scope',
+            'target',
+            'description',
+            'created_at',
+        ]
+        read_only_fields = ['id', 'rule_type', 'created_at']
+    
+    def validate_pattern(self, value):
+        """验证规则模式"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("规则模式不能为空")
+        return value.strip()
+    
+    def create(self, validated_data):
+        """创建规则时自动识别规则类型"""
+        pattern = validated_data.get('pattern', '')
+        validated_data['rule_type'] = detect_rule_type(pattern)
+        return super().create(validated_data)
+    
+    def update(self, instance, validated_data):
+        """更新规则时重新识别规则类型"""
+        if 'pattern' in validated_data:
+            pattern = validated_data['pattern']
+            validated_data['rule_type'] = detect_rule_type(pattern)
+        return super().update(instance, validated_data)
+
+
+class GlobalBlacklistRuleSerializer(BlacklistRuleSerializer):
+    """全局黑名单规则序列化器"""
+    
+    class Meta(BlacklistRuleSerializer.Meta):
+        fields = ['id', 'pattern', 'rule_type', 'description', 'created_at']
+        read_only_fields = ['id', 'rule_type', 'created_at']
+    
+    def create(self, validated_data):
+        """创建全局规则"""
+        validated_data['scope'] = BlacklistRule.Scope.GLOBAL
+        validated_data['target'] = None
+        return super().create(validated_data)
+
+
+class TargetBlacklistRuleSerializer(BlacklistRuleSerializer):
+    """Target 黑名单规则序列化器"""
+    
+    class Meta(BlacklistRuleSerializer.Meta):
+        fields = ['id', 'pattern', 'rule_type', 'description', 'created_at']
+        read_only_fields = ['id', 'rule_type', 'created_at']
+    
+    def create(self, validated_data):
+        """创建 Target 规则（target_id 由 view 设置）"""
+        validated_data['scope'] = BlacklistRule.Scope.TARGET
+        return super().create(validated_data)

backend/apps/common/services/__init__.py

@@ -3,13 +3,16 @@
 
 提供系统级别的公共服务，包括：
 - SystemLogService: 系统日志读取服务
+- BlacklistService: 黑名单过滤服务
 
 注意：FilterService 已移至 apps.common.utils.filter_utils
 推荐使用: from apps.common.utils.filter_utils import apply_filters
 """
 
 from .system_log_service import SystemLogService
+from .blacklist_service import BlacklistService
 
 __all__ = [
     'SystemLogService',
+    'BlacklistService',
 ]

backend/apps/common/services/blacklist_service.py

@@ -0,0 +1,176 @@
+"""
+黑名单规则管理服务
+
+负责黑名单规则的 CRUD 操作（数据库层面）。
+过滤逻辑请使用 apps.common.utils.BlacklistFilter。
+
+架构说明：
+- Model: BlacklistRule (apps.common.models.blacklist)
+- Service: BlacklistService (本文件) - 规则 CRUD
+- Utils: BlacklistFilter (apps.common.utils.blacklist_filter) - 过滤逻辑
+- View: GlobalBlacklistView, TargetViewSet.blacklist
+"""
+
+import logging
+from typing import List, Dict, Any, Optional
+
+from django.db.models import QuerySet
+
+from apps.common.utils import detect_rule_type
+
+logger = logging.getLogger(__name__)
+
+
+def _normalize_patterns(patterns: List[str]) -> List[str]:
+    """
+    规范化规则列表：去重 + 过滤空行
+    
+    Args:
+        patterns: 原始规则列表
+        
+    Returns:
+        List[str]: 去重后的规则列表（保持顺序）
+    """
+    return list(dict.fromkeys(filter(None, (p.strip() for p in patterns))))
+
+
+class BlacklistService:
+    """
+    黑名单规则管理服务
+    
+    只负责规则的 CRUD 操作，不包含过滤逻辑。
+    过滤逻辑请使用 BlacklistFilter 工具类。
+    """
+    
+    def get_global_rules(self) -> QuerySet:
+        """
+        获取全局黑名单规则列表
+        
+        Returns:
+            QuerySet: 全局规则查询集
+        """
+        from apps.common.models import BlacklistRule
+        return BlacklistRule.objects.filter(scope=BlacklistRule.Scope.GLOBAL)
+    
+    def get_target_rules(self, target_id: int) -> QuerySet:
+        """
+        获取 Target 级黑名单规则列表
+        
+        Args:
+            target_id: Target ID
+            
+        Returns:
+            QuerySet: Target 级规则查询集
+        """
+        from apps.common.models import BlacklistRule
+        return BlacklistRule.objects.filter(
+            scope=BlacklistRule.Scope.TARGET,
+            target_id=target_id
+        )
+    
+    def get_rules(self, target_id: Optional[int] = None) -> List:
+        """
+        获取黑名单规则（全局 + Target 级）
+        
+        Args:
+            target_id: Target ID，用于加载 Target 级规则
+            
+        Returns:
+            List[BlacklistRule]: 规则列表
+        """
+        from apps.common.models import BlacklistRule
+        
+        # 加载全局规则
+        rules = list(BlacklistRule.objects.filter(scope=BlacklistRule.Scope.GLOBAL))
+        
+        # 加载 Target 级规则
+        if target_id:
+            target_rules = BlacklistRule.objects.filter(
+                scope=BlacklistRule.Scope.TARGET,
+                target_id=target_id
+            )
+            rules.extend(target_rules)
+        
+        return rules
+    
+    def replace_global_rules(self, patterns: List[str]) -> Dict[str, Any]:
+        """
+        全量替换全局黑名单规则（PUT 语义）
+        
+        Args:
+            patterns: 新的规则模式列表
+            
+        Returns:
+            Dict: {'count': int} 最终规则数量
+        """
+        from apps.common.models import BlacklistRule
+        
+        count = self._replace_rules(
+            patterns=patterns,
+            scope=BlacklistRule.Scope.GLOBAL,
+            target=None
+        )
+        
+        logger.info("全量替换全局黑名单规则: %d 条", count)
+        return {'count': count}
+    
+    def replace_target_rules(self, target, patterns: List[str]) -> Dict[str, Any]:
+        """
+        全量替换 Target 级黑名单规则（PUT 语义）
+        
+        Args:
+            target: Target 对象
+            patterns: 新的规则模式列表
+            
+        Returns:
+            Dict: {'count': int} 最终规则数量
+        """
+        from apps.common.models import BlacklistRule
+        
+        count = self._replace_rules(
+            patterns=patterns,
+            scope=BlacklistRule.Scope.TARGET,
+            target=target
+        )
+        
+        logger.info("全量替换 Target 黑名单规则: %d 条 (Target: %s)", count, target.name)
+        return {'count': count}
+    
+    def _replace_rules(self, patterns: List[str], scope: str, target=None) -> int:
+        """
+        内部方法：全量替换规则
+        
+        Args:
+            patterns: 规则模式列表
+            scope: 规则作用域 (GLOBAL/TARGET)
+            target: Target 对象（仅 TARGET 作用域需要）
+            
+        Returns:
+            int: 最终规则数量
+        """
+        from apps.common.models import BlacklistRule
+        from django.db import transaction
+        
+        patterns = _normalize_patterns(patterns)
+        
+        with transaction.atomic():
+            # 1. 删除旧规则
+            delete_filter = {'scope': scope}
+            if target:
+                delete_filter['target'] = target
+            BlacklistRule.objects.filter(**delete_filter).delete()
+            
+            # 2. 创建新规则
+            if patterns:
+                rules = [
+                    BlacklistRule(
+                        pattern=pattern,
+                        rule_type=detect_rule_type(pattern),
+                        scope=scope,
+                        target=target
+                    )
+                    for pattern in patterns
+                ]
+                BlacklistRule.objects.bulk_create(rules)
+        
+        return len(patterns)

backend/apps/common/services/system_log_service.py

@@ -4,15 +4,28 @@
 提供系统日志的读取功能，支持：
 - 从日志目录读取日志文件
 - 限制返回行数，防止内存溢出
+- 列出可用的日志文件
 """
 
+import fnmatch
 import logging
+import os
 import subprocess
+from datetime import datetime, timezone
+from typing import TypedDict
 
 
 logger = logging.getLogger(__name__)
 
 
+class LogFileInfo(TypedDict):
+    """日志文件信息"""
+    filename: str
+    category: str  # 'system' | 'error' | 'performance' | 'container'
+    size: int
+    modifiedAt: str  # ISO 8601 格式
+
+
 class SystemLogService:
     """
     系统日志服务类
@@ -20,23 +33,131 @@ class SystemLogService:
     负责读取系统日志文件，支持从容器内路径或宿主机挂载路径读取日志。
     """
     
-    def __init__(self):
+    # 日志文件分类规则
-        # 日志文件路径（统一使用 /opt/xingrin/logs）
+    CATEGORY_RULES = [
-        self.log_file = "/opt/xingrin/logs/xingrin.log"
+        ('xingrin.log', 'system'),
-        self.default_lines = 200        # 默认返回行数
+        ('xingrin_error.log', 'error'),
-        self.max_lines = 10000          # 最大返回行数限制
+        ('performance.log', 'performance'),
-        self.timeout_seconds = 3        # tail 命令超时时间
+        ('container_*.log', 'container'),
+    ]
     
-    def get_logs_content(self, lines: int | None = None) -> str:
+    def __init__(self):
+        # 日志目录路径
+        self.log_dir = "/opt/xingrin/logs"
+        self.default_file = "xingrin.log"  # 默认日志文件
+        self.default_lines = 200           # 默认返回行数
+        self.max_lines = 10000             # 最大返回行数限制
+        self.timeout_seconds = 3           # tail 命令超时时间
+
+    def _categorize_file(self, filename: str) -> str | None:
+        """
+        根据文件名判断日志分类
+        
+        Returns:
+            分类名称，如果不是日志文件则返回 None
+        """
+        for pattern, category in self.CATEGORY_RULES:
+            if fnmatch.fnmatch(filename, pattern):
+                return category
+        return None
+
+    def _validate_filename(self, filename: str) -> bool:
+        """
+        验证文件名是否合法（防止路径遍历攻击）
+        
+        Args:
+            filename: 要验证的文件名
+            
+        Returns:
+            bool: 文件名是否合法
+        """
+        # 不允许包含路径分隔符
+        if '/' in filename or '\\' in filename:
+            return False
+        # 不允许 .. 路径遍历
+        if '..' in filename:
+            return False
+        # 必须是已知的日志文件类型
+        return self._categorize_file(filename) is not None
+
+    def get_log_files(self) -> list[LogFileInfo]:
+        """
+        获取所有可用的日志文件列表
+        
+        Returns:
+            日志文件信息列表，按分类和文件名排序
+        """
+        files: list[LogFileInfo] = []
+        
+        if not os.path.isdir(self.log_dir):
+            logger.warning("日志目录不存在: %s", self.log_dir)
+            return files
+        
+        for filename in os.listdir(self.log_dir):
+            filepath = os.path.join(self.log_dir, filename)
+            
+            # 只处理文件，跳过目录
+            if not os.path.isfile(filepath):
+                continue
+            
+            # 判断分类
+            category = self._categorize_file(filename)
+            if category is None:
+                continue
+            
+            # 获取文件信息
+            try:
+                stat = os.stat(filepath)
+                modified_at = datetime.fromtimestamp(
+                    stat.st_mtime, tz=timezone.utc
+                ).isoformat()
+                
+                files.append({
+                    'filename': filename,
+                    'category': category,
+                    'size': stat.st_size,
+                    'modifiedAt': modified_at,
+                })
+            except OSError as e:
+                logger.warning("获取文件信息失败 %s: %s", filepath, e)
+                continue
+        
+        # 排序：按分类优先级（system > error > performance > container），然后按文件名
+        category_order = {'system': 0, 'error': 1, 'performance': 2, 'container': 3}
+        files.sort(key=lambda f: (category_order.get(f['category'], 99), f['filename']))
+        
+        return files
+
+    def get_logs_content(self, filename: str | None = None, lines: int | None = None) -> str:
         """
         获取系统日志内容
         
         Args:
+            filename: 日志文件名，默认为 xingrin.log
             lines: 返回的日志行数，默认 200 行，最大 10000 行
             
         Returns:
             str: 日志内容，每行以换行符分隔，保持原始顺序
+            
+        Raises:
+            ValueError: 文件名不合法
+            FileNotFoundError: 日志文件不存在
         """
+        # 文件名处理
+        if filename is None:
+            filename = self.default_file
+        
+        # 验证文件名
+        if not self._validate_filename(filename):
+            raise ValueError(f"无效的文件名: {filename}")
+        
+        # 构建完整路径
+        log_file = os.path.join(self.log_dir, filename)
+        
+        # 检查文件是否存在
+        if not os.path.isfile(log_file):
+            raise FileNotFoundError(f"日志文件不存在: {filename}")
+        
         # 参数校验和默认值处理
         if lines is None:
             lines = self.default_lines
@@ -48,7 +169,7 @@ class SystemLogService:
             lines = self.max_lines
 
         # 使用 tail 命令读取日志文件末尾内容
-        cmd = ["tail", "-n", str(lines), self.log_file]
+        cmd = ["tail", "-n", str(lines), log_file]
 
         result = subprocess.run(
             cmd,

backend/apps/common/urls.py

@@ -2,14 +2,25 @@
 通用模块 URL 配置
 
 路由说明：
-- /api/auth/*     认证相关接口（登录、登出、用户信息）
+- /api/health/       健康检查接口（无需认证）
-- /api/system/*   系统管理接口（日志查看等）
+- /api/auth/*        认证相关接口（登录、登出、用户信息）
+- /api/system/*      系统管理接口（日志查看等）
+- /api/blacklist/*   黑名单管理接口
 """
 
 from django.urls import path
-from .views import LoginView, LogoutView, MeView, ChangePasswordView, SystemLogsView
+
+from .views import (
+    LoginView, LogoutView, MeView, ChangePasswordView,
+    SystemLogsView, SystemLogFilesView, HealthCheckView,
+    GlobalBlacklistView,
+    VersionView, CheckUpdateView,
+)
 
 urlpatterns = [
+    # 健康检查（无需认证）
+    path('health/', HealthCheckView.as_view(), name='health-check'),
+    
     # 认证相关
     path('auth/login/', LoginView.as_view(), name='auth-login'),
     path('auth/logout/', LogoutView.as_view(), name='auth-logout'),
@@ -18,4 +29,10 @@ urlpatterns = [
     
     # 系统管理
     path('system/logs/', SystemLogsView.as_view(), name='system-logs'),
+    path('system/logs/files/', SystemLogFilesView.as_view(), name='system-log-files'),
+    path('system/version/', VersionView.as_view(), name='system-version'),
+    path('system/check-update/', CheckUpdateView.as_view(), name='system-check-update'),
+    
+    # 黑名单管理（PUT 全量替换模式）
+    path('blacklist/rules/', GlobalBlacklistView.as_view(), name='blacklist-rules'),
 ]

backend/apps/common/utils/__init__.py

@@ -11,9 +11,14 @@ from .csv_utils import (
     generate_csv_rows,
     format_list_field,
     format_datetime,
+    create_csv_export_response,
     UTF8_BOM,
 )
-from .git_proxy import get_git_proxy_url
+from .blacklist_filter import (
+    BlacklistFilter,
+    detect_rule_type,
+    extract_host,
+)
 
 __all__ = [
     'deduplicate_for_bulk',
@@ -25,6 +30,9 @@ __all__ = [
     'generate_csv_rows',
     'format_list_field',
     'format_datetime',
+    'create_csv_export_response',
     'UTF8_BOM',
-    'get_git_proxy_url',
+    'BlacklistFilter',
+    'detect_rule_type',
+    'extract_host',
 ]

backend/apps/common/utils/blacklist_filter.py

@@ -0,0 +1,246 @@
+"""
+黑名单过滤工具
+
+提供域名、IP、CIDR、关键词的黑名单匹配功能。
+纯工具类，不涉及数据库操作。
+
+支持的规则类型：
+    1. 域名精确匹配: example.com
+       - 规则: example.com
+       - 匹配: example.com
+       - 不匹配: sub.example.com, other.com
+    
+    2. 域名后缀匹配: *.example.com
+       - 规则: *.example.com
+       - 匹配: sub.example.com, a.b.example.com, example.com
+       - 不匹配: other.com, example.com.cn
+    
+    3. 关键词匹配: *cdn*
+       - 规则: *cdn*
+       - 匹配: cdn.example.com, a.cdn.b.com, mycdn123.com
+       - 不匹配: example.com (不包含 cdn)
+    
+    4. IP 精确匹配: 192.168.1.1
+       - 规则: 192.168.1.1
+       - 匹配: 192.168.1.1
+       - 不匹配: 192.168.1.2
+    
+    5. CIDR 范围匹配: 192.168.0.0/24
+       - 规则: 192.168.0.0/24
+       - 匹配: 192.168.0.1, 192.168.0.255
+       - 不匹配: 192.168.1.1
+
+使用方式：
+    from apps.common.utils import BlacklistFilter
+    
+    # 创建过滤器（传入规则列表）
+    rules = BlacklistRule.objects.filter(...)
+    filter = BlacklistFilter(rules)
+    
+    # 检查单个目标
+    if filter.is_allowed('http://example.com'):
+        process(url)
+    
+    # 流式处理
+    for url in urls:
+        if filter.is_allowed(url):
+            process(url)
+"""
+
+import ipaddress
+import logging
+from typing import List, Optional
+from urllib.parse import urlparse
+
+from apps.common.validators import is_valid_ip, validate_cidr
+
+logger = logging.getLogger(__name__)
+
+
+def detect_rule_type(pattern: str) -> str:
+    """
+    自动识别规则类型
+    
+    支持的模式：
+    - 域名精确匹配: example.com
+    - 域名后缀匹配: *.example.com
+    - 关键词匹配: *cdn* (匹配包含 cdn 的域名)
+    - IP 精确匹配: 192.168.1.1
+    - CIDR 范围: 192.168.0.0/24
+    
+    Args:
+        pattern: 规则模式字符串
+        
+    Returns:
+        str: 规则类型 ('domain', 'ip', 'cidr', 'keyword')
+    """
+    if not pattern:
+        return 'domain'
+    
+    pattern = pattern.strip()
+    
+    # 检查关键词模式: *keyword* (前后都有星号，中间无点)
+    if pattern.startswith('*') and pattern.endswith('*') and len(pattern) > 2:
+        keyword = pattern[1:-1]
+        # 关键词中不能有点（否则可能是域名模式）
+        if '.' not in keyword:
+            return 'keyword'
+    
+    # 检查 CIDR（包含 /）
+    if '/' in pattern:
+        try:
+            validate_cidr(pattern)
+            return 'cidr'
+        except ValueError:
+            pass
+    
+    # 检查 IP（去掉通配符前缀后验证）
+    clean_pattern = pattern.lstrip('*').lstrip('.')
+    if is_valid_ip(clean_pattern):
+        return 'ip'
+    
+    # 默认为域名
+    return 'domain'
+
+
+def extract_host(target: str) -> str:
+    """
+    从目标字符串中提取主机名
+    
+    支持：
+    - 纯域名：example.com
+    - 纯 IP：192.168.1.1
+    - URL：http://example.com/path
+    
+    Args:
+        target: 目标字符串
+        
+    Returns:
+        str: 提取的主机名
+    """
+    if not target:
+        return ''
+    
+    target = target.strip()
+    
+    # 如果是 URL，提取 hostname
+    if '://' in target:
+        try:
+            parsed = urlparse(target)
+            return parsed.hostname or target
+        except Exception:
+            return target
+    
+    return target
+
+
+class BlacklistFilter:
+    """
+    黑名单过滤器
+    
+    预编译规则，提供高效的匹配功能。
+    """
+    
+    def __init__(self, rules: List):
+        """
+        初始化过滤器
+        
+        Args:
+            rules: BlacklistRule 对象列表
+        """
+        from apps.common.models import BlacklistRule
+        
+        # 预解析：按类型分类 + CIDR 预编译
+        self._domain_rules = []  # (pattern, is_wildcard, suffix)
+        self._ip_rules = set()   # 精确 IP 用 set，O(1) 查找
+        self._cidr_rules = []    # (pattern, network_obj)
+        self._keyword_rules = [] # 关键词列表（小写）
+        
+        # 去重：跨 scope 可能有重复规则
+        seen_patterns = set()
+        
+        for rule in rules:
+            if rule.pattern in seen_patterns:
+                continue
+            seen_patterns.add(rule.pattern)
+            if rule.rule_type == BlacklistRule.RuleType.DOMAIN:
+                pattern = rule.pattern.lower()
+                if pattern.startswith('*.'):
+                    self._domain_rules.append((pattern, True, pattern[1:]))
+                else:
+                    self._domain_rules.append((pattern, False, None))
+            elif rule.rule_type == BlacklistRule.RuleType.IP:
+                self._ip_rules.add(rule.pattern)
+            elif rule.rule_type == BlacklistRule.RuleType.CIDR:
+                try:
+                    network = ipaddress.ip_network(rule.pattern, strict=False)
+                    self._cidr_rules.append((rule.pattern, network))
+                except ValueError:
+                    pass
+            elif rule.rule_type == BlacklistRule.RuleType.KEYWORD:
+                # *cdn* -> cdn
+                keyword = rule.pattern[1:-1].lower()
+                self._keyword_rules.append(keyword)
+    
+    def is_allowed(self, target: str) -> bool:
+        """
+        检查目标是否通过过滤
+        
+        Args:
+            target: 要检查的目标（域名/IP/URL）
+            
+        Returns:
+            bool: True 表示通过（不在黑名单），False 表示被过滤
+        """
+        if not target:
+            return True
+        
+        host = extract_host(target)
+        if not host:
+            return True
+        
+        # 先判断输入类型，再走对应分支
+        if is_valid_ip(host):
+            return self._check_ip_rules(host)
+        else:
+            return self._check_domain_rules(host)
+    
+    def _check_domain_rules(self, host: str) -> bool:
+        """检查域名规则（精确匹配 + 后缀匹配 + 关键词匹配）"""
+        host_lower = host.lower()
+        
+        # 1. 域名规则（精确 + 后缀）
+        for pattern, is_wildcard, suffix in self._domain_rules:
+            if is_wildcard:
+                if host_lower.endswith(suffix) or host_lower == pattern[2:]:
+                    return False
+            else:
+                if host_lower == pattern:
+                    return False
+        
+        # 2. 关键词匹配（字符串 in 操作，O(n*m)）
+        for keyword in self._keyword_rules:
+            if keyword in host_lower:
+                return False
+        
+        return True
+    
+    def _check_ip_rules(self, host: str) -> bool:
+        """检查 IP 规则（精确匹配 + CIDR）"""
+        # 1. IP 精确匹配（O(1)）
+        if host in self._ip_rules:
+            return False
+        
+        # 2. CIDR 匹配
+        if self._cidr_rules:
+            try:
+                ip_obj = ipaddress.ip_address(host)
+                for _, network in self._cidr_rules:
+                    if ip_obj in network:
+                        return False
+            except ValueError:
+                pass
+        
+        return True
+    
+

backend/apps/common/utils/csv_utils.py

@@ -4,13 +4,21 @@
 - UTF-8 BOM（Excel 兼容）
 - RFC 4180 规范转义
 - 流式生成（内存友好）
+- 带 Content-Length 的文件响应（支持浏览器下载进度显示）
 """
 
 import csv
 import io
+import os
+import tempfile
+import logging
 from datetime import datetime
 from typing import Iterator, Dict, Any, List, Callable, Optional
 
+from django.http import FileResponse, StreamingHttpResponse
+
+logger = logging.getLogger(__name__)
+
 # UTF-8 BOM，确保 Excel 正确识别编码
 UTF8_BOM = '\ufeff'
 
@@ -114,3 +122,123 @@ def format_datetime(dt: Optional[datetime]) -> str:
         dt = timezone.localtime(dt)
     
     return dt.strftime('%Y-%m-%d %H:%M:%S')
+
+
+def create_csv_export_response(
+    data_iterator: Iterator[Dict[str, Any]],
+    headers: List[str],
+    filename: str,
+    field_formatters: Optional[Dict[str, Callable]] = None,
+    show_progress: bool = True
+) -> FileResponse | StreamingHttpResponse:
+    """
+    创建 CSV 导出响应
+    
+    根据 show_progress 参数选择响应类型：
+    - True: 使用临时文件 + FileResponse，带 Content-Length（浏览器显示下载进度）
+    - False: 使用 StreamingHttpResponse（内存更友好，但无下载进度）
+    
+    Args:
+        data_iterator: 数据迭代器，每个元素是一个字典
+        headers: CSV 表头列表
+        filename: 下载文件名（如 "export_2024.csv"）
+        field_formatters: 字段格式化函数字典
+        show_progress: 是否显示下载进度（默认 True）
+    
+    Returns:
+        FileResponse 或 StreamingHttpResponse
+    
+    Example:
+        >>> data_iter = service.iter_data()
+        >>> headers = ['url', 'host', 'created_at']
+        >>> formatters = {'created_at': format_datetime}
+        >>> response = create_csv_export_response(
+        ...     data_iter, headers, 'websites.csv', formatters
+        ... )
+        >>> return response
+    """
+    if show_progress:
+        return _create_file_response(data_iterator, headers, filename, field_formatters)
+    else:
+        return _create_streaming_response(data_iterator, headers, filename, field_formatters)
+
+
+def _create_file_response(
+    data_iterator: Iterator[Dict[str, Any]],
+    headers: List[str],
+    filename: str,
+    field_formatters: Optional[Dict[str, Callable]] = None
+) -> FileResponse:
+    """
+    创建带 Content-Length 的文件响应（支持浏览器下载进度）
+    
+    实现方式：先写入临时文件，再返回 FileResponse
+    """
+    # 创建临时文件
+    temp_file = tempfile.NamedTemporaryFile(
+        mode='w', 
+        suffix='.csv', 
+        delete=False, 
+        encoding='utf-8'
+    )
+    temp_path = temp_file.name
+    
+    try:
+        # 流式写入 CSV 数据到临时文件
+        for row in generate_csv_rows(data_iterator, headers, field_formatters):
+            temp_file.write(row)
+        temp_file.close()
+        
+        # 获取文件大小
+        file_size = os.path.getsize(temp_path)
+        
+        # 创建文件响应
+        response = FileResponse(
+            open(temp_path, 'rb'),
+            content_type='text/csv; charset=utf-8',
+            as_attachment=True,
+            filename=filename
+        )
+        response['Content-Length'] = file_size
+        
+        # 设置清理回调：响应完成后删除临时文件
+        original_close = response.file_to_stream.close
+        def close_and_cleanup():
+            original_close()
+            try:
+                os.unlink(temp_path)
+            except OSError:
+                pass
+        response.file_to_stream.close = close_and_cleanup
+        
+        return response
+        
+    except Exception as e:
+        # 清理临时文件
+        try:
+            temp_file.close()
+        except:
+            pass
+        try:
+            os.unlink(temp_path)
+        except OSError:
+            pass
+        logger.error(f"创建 CSV 导出响应失败: {e}")
+        raise
+
+
+def _create_streaming_response(
+    data_iterator: Iterator[Dict[str, Any]],
+    headers: List[str],
+    filename: str,
+    field_formatters: Optional[Dict[str, Callable]] = None
+) -> StreamingHttpResponse:
+    """
+    创建流式响应（无 Content-Length，内存更友好）
+    """
+    response = StreamingHttpResponse(
+        generate_csv_rows(data_iterator, headers, field_formatters),
+        content_type='text/csv; charset=utf-8'
+    )
+    response['Content-Disposition'] = f'attachment; filename="{filename}"'
+    return response

backend/apps/common/utils/filter_utils.py

@@ -29,11 +29,19 @@ from dataclasses import dataclass
 from typing import List, Dict, Optional, Union
 from enum import Enum
 
-from django.db.models import QuerySet, Q
+from django.db.models import QuerySet, Q, F, Func, CharField
+from django.db.models.functions import Cast
 
 logger = logging.getLogger(__name__)
 
 
+class ArrayToString(Func):
+    """PostgreSQL array_to_string 函数"""
+    function = 'array_to_string'
+    template = "%(function)s(%(expressions)s, ',')"
+    output_field = CharField()
+
+
 class LogicalOp(Enum):
     """逻辑运算符"""
     AND = 'AND'
@@ -86,9 +94,21 @@ class QueryParser:
         if not query_string or not query_string.strip():
             return []
         
+        # 第一步：提取所有过滤条件并用占位符替换，保护引号内的空格
+        filters_found = []
+        placeholder_pattern = '__FILTER_{}__'
+        
+        def replace_filter(match):
+            idx = len(filters_found)
+            filters_found.append(match.group(0))
+            return placeholder_pattern.format(idx)
+        
+        # 先用正则提取所有 field="value" 形式的条件
+        protected = cls.FILTER_PATTERN.sub(replace_filter, query_string)
+        
         # 标准化逻辑运算符
         # 先处理 || 和 or -> __OR__
-        normalized = cls.OR_PATTERN.sub(' __OR__ ', query_string)
+        normalized = cls.OR_PATTERN.sub(' __OR__ ', protected)
         # 再处理 && 和 and -> __AND__
         normalized = cls.AND_PATTERN.sub(' __AND__ ', normalized)
         
@@ -103,20 +123,26 @@ class QueryParser:
                 pending_op = LogicalOp.OR
             elif token == '__AND__':
                 pending_op = LogicalOp.AND
-            else:
+            elif token.startswith('__FILTER_') and token.endswith('__'):
-                # 尝试解析为过滤条件
+                # 还原占位符为原始过滤条件
-                match = cls.FILTER_PATTERN.match(token)
+                try:
-                if match:
+                    idx = int(token[9:-2])  # 提取索引
-                    field, operator, value = match.groups()
+                    original_filter = filters_found[idx]
-                    groups.append(FilterGroup(
+                    match = cls.FILTER_PATTERN.match(original_filter)
-                        filter=ParsedFilter(
+                    if match:
-                            field=field.lower(),
+                        field, operator, value = match.groups()
-                            operator=operator,
+                        groups.append(FilterGroup(
-                            value=value
+                            filter=ParsedFilter(
-                        ),
+                                field=field.lower(),
-                        logical_op=pending_op if groups else LogicalOp.AND  # 第一个条件默认 AND
+                                operator=operator,
-                    ))
+                                value=value
-                    pending_op = LogicalOp.AND  # 重置为默认 AND
+                            ),
+                            logical_op=pending_op if groups else LogicalOp.AND
+                        ))
+                        pending_op = LogicalOp.AND  # 重置为默认 AND
+                except (ValueError, IndexError):
+                    pass
+            # 其他 token 忽略（无效输入）
         
         return groups
 
@@ -151,6 +177,21 @@ class QueryBuilder:
         
         json_array_fields = json_array_fields or []
         
+        # 收集需要 annotate 的数组模糊搜索字段
+        array_fuzzy_fields = set()
+        
+        # 第一遍：检查是否有数组模糊匹配
+        for group in filter_groups:
+            f = group.filter
+            db_field = field_mapping.get(f.field)
+            if db_field and db_field in json_array_fields and f.operator == '=':
+                array_fuzzy_fields.add(db_field)
+        
+        # 对数组模糊搜索字段做 annotate
+        for field in array_fuzzy_fields:
+            annotate_name = f'{field}_text'
+            queryset = queryset.annotate(**{annotate_name: ArrayToString(F(field))})
+        
         # 构建 Q 对象
         combined_q = None
         
@@ -187,8 +228,17 @@ class QueryBuilder:
     def _build_single_q(cls, field: str, operator: str, value: str, is_json_array: bool = False) -> Optional[Q]:
         """构建单个条件的 Q 对象"""
         if is_json_array:
-            # JSON 数组字段使用 __contains 查询
+            if operator == '==':
-            return Q(**{f'{field}__contains': [value]})
+                # 精确匹配：数组中包含完全等于 value 的元素
+                return Q(**{f'{field}__contains': [value]})
+            elif operator == '!=':
+                # 不包含：数组中不包含完全等于 value 的元素
+                return ~Q(**{f'{field}__contains': [value]})
+            else:  # '=' 模糊匹配
+                # 使用 annotate 后的字段进行模糊搜索
+                # 字段已在 build_query 中通过 ArrayToString 转换为文本
+                annotate_name = f'{field}_text'
+                return Q(**{f'{annotate_name}__icontains': value})
         
         if operator == '!=':
             return cls._build_not_equal_q(field, value)

backend/apps/common/utils/git_proxy.py

@@ -1,39 +0,0 @@
-"""Git proxy utilities for URL acceleration."""
-
-import os
-from urllib.parse import urlparse
-
-
-def get_git_proxy_url(original_url: str) -> str:
-    """
-    Convert Git repository URL to proxy format for acceleration.
-    
-    Supports multiple mirror services (standard format):
-    - gh-proxy.org: https://gh-proxy.org/https://github.com/user/repo.git
-    - ghproxy.com: https://ghproxy.com/https://github.com/user/repo.git
-    - mirror.ghproxy.com: https://mirror.ghproxy.com/https://github.com/user/repo.git
-    - ghps.cc: https://ghps.cc/https://github.com/user/repo.git
-    
-    Args:
-        original_url: Original repository URL, e.g., https://github.com/user/repo.git
-        
-    Returns:
-        Converted URL based on GIT_MIRROR setting.
-        If GIT_MIRROR is not set, returns the original URL unchanged.
-    """
-    git_mirror = os.getenv("GIT_MIRROR", "").strip()
-    if not git_mirror:
-        return original_url
-    
-    # Remove trailing slash from mirror URL if present
-    git_mirror = git_mirror.rstrip("/")
-    
-    parsed = urlparse(original_url)
-    host = parsed.netloc.lower()
-    
-    # Only support GitHub for now
-    if "github.com" not in host:
-        return original_url
-    
-    # Standard format: https://mirror.example.com/https://github.com/user/repo.git
-    return f"{git_mirror}/{original_url}"

backend/apps/common/views/__init__.py

@@ -2,11 +2,23 @@
 通用模块视图导出
 
 包含：
+- 健康检查视图：Docker 健康检查
 - 认证相关视图：登录、登出、用户信息、修改密码
 - 系统日志视图：实时日志查看
+- 黑名单视图：全局黑名单规则管理
+- 版本视图：系统版本和更新检查
 """
 
+from .health_views import HealthCheckView
 from .auth_views import LoginView, LogoutView, MeView, ChangePasswordView
-from .system_log_views import SystemLogsView
+from .system_log_views import SystemLogsView, SystemLogFilesView
+from .blacklist_views import GlobalBlacklistView
+from .version_views import VersionView, CheckUpdateView
 
-__all__ = ['LoginView', 'LogoutView', 'MeView', 'ChangePasswordView', 'SystemLogsView']
+__all__ = [
+    'HealthCheckView',
+    'LoginView', 'LogoutView', 'MeView', 'ChangePasswordView',
+    'SystemLogsView', 'SystemLogFilesView',
+    'GlobalBlacklistView',
+    'VersionView', 'CheckUpdateView',
+]

backend/apps/common/views/auth_views.py

@@ -9,7 +9,10 @@ from django.utils.decorators import method_decorator
 from rest_framework import status
 from rest_framework.views import APIView
 from rest_framework.response import Response
-from rest_framework.permissions import AllowAny, IsAuthenticated
+from rest_framework.permissions import AllowAny
+
+from apps.common.response_helpers import success_response, error_response
+from apps.common.error_codes import ErrorCodes
 
 logger = logging.getLogger(__name__)
 
@@ -28,9 +31,10 @@ class LoginView(APIView):
         password = request.data.get('password')
         
         if not username or not password:
-            return Response(
+            return error_response(
-                {'error': '请提供用户名和密码'},
+                code=ErrorCodes.VALIDATION_ERROR,
-                status=status.HTTP_400_BAD_REQUEST
+                message='Username and password are required',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         user = authenticate(request, username=username, password=password)
@@ -38,20 +42,22 @@ class LoginView(APIView):
         if user is not None:
             login(request, user)
             logger.info(f"用户 {username} 登录成功")
-            return Response({
+            return success_response(
-                'message': '登录成功',
+                data={
-                'user': {
+                    'user': {
-                    'id': user.id,
+                        'id': user.id,
-                    'username': user.username,
+                        'username': user.username,
-                    'isStaff': user.is_staff,
+                        'isStaff': user.is_staff,
-                    'isSuperuser': user.is_superuser,
+                        'isSuperuser': user.is_superuser,
+                    }
                 }
-            })
+            )
         else:
             logger.warning(f"用户 {username} 登录失败：用户名或密码错误")
-            return Response(
+            return error_response(
-                {'error': '用户名或密码错误'},
+                code=ErrorCodes.UNAUTHORIZED,
-                status=status.HTTP_401_UNAUTHORIZED
+                message='Invalid username or password',
+                status_code=status.HTTP_401_UNAUTHORIZED
             )
 
 
@@ -79,7 +85,7 @@ class LogoutView(APIView):
                 logout(request)
         else:
             logout(request)
-        return Response({'message': '已登出'})
+        return success_response()
 
 
 @method_decorator(csrf_exempt, name='dispatch')
@@ -100,22 +106,26 @@ class MeView(APIView):
         if user_id:
             try:
                 user = User.objects.get(pk=user_id)
-                return Response({
+                return success_response(
-                    'authenticated': True,
+                    data={
-                    'user': {
+                        'authenticated': True,
-                        'id': user.id,
+                        'user': {
-                        'username': user.username,
+                            'id': user.id,
-                        'isStaff': user.is_staff,
+                            'username': user.username,
-                        'isSuperuser': user.is_superuser,
+                            'isStaff': user.is_staff,
+                            'isSuperuser': user.is_superuser,
+                        }
                     }
-                })
+                )
             except User.DoesNotExist:
                 pass
         
-        return Response({
+        return success_response(
-            'authenticated': False,
+            data={
-            'user': None
+                'authenticated': False,
-        })
+                'user': None
+            }
+        )
 
 
 @method_decorator(csrf_exempt, name='dispatch')
@@ -124,43 +134,27 @@ class ChangePasswordView(APIView):
     修改密码
     POST /api/auth/change-password/
     """
-    authentication_classes = []  # 禁用认证（绕过 CSRF）
-    permission_classes = [AllowAny]  # 手动检查登录状态
     
     def post(self, request):
-        # 手动检查登录状态（从 session 获取用户）
+        # 使用全局权限类验证，request.user 已经是认证用户
-        from django.contrib.auth import get_user_model
+        user = request.user
-        User = get_user_model()
-        
-        user_id = request.session.get('_auth_user_id')
-        if not user_id:
-            return Response(
-                {'error': '请先登录'},
-                status=status.HTTP_401_UNAUTHORIZED
-            )
-        
-        try:
-            user = User.objects.get(pk=user_id)
-        except User.DoesNotExist:
-            return Response(
-                {'error': '用户不存在'},
-                status=status.HTTP_401_UNAUTHORIZED
-            )
         
         # CamelCaseParser 将 oldPassword -> old_password
         old_password = request.data.get('old_password')
         new_password = request.data.get('new_password')
         
         if not old_password or not new_password:
-            return Response(
+            return error_response(
-                {'error': '请提供旧密码和新密码'},
+                code=ErrorCodes.VALIDATION_ERROR,
-                status=status.HTTP_400_BAD_REQUEST
+                message='Old password and new password are required',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         if not user.check_password(old_password):
-            return Response(
+            return error_response(
-                {'error': '旧密码错误'},
+                code=ErrorCodes.VALIDATION_ERROR,
-                status=status.HTTP_400_BAD_REQUEST
+                message='Old password is incorrect',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         user.set_password(new_password)
@@ -170,4 +164,4 @@ class ChangePasswordView(APIView):
         update_session_auth_hash(request, user)
         
         logger.info(f"用户 {user.username} 已修改密码")
-        return Response({'message': '密码修改成功'})
+        return success_response()

backend/apps/common/views/blacklist_views.py

@@ -0,0 +1,80 @@
+"""全局黑名单 API 视图"""
+import logging
+
+from rest_framework import status
+from rest_framework.views import APIView
+from rest_framework.permissions import IsAuthenticated
+
+from apps.common.response_helpers import success_response, error_response
+from apps.common.services import BlacklistService
+
+logger = logging.getLogger(__name__)
+
+
+class GlobalBlacklistView(APIView):
+    """
+    全局黑名单规则 API
+    
+    Endpoints:
+    - GET /api/blacklist/rules/ - 获取全局黑名单列表
+    - PUT /api/blacklist/rules/ - 全量替换规则（文本框保存场景）
+    
+    设计说明：
+    - 使用 PUT 全量替换模式，适合"文本框每行一个规则"的前端场景
+    - 用户编辑文本框 -> 点击保存 -> 后端全量替换
+    
+    架构：MVS 模式
+    - View: 参数验证、响应格式化
+    - Service: 业务逻辑（BlacklistService）
+    - Model: 数据持久化（BlacklistRule）
+    """
+    
+    permission_classes = [IsAuthenticated]
+    
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        self.blacklist_service = BlacklistService()
+    
+    def get(self, request):
+        """
+        获取全局黑名单规则列表
+        
+        返回格式：
+        {
+            "patterns": ["*.gov", "*.edu", "10.0.0.0/8"]
+        }
+        """
+        rules = self.blacklist_service.get_global_rules()
+        patterns = list(rules.values_list('pattern', flat=True))
+        return success_response(data={'patterns': patterns})
+    
+    def put(self, request):
+        """
+        全量替换全局黑名单规则
+        
+        请求格式：
+        {
+            "patterns": ["*.gov", "*.edu", "10.0.0.0/8"]
+        }
+        
+        或者空数组清空所有规则：
+        {
+            "patterns": []
+        }
+        """
+        patterns = request.data.get('patterns', [])
+        
+        # 兼容字符串输入（换行分隔）
+        if isinstance(patterns, str):
+            patterns = [p for p in patterns.split('\n') if p.strip()]
+        
+        if not isinstance(patterns, list):
+            return error_response(
+                code='VALIDATION_ERROR',
+                message='patterns 必须是数组'
+            )
+        
+        # 调用 Service 层全量替换
+        result = self.blacklist_service.replace_global_rules(patterns)
+        
+        return success_response(data=result)

backend/apps/common/views/health_views.py

@@ -0,0 +1,24 @@
+"""
+健康检查视图
+
+提供 Docker 健康检查端点，无需认证。
+"""
+
+from rest_framework.views import APIView
+from rest_framework.response import Response
+from rest_framework.permissions import AllowAny
+
+
+class HealthCheckView(APIView):
+    """
+    健康检查端点
+    
+    GET /api/health/
+    
+    返回服务状态，用于 Docker 健康检查。
+    此端点无需认证。
+    """
+    permission_classes = [AllowAny]
+    
+    def get(self, request):
+        return Response({'status': 'ok'})

backend/apps/common/views/system_log_views.py

@@ -9,16 +9,57 @@ import logging
 from django.utils.decorators import method_decorator
 from django.views.decorators.csrf import csrf_exempt
 from rest_framework import status
-from rest_framework.permissions import AllowAny
 from rest_framework.response import Response
 from rest_framework.views import APIView
 
+from apps.common.response_helpers import success_response, error_response
+from apps.common.error_codes import ErrorCodes
 from apps.common.services.system_log_service import SystemLogService
 
 
 logger = logging.getLogger(__name__)
 
 
+@method_decorator(csrf_exempt, name="dispatch")
+class SystemLogFilesView(APIView):
+    """
+    日志文件列表 API 视图
+    
+    GET /api/system/logs/files/
+        获取所有可用的日志文件列表
+        
+    Response:
+        {
+            "files": [
+                {
+                    "filename": "xingrin.log",
+                    "category": "system",
+                    "size": 1048576,
+                    "modifiedAt": "2025-01-15T10:30:00+00:00"
+                },
+                ...
+            ]
+        }
+    """
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        self.service = SystemLogService()
+
+    def get(self, request):
+        """获取日志文件列表"""
+        try:
+            files = self.service.get_log_files()
+            return success_response(data={"files": files})
+        except Exception:
+            logger.exception("获取日志文件列表失败")
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Failed to get log files',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )
+
+
 @method_decorator(csrf_exempt, name="dispatch")
 class SystemLogsView(APIView):
     """
@@ -28,22 +69,15 @@ class SystemLogsView(APIView):
         获取系统日志内容
         
     Query Parameters:
+        file (str, optional): 日志文件名，默认 xingrin.log
         lines (int, optional): 返回的日志行数，默认 200，最大 10000
         
     Response:
         {
             "content": "日志内容字符串..."
         }
-        
-    Note:
-        - 当前为开发阶段，暂时允许匿名访问
-        - 生产环境应添加管理员权限验证
     """
 
-    # TODO: 生产环境应改为 IsAdminUser 权限
-    authentication_classes = []
-    permission_classes = [AllowAny]
-
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
         self.service = SystemLogService()
@@ -52,18 +86,33 @@ class SystemLogsView(APIView):
         """
         获取系统日志
         
-        支持通过 lines 参数控制返回行数，用于前端分页或实时刷新场景。
+        支持通过 file 和 lines 参数控制返回内容。
         """
         try:
-            # 解析 lines 参数
+            # 解析参数
+            filename = request.query_params.get("file")
             lines_raw = request.query_params.get("lines")
             lines = int(lines_raw) if lines_raw is not None else None
 
             # 调用服务获取日志内容
-            content = self.service.get_logs_content(lines=lines)
+            content = self.service.get_logs_content(filename=filename, lines=lines)
-            return Response({"content": content})
+            return success_response(data={"content": content})
-        except ValueError:
+        except ValueError as e:
-            return Response({"error": "lines 参数必须是整数"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message=str(e) if 'file' in str(e).lower() else 'lines must be an integer',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
+        except FileNotFoundError as e:
+            return error_response(
+                code=ErrorCodes.NOT_FOUND,
+                message=str(e),
+                status_code=status.HTTP_404_NOT_FOUND
+            )
         except Exception:
             logger.exception("获取系统日志失败")
-            return Response({"error": "获取系统日志失败"}, status=status.HTTP_500_INTERNAL_SERVER_ERROR)
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Failed to get system logs',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )

backend/apps/common/views/version_views.py

@@ -0,0 +1,136 @@
+"""
+系统版本相关视图
+"""
+
+import logging
+from pathlib import Path
+
+import requests
+from rest_framework.request import Request
+from rest_framework.response import Response
+from rest_framework.views import APIView
+
+from apps.common.error_codes import ErrorCodes
+from apps.common.response_helpers import error_response, success_response
+
+logger = logging.getLogger(__name__)
+
+# GitHub 仓库信息
+GITHUB_REPO = "yyhuni/xingrin"
+GITHUB_API_URL = f"https://api.github.com/repos/{GITHUB_REPO}/releases/latest"
+GITHUB_RELEASES_URL = f"https://github.com/{GITHUB_REPO}/releases"
+
+
+def get_current_version() -> str:
+    """读取当前版本号"""
+    import os
+
+    # 方式1：从环境变量读取（Docker 容器中推荐）
+    version = os.environ.get('IMAGE_TAG', '')
+    if version:
+        return version
+
+    # 方式2：从文件读取（开发环境）
+    possible_paths = [
+        Path('/app/VERSION'),
+        Path(__file__).parent.parent.parent.parent.parent / 'VERSION',
+    ]
+
+    for path in possible_paths:
+        try:
+            return path.read_text(encoding='utf-8').strip()
+        except (FileNotFoundError, OSError):
+            continue
+
+    return "unknown"
+
+
+def compare_versions(current: str, latest: str) -> bool:
+    """
+    比较版本号，判断是否有更新
+
+    Returns:
+        True 表示有更新可用
+    """
+    def parse_version(v: str) -> tuple:
+        v = v.lstrip('v')
+        parts = v.split('.')
+        result = []
+        for part in parts:
+            if '-' in part:
+                num, _ = part.split('-', 1)
+                result.append(int(num))
+            else:
+                result.append(int(part))
+        return tuple(result)
+
+    try:
+        return parse_version(latest) > parse_version(current)
+    except (ValueError, AttributeError):
+        return False
+
+
+class VersionView(APIView):
+    """获取当前系统版本"""
+
+    def get(self, _request: Request) -> Response:
+        """获取当前版本信息"""
+        return success_response(data={
+            'version': get_current_version(),
+            'github_repo': GITHUB_REPO,
+        })
+
+
+class CheckUpdateView(APIView):
+    """检查系统更新"""
+
+    def get(self, _request: Request) -> Response:
+        """
+        检查是否有新版本
+
+        Returns:
+            - current_version: 当前版本
+            - latest_version: 最新版本
+            - has_update: 是否有更新
+            - release_url: 发布页面 URL
+            - release_notes: 更新说明（如果有）
+        """
+        current_version = get_current_version()
+
+        try:
+            response = requests.get(
+                GITHUB_API_URL,
+                headers={'Accept': 'application/vnd.github.v3+json'},
+                timeout=10
+            )
+
+            if response.status_code == 404:
+                return success_response(data={
+                    'current_version': current_version,
+                    'latest_version': current_version,
+                    'has_update': False,
+                    'release_url': GITHUB_RELEASES_URL,
+                    'release_notes': None,
+                })
+
+            response.raise_for_status()
+            release_data = response.json()
+
+            latest_version = release_data.get('tag_name', current_version)
+            has_update = compare_versions(current_version, latest_version)
+
+            return success_response(data={
+                'current_version': current_version,
+                'latest_version': latest_version,
+                'has_update': has_update,
+                'release_url': release_data.get('html_url', GITHUB_RELEASES_URL),
+                'release_notes': release_data.get('body'),
+                'published_at': release_data.get('published_at'),
+            })
+
+        except requests.RequestException as e:
+            logger.warning("检查更新失败: %s", e)
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message="无法连接到 GitHub，请稍后重试",
+            )

backend/apps/common/websocket_auth.py

@@ -0,0 +1,44 @@
+"""
+WebSocket 认证基类
+
+提供需要认证的 WebSocket Consumer 基类
+"""
+
+import logging
+from channels.generic.websocket import AsyncWebsocketConsumer
+
+logger = logging.getLogger(__name__)
+
+
+class AuthenticatedWebsocketConsumer(AsyncWebsocketConsumer):
+    """
+    需要认证的 WebSocket Consumer 基类
+    
+    子类应该重写 on_connect() 方法实现具体的连接逻辑
+    """
+    
+    async def connect(self):
+        """
+        连接时验证用户认证状态
+        
+        未认证时使用 close(code=4001) 拒绝连接
+        """
+        user = self.scope.get('user')
+        
+        if not user or not user.is_authenticated:
+            logger.warning(
+                f"WebSocket 连接被拒绝：用户未认证 - Path: {self.scope.get('path')}"
+            )
+            await self.close(code=4001)
+            return
+        
+        # 调用子类的连接逻辑
+        await self.on_connect()
+    
+    async def on_connect(self):
+        """
+        子类实现具体的连接逻辑
+        
+        默认实现：接受连接
+        """
+        await self.accept()

backend/apps/engine/consumers/worker_deploy_consumer.py

@@ -6,17 +6,17 @@ import json
 import logging
 import asyncio
 import os
-from channels.generic.websocket import AsyncWebsocketConsumer
 from asgiref.sync import sync_to_async
 
 from django.conf import settings
 
+from apps.common.websocket_auth import AuthenticatedWebsocketConsumer
 from apps.engine.services import WorkerService
 
 logger = logging.getLogger(__name__)
 
 
-class WorkerDeployConsumer(AsyncWebsocketConsumer):
+class WorkerDeployConsumer(AuthenticatedWebsocketConsumer):
     """
     Worker 交互式终端 WebSocket Consumer
     
@@ -31,8 +31,8 @@ class WorkerDeployConsumer(AsyncWebsocketConsumer):
         self.read_task = None
         self.worker_service = WorkerService()
     
-    async def connect(self):
+    async def on_connect(self):
-        """连接时加入对应 Worker 的组并自动建立 SSH 连接"""
+        """连接时加入对应 Worker 的组并自动建立 SSH 连接（已通过认证）"""
         self.worker_id = self.scope['url_route']['kwargs']['worker_id']
         self.group_name = f'worker_deploy_{self.worker_id}'
         

backend/apps/engine/management/commands/init_default_engine.py

@@ -2,8 +2,9 @@
 初始化默认扫描引擎
 
 用法：
-  python manage.py init_default_engine          # 只创建不存在的引擎（不覆盖已有）
+  python manage.py init_default_engine              # 只创建不存在的引擎（不覆盖已有）
-  python manage.py init_default_engine --force  # 强制覆盖所有引擎配置
+  python manage.py init_default_engine --force      # 强制覆盖所有引擎配置
+  python manage.py init_default_engine --force-sub  # 只覆盖子引擎，保留 full scan
   
   cd /root/my-vulun-scan/docker
   docker compose exec server python backend/manage.py init_default_engine --force
@@ -12,12 +13,14 @@
 - 读取 engine_config_example.yaml 作为默认配置
 - 创建 full scan（默认引擎）+ 各扫描类型的子引擎
 - 默认不覆盖已有配置，加 --force 才会覆盖
+- 加 --force-sub 只覆盖子引擎配置，保留用户自定义的 full scan
 """
 
 from django.core.management.base import BaseCommand
+from io import StringIO
 from pathlib import Path
 
-import yaml
+from ruamel.yaml import YAML
 
 from apps.engine.models import ScanEngine
 
@@ -29,11 +32,18 @@ class Command(BaseCommand):
         parser.add_argument(
             '--force',
             action='store_true',
-            help='强制覆盖已有的引擎配置',
+            help='强制覆盖已有的引擎配置（包括 full scan 和子引擎）',
+        )
+        parser.add_argument(
+            '--force-sub',
+            action='store_true',
+            help='只覆盖子引擎配置，保留 full scan（升级时使用）',
         )
 
     def handle(self, *args, **options):
         force = options.get('force', False)
+        force_sub = options.get('force_sub', False)
+        
         # 读取默认配置文件
         config_path = Path(__file__).resolve().parent.parent.parent.parent / 'scan' / 'configs' / 'engine_config_example.yaml'
         
@@ -44,10 +54,12 @@ class Command(BaseCommand):
         with open(config_path, 'r', encoding='utf-8') as f:
             default_config = f.read()
 
-        # 解析 YAML 为字典，后续用于生成子引擎配置
+        # 使用 ruamel.yaml 解析，保留注释
+        yaml_parser = YAML()
+        yaml_parser.preserve_quotes = True
         try:
-            config_dict = yaml.safe_load(default_config) or {}
+            config_dict = yaml_parser.load(default_config) or {}
-        except yaml.YAMLError as e:
+        except Exception as e:
             self.stdout.write(self.style.ERROR(f'引擎配置 YAML 解析失败: {e}'))
             return
 
@@ -83,30 +95,35 @@ class Command(BaseCommand):
             if scan_type != 'subdomain_discovery' and 'tools' not in scan_cfg:
                 continue
 
-            # 构造只包含当前扫描类型配置的 YAML
+            # 构造只包含当前扫描类型配置的 YAML（保留注释）
             single_config = {scan_type: scan_cfg}
             try:
-                single_yaml = yaml.safe_dump(
+                stream = StringIO()
-                    single_config,
+                yaml_parser.dump(single_config, stream)
-                    sort_keys=False,
+                single_yaml = stream.getvalue()
-                    allow_unicode=True,
+            except Exception as e:
-                )
-            except yaml.YAMLError as e:
                 self.stdout.write(self.style.ERROR(f'生成子引擎 {scan_type} 配置失败: {e}'))
                 continue
 
             engine_name = f"{scan_type}"
             sub_engine = ScanEngine.objects.filter(name=engine_name).first()
             if sub_engine:
-                if force:
+                # force 或 force_sub 都会覆盖子引擎
+                if force or force_sub:
                     sub_engine.configuration = single_yaml
                     sub_engine.save()
-                    self.stdout.write(self.style.SUCCESS(f'  ✓ 子引擎 {engine_name} 配置已更新 (ID: {sub_engine.id})'))
+                    self.stdout.write(self.style.SUCCESS(
+                        f'  ✓ 子引擎 {engine_name} 配置已更新 (ID: {sub_engine.id})'
+                    ))
                 else:
-                    self.stdout.write(self.style.WARNING(f'  ⊘ {engine_name} 已存在，跳过（使用 --force 覆盖）'))
+                    self.stdout.write(self.style.WARNING(
+                        f'  ⊘ {engine_name} 已存在，跳过（使用 --force 覆盖）'
+                    ))
             else:
                 sub_engine = ScanEngine.objects.create(
                     name=engine_name,
                     configuration=single_yaml,
                 )
-                self.stdout.write(self.style.SUCCESS(f'  ✓ 子引擎 {engine_name} 已创建 (ID: {sub_engine.id})'))
+                self.stdout.write(self.style.SUCCESS(
+                    f'  ✓ 子引擎 {engine_name} 已创建 (ID: {sub_engine.id})'
+                ))

backend/apps/engine/management/commands/init_fingerprints.py

@@ -3,6 +3,9 @@
 - EHole 指纹: ehole.json -> 导入到数据库
 - Goby 指纹: goby.json -> 导入到数据库
 - Wappalyzer 指纹: wappalyzer.json -> 导入到数据库
+- Fingers 指纹: fingers_http.json -> 导入到数据库
+- FingerPrintHub 指纹: fingerprinthub_web.json -> 导入到数据库
+- ARL 指纹: ARL.yaml -> 导入到数据库
 
 可重复执行：如果数据库已有数据则跳过，只在空库时导入。
 """
@@ -11,14 +14,25 @@ import json
 import logging
 from pathlib import Path
 
+import yaml
 from django.conf import settings
 from django.core.management.base import BaseCommand
 
-from apps.engine.models import EholeFingerprint, GobyFingerprint, WappalyzerFingerprint
+from apps.engine.models import (
+    EholeFingerprint,
+    GobyFingerprint,
+    WappalyzerFingerprint,
+    FingersFingerprint,
+    FingerPrintHubFingerprint,
+    ARLFingerprint,
+)
 from apps.engine.services.fingerprints import (
     EholeFingerprintService,
     GobyFingerprintService,
     WappalyzerFingerprintService,
+    FingersFingerprintService,
+    FingerPrintHubFingerprintService,
+    ARLFingerprintService,
 )
 
 
@@ -33,6 +47,7 @@ DEFAULT_FINGERPRINTS = [
         "model": EholeFingerprint,
         "service": EholeFingerprintService,
         "data_key": "fingerprint",  # JSON 中指纹数组的 key
+        "file_format": "json",
     },
     {
         "type": "goby",
@@ -40,6 +55,7 @@ DEFAULT_FINGERPRINTS = [
         "model": GobyFingerprint,
         "service": GobyFingerprintService,
         "data_key": None,  # Goby 是数组格式，直接使用整个 JSON
+        "file_format": "json",
     },
     {
         "type": "wappalyzer",
@@ -47,6 +63,31 @@ DEFAULT_FINGERPRINTS = [
         "model": WappalyzerFingerprint,
         "service": WappalyzerFingerprintService,
         "data_key": "apps",  # Wappalyzer 使用 apps 对象
+        "file_format": "json",
+    },
+    {
+        "type": "fingers",
+        "filename": "fingers_http.json",
+        "model": FingersFingerprint,
+        "service": FingersFingerprintService,
+        "data_key": None,  # Fingers 是数组格式
+        "file_format": "json",
+    },
+    {
+        "type": "fingerprinthub",
+        "filename": "fingerprinthub_web.json",
+        "model": FingerPrintHubFingerprint,
+        "service": FingerPrintHubFingerprintService,
+        "data_key": None,  # FingerPrintHub 是数组格式
+        "file_format": "json",
+    },
+    {
+        "type": "arl",
+        "filename": "ARL.yaml",
+        "model": ARLFingerprint,
+        "service": ARLFingerprintService,
+        "data_key": None,  # ARL 是 YAML 数组格式
+        "file_format": "yaml",
     },
 ]
 
@@ -68,6 +109,7 @@ class Command(BaseCommand):
             model = item["model"]
             service_class = item["service"]
             data_key = item["data_key"]
+            file_format = item.get("file_format", "json")
 
             # 检查数据库是否已有数据
             existing_count = model.objects.count()
@@ -87,11 +129,14 @@ class Command(BaseCommand):
                 failed += 1
                 continue
 
-            # 读取并解析 JSON
+            # 读取并解析文件（支持 JSON 和 YAML）
             try:
                 with open(src_path, "r", encoding="utf-8") as f:
-                    json_data = json.load(f)
+                    if file_format == "yaml":
-            except (json.JSONDecodeError, OSError) as exc:
+                        file_data = yaml.safe_load(f)
+                    else:
+                        file_data = json.load(f)
+            except (json.JSONDecodeError, yaml.YAMLError, OSError) as exc:
                 self.stdout.write(self.style.ERROR(
                     f"[{fp_type}] 读取指纹文件失败: {exc}"
                 ))
@@ -99,7 +144,7 @@ class Command(BaseCommand):
                 continue
 
             # 提取指纹数据（根据不同格式处理）
-            fingerprints = self._extract_fingerprints(json_data, data_key, fp_type)
+            fingerprints = self._extract_fingerprints(file_data, data_key, fp_type)
             if not fingerprints:
                 self.stdout.write(self.style.WARNING(
                     f"[{fp_type}] 指纹文件中没有有效数据，跳过"

backend/apps/engine/management/commands/init_nuclei_templates.py

@@ -21,11 +21,11 @@ from apps.engine.services import NucleiTemplateRepoService
 logger = logging.getLogger(__name__)
 
 
-# 默认仓库配置
+# 默认仓库配置（从 settings 读取，支持 Gitee 镜像）
 DEFAULT_REPOS = [
     {
         "name": "nuclei-templates",
-        "repo_url": "https://github.com/projectdiscovery/nuclei-templates.git",
+        "repo_url": getattr(settings, 'NUCLEI_TEMPLATES_REPO_URL', 'https://github.com/projectdiscovery/nuclei-templates.git'),
         "description": "Nuclei 官方模板仓库，包含数千个漏洞检测模板",
     },
 ]

backend/apps/engine/migrations/0001_initial.py

@@ -0,0 +1,213 @@
+# Generated by Django 5.2.7 on 2026-01-06 00:55
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = [
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='NucleiTemplateRepo',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('name', models.CharField(help_text='仓库名称，用于前端展示和配置引用', max_length=200, unique=True)),
+                ('repo_url', models.CharField(help_text='Git 仓库地址', max_length=500)),
+                ('local_path', models.CharField(blank=True, default='', help_text='本地工作目录绝对路径', max_length=500)),
+                ('commit_hash', models.CharField(blank=True, default='', help_text='最后同步的 Git commit hash，用于 Worker 版本校验', max_length=40)),
+                ('last_synced_at', models.DateTimeField(blank=True, help_text='最后一次成功同步时间', null=True)),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('updated_at', models.DateTimeField(auto_now=True, help_text='更新时间')),
+            ],
+            options={
+                'verbose_name': 'Nuclei 模板仓库',
+                'verbose_name_plural': 'Nuclei 模板仓库',
+                'db_table': 'nuclei_template_repo',
+            },
+        ),
+        migrations.CreateModel(
+            name='ARLFingerprint',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('name', models.CharField(help_text='指纹名称', max_length=300, unique=True)),
+                ('rule', models.TextField(help_text='匹配规则表达式')),
+                ('created_at', models.DateTimeField(auto_now_add=True)),
+            ],
+            options={
+                'verbose_name': 'ARL 指纹',
+                'verbose_name_plural': 'ARL 指纹',
+                'db_table': 'arl_fingerprint',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['name'], name='arl_fingerp_name_c3a305_idx'), models.Index(fields=['-created_at'], name='arl_fingerp_created_ed1060_idx')],
+            },
+        ),
+        migrations.CreateModel(
+            name='EholeFingerprint',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('cms', models.CharField(help_text='产品/CMS名称', max_length=200)),
+                ('method', models.CharField(default='keyword', help_text='匹配方式', max_length=200)),
+                ('location', models.CharField(default='body', help_text='匹配位置', max_length=200)),
+                ('keyword', models.JSONField(default=list, help_text='关键词列表')),
+                ('is_important', models.BooleanField(default=False, help_text='是否重点资产')),
+                ('type', models.CharField(blank=True, default='-', help_text='分类', max_length=100)),
+                ('created_at', models.DateTimeField(auto_now_add=True)),
+            ],
+            options={
+                'verbose_name': 'EHole 指纹',
+                'verbose_name_plural': 'EHole 指纹',
+                'db_table': 'ehole_fingerprint',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['cms'], name='ehole_finge_cms_72ca2c_idx'), models.Index(fields=['method'], name='ehole_finge_method_17f0db_idx'), models.Index(fields=['location'], name='ehole_finge_locatio_7bb82b_idx'), models.Index(fields=['type'], name='ehole_finge_type_ca2bce_idx'), models.Index(fields=['is_important'], name='ehole_finge_is_impo_d56e64_idx'), models.Index(fields=['-created_at'], name='ehole_finge_created_d862b0_idx')],
+                'constraints': [models.UniqueConstraint(fields=('cms', 'method', 'location'), name='unique_ehole_fingerprint')],
+            },
+        ),
+        migrations.CreateModel(
+            name='FingerPrintHubFingerprint',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('fp_id', models.CharField(help_text='指纹ID', max_length=200, unique=True)),
+                ('name', models.CharField(help_text='指纹名称', max_length=300)),
+                ('author', models.CharField(blank=True, default='', help_text='作者', max_length=200)),
+                ('tags', models.CharField(blank=True, default='', help_text='标签', max_length=500)),
+                ('severity', models.CharField(blank=True, default='info', help_text='严重程度', max_length=50)),
+                ('metadata', models.JSONField(blank=True, default=dict, help_text='元数据')),
+                ('http', models.JSONField(default=list, help_text='HTTP 匹配规则')),
+                ('source_file', models.CharField(blank=True, default='', help_text='来源文件', max_length=500)),
+                ('created_at', models.DateTimeField(auto_now_add=True)),
+            ],
+            options={
+                'verbose_name': 'FingerPrintHub 指纹',
+                'verbose_name_plural': 'FingerPrintHub 指纹',
+                'db_table': 'fingerprinthub_fingerprint',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['fp_id'], name='fingerprint_fp_id_df467f_idx'), models.Index(fields=['name'], name='fingerprint_name_95b6fb_idx'), models.Index(fields=['author'], name='fingerprint_author_80f54b_idx'), models.Index(fields=['severity'], name='fingerprint_severit_f70422_idx'), models.Index(fields=['-created_at'], name='fingerprint_created_bec16c_idx')],
+            },
+        ),
+        migrations.CreateModel(
+            name='FingersFingerprint',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('name', models.CharField(help_text='指纹名称', max_length=300, unique=True)),
+                ('link', models.URLField(blank=True, default='', help_text='相关链接', max_length=500)),
+                ('rule', models.JSONField(default=list, help_text='匹配规则数组')),
+                ('tag', models.JSONField(default=list, help_text='标签数组')),
+                ('focus', models.BooleanField(default=False, help_text='是否重点关注')),
+                ('default_port', models.JSONField(blank=True, default=list, help_text='默认端口数组')),
+                ('created_at', models.DateTimeField(auto_now_add=True)),
+            ],
+            options={
+                'verbose_name': 'Fingers 指纹',
+                'verbose_name_plural': 'Fingers 指纹',
+                'db_table': 'fingers_fingerprint',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['name'], name='fingers_fin_name_952de0_idx'), models.Index(fields=['link'], name='fingers_fin_link_4c6b7f_idx'), models.Index(fields=['focus'], name='fingers_fin_focus_568c7f_idx'), models.Index(fields=['-created_at'], name='fingers_fin_created_46fc91_idx')],
+            },
+        ),
+        migrations.CreateModel(
+            name='GobyFingerprint',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('name', models.CharField(help_text='产品名称', max_length=300, unique=True)),
+                ('logic', models.CharField(help_text='逻辑表达式', max_length=500)),
+                ('rule', models.JSONField(default=list, help_text='规则数组')),
+                ('created_at', models.DateTimeField(auto_now_add=True)),
+            ],
+            options={
+                'verbose_name': 'Goby 指纹',
+                'verbose_name_plural': 'Goby 指纹',
+                'db_table': 'goby_fingerprint',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['name'], name='goby_finger_name_82084c_idx'), models.Index(fields=['logic'], name='goby_finger_logic_a63226_idx'), models.Index(fields=['-created_at'], name='goby_finger_created_50e000_idx')],
+            },
+        ),
+        migrations.CreateModel(
+            name='ScanEngine',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('name', models.CharField(help_text='引擎名称', max_length=200, unique=True)),
+                ('configuration', models.CharField(blank=True, default='', help_text='引擎配置，yaml 格式', max_length=10000)),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('updated_at', models.DateTimeField(auto_now=True, help_text='更新时间')),
+            ],
+            options={
+                'verbose_name': '扫描引擎',
+                'verbose_name_plural': '扫描引擎',
+                'db_table': 'scan_engine',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['-created_at'], name='scan_engine_created_da4870_idx')],
+            },
+        ),
+        migrations.CreateModel(
+            name='WappalyzerFingerprint',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('name', models.CharField(help_text='应用名称', max_length=300, unique=True)),
+                ('cats', models.JSONField(default=list, help_text='分类 ID 数组')),
+                ('cookies', models.JSONField(blank=True, default=dict, help_text='Cookie 检测规则')),
+                ('headers', models.JSONField(blank=True, default=dict, help_text='HTTP Header 检测规则')),
+                ('script_src', models.JSONField(blank=True, default=list, help_text='脚本 URL 正则数组')),
+                ('js', models.JSONField(blank=True, default=list, help_text='JavaScript 变量检测规则')),
+                ('implies', models.JSONField(blank=True, default=list, help_text='依赖关系数组')),
+                ('meta', models.JSONField(blank=True, default=dict, help_text='HTML meta 标签检测规则')),
+                ('html', models.JSONField(blank=True, default=list, help_text='HTML 内容正则数组')),
+                ('description', models.TextField(blank=True, default='', help_text='应用描述')),
+                ('website', models.URLField(blank=True, default='', help_text='官网链接', max_length=500)),
+                ('cpe', models.CharField(blank=True, default='', help_text='CPE 标识符', max_length=300)),
+                ('created_at', models.DateTimeField(auto_now_add=True)),
+            ],
+            options={
+                'verbose_name': 'Wappalyzer 指纹',
+                'verbose_name_plural': 'Wappalyzer 指纹',
+                'db_table': 'wappalyzer_fingerprint',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['name'], name='wappalyzer__name_63c669_idx'), models.Index(fields=['website'], name='wappalyzer__website_88de1c_idx'), models.Index(fields=['cpe'], name='wappalyzer__cpe_30c761_idx'), models.Index(fields=['-created_at'], name='wappalyzer__created_8e6c21_idx')],
+            },
+        ),
+        migrations.CreateModel(
+            name='Wordlist',
+            fields=[
+                ('id', models.AutoField(primary_key=True, serialize=False)),
+                ('name', models.CharField(help_text='字典名称，唯一', max_length=200, unique=True)),
+                ('description', models.CharField(blank=True, default='', help_text='字典描述', max_length=200)),
+                ('file_path', models.CharField(help_text='后端保存的字典文件绝对路径', max_length=500)),
+                ('file_size', models.BigIntegerField(default=0, help_text='文件大小（字节）')),
+                ('line_count', models.IntegerField(default=0, help_text='字典行数')),
+                ('file_hash', models.CharField(blank=True, default='', help_text='文件 SHA-256 哈希，用于缓存校验', max_length=64)),
+                ('created_at', models.DateTimeField(auto_now_add=True, help_text='创建时间')),
+                ('updated_at', models.DateTimeField(auto_now=True, help_text='更新时间')),
+            ],
+            options={
+                'verbose_name': '字典文件',
+                'verbose_name_plural': '字典文件',
+                'db_table': 'wordlist',
+                'ordering': ['-created_at'],
+                'indexes': [models.Index(fields=['-created_at'], name='wordlist_created_4afb02_idx')],
+            },
+        ),
+        migrations.CreateModel(
+            name='WorkerNode',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('name', models.CharField(help_text='节点名称', max_length=100)),
+                ('ip_address', models.GenericIPAddressField(help_text='IP 地址（本地节点为 127.0.0.1）')),
+                ('ssh_port', models.IntegerField(default=22, help_text='SSH 端口')),
+                ('username', models.CharField(default='root', help_text='SSH 用户名', max_length=50)),
+                ('password', models.CharField(blank=True, default='', help_text='SSH 密码', max_length=200)),
+                ('is_local', models.BooleanField(default=False, help_text='是否为本地节点（Docker 容器内）')),
+                ('status', models.CharField(choices=[('pending', '待部署'), ('deploying', '部署中'), ('online', '在线'), ('offline', '离线'), ('updating', '更新中'), ('outdated', '版本过低')], default='pending', help_text='状态: pending/deploying/online/offline', max_length=20)),
+                ('created_at', models.DateTimeField(auto_now_add=True)),
+                ('updated_at', models.DateTimeField(auto_now=True)),
+            ],
+            options={
+                'verbose_name': 'Worker 节点',
+                'db_table': 'worker_node',
+                'ordering': ['-created_at'],
+                'constraints': [models.UniqueConstraint(condition=models.Q(('is_local', False)), fields=('ip_address',), name='unique_remote_worker_ip'), models.UniqueConstraint(fields=('name',), name='unique_worker_name')],
+            },
+        ),
+    ]

backend/apps/engine/models/__init__.py

@@ -4,7 +4,14 @@
 """
 
 from .engine import WorkerNode, ScanEngine, Wordlist, NucleiTemplateRepo
-from .fingerprints import EholeFingerprint, GobyFingerprint, WappalyzerFingerprint
+from .fingerprints import (
+    EholeFingerprint,
+    GobyFingerprint,
+    WappalyzerFingerprint,
+    FingersFingerprint,
+    FingerPrintHubFingerprint,
+    ARLFingerprint,
+)
 
 __all__ = [
     # 核心 Models
@@ -16,4 +23,7 @@ __all__ = [
     "EholeFingerprint",
     "GobyFingerprint",
     "WappalyzerFingerprint",
+    "FingersFingerprint",
+    "FingerPrintHubFingerprint",
+    "ARLFingerprint",
 ]

backend/apps/engine/models/fingerprints.py

@@ -106,3 +106,90 @@ class WappalyzerFingerprint(models.Model):
     
     def __str__(self) -> str:
         return f"{self.name}"
+
+
+class FingersFingerprint(models.Model):
+    """Fingers 格式指纹规则 (fingers_http.json)
+    
+    使用正则表达式和标签进行匹配，支持 favicon hash、header、body 等多种检测方式
+    """
+    
+    name = models.CharField(max_length=300, unique=True, help_text='指纹名称')
+    link = models.URLField(max_length=500, blank=True, default='', help_text='相关链接')
+    rule = models.JSONField(default=list, help_text='匹配规则数组')
+    tag = models.JSONField(default=list, help_text='标签数组')
+    focus = models.BooleanField(default=False, help_text='是否重点关注')
+    default_port = models.JSONField(default=list, blank=True, help_text='默认端口数组')
+    created_at = models.DateTimeField(auto_now_add=True)
+    
+    class Meta:
+        db_table = 'fingers_fingerprint'
+        verbose_name = 'Fingers 指纹'
+        verbose_name_plural = 'Fingers 指纹'
+        ordering = ['-created_at']
+        indexes = [
+            models.Index(fields=['name']),
+            models.Index(fields=['link']),
+            models.Index(fields=['focus']),
+            models.Index(fields=['-created_at']),
+        ]
+    
+    def __str__(self) -> str:
+        return f"{self.name}"
+
+
+class FingerPrintHubFingerprint(models.Model):
+    """FingerPrintHub 格式指纹规则 (fingerprinthub_web.json)
+    
+    基于 nuclei 模板格式，使用 HTTP 请求和响应特征进行匹配
+    """
+    
+    fp_id = models.CharField(max_length=200, unique=True, help_text='指纹ID')
+    name = models.CharField(max_length=300, help_text='指纹名称')
+    author = models.CharField(max_length=200, blank=True, default='', help_text='作者')
+    tags = models.CharField(max_length=500, blank=True, default='', help_text='标签')
+    severity = models.CharField(max_length=50, blank=True, default='info', help_text='严重程度')
+    metadata = models.JSONField(default=dict, blank=True, help_text='元数据')
+    http = models.JSONField(default=list, help_text='HTTP 匹配规则')
+    source_file = models.CharField(max_length=500, blank=True, default='', help_text='来源文件')
+    created_at = models.DateTimeField(auto_now_add=True)
+    
+    class Meta:
+        db_table = 'fingerprinthub_fingerprint'
+        verbose_name = 'FingerPrintHub 指纹'
+        verbose_name_plural = 'FingerPrintHub 指纹'
+        ordering = ['-created_at']
+        indexes = [
+            models.Index(fields=['fp_id']),
+            models.Index(fields=['name']),
+            models.Index(fields=['author']),
+            models.Index(fields=['severity']),
+            models.Index(fields=['-created_at']),
+        ]
+    
+    def __str__(self) -> str:
+        return f"{self.name} ({self.fp_id})"
+
+
+class ARLFingerprint(models.Model):
+    """ARL 格式指纹规则 (ARL.yaml)
+    
+    使用简单的 name + rule 表达式格式
+    """
+    
+    name = models.CharField(max_length=300, unique=True, help_text='指纹名称')
+    rule = models.TextField(help_text='匹配规则表达式')
+    created_at = models.DateTimeField(auto_now_add=True)
+    
+    class Meta:
+        db_table = 'arl_fingerprint'
+        verbose_name = 'ARL 指纹'
+        verbose_name_plural = 'ARL 指纹'
+        ordering = ['-created_at']
+        indexes = [
+            models.Index(fields=['name']),
+            models.Index(fields=['-created_at']),
+        ]
+    
+    def __str__(self) -> str:
+        return f"{self.name}"

backend/apps/engine/scheduler.py

@@ -89,6 +89,8 @@ def _register_scheduled_jobs(scheduler: BackgroundScheduler):
     )
     logger.info("  - 已注册: 扫描结果清理（每天 03:00）")
     
+    # 注意：搜索物化视图刷新已迁移到 pg_ivm 增量维护，无需定时任务
+
 
 def _trigger_scheduled_scans():
     """触发到期的定时扫描任务"""

backend/apps/engine/serializers/fingerprints/__init__.py

@@ -6,9 +6,15 @@
 from .ehole import EholeFingerprintSerializer
 from .goby import GobyFingerprintSerializer
 from .wappalyzer import WappalyzerFingerprintSerializer
+from .fingers import FingersFingerprintSerializer
+from .fingerprinthub import FingerPrintHubFingerprintSerializer
+from .arl import ARLFingerprintSerializer
 
 __all__ = [
     "EholeFingerprintSerializer",
     "GobyFingerprintSerializer",
     "WappalyzerFingerprintSerializer",
+    "FingersFingerprintSerializer",
+    "FingerPrintHubFingerprintSerializer",
+    "ARLFingerprintSerializer",
 ]

backend/apps/engine/serializers/fingerprints/arl.py

@@ -0,0 +1,31 @@
+"""ARL 指纹 Serializer"""
+
+from rest_framework import serializers
+
+from apps.engine.models import ARLFingerprint
+
+
+class ARLFingerprintSerializer(serializers.ModelSerializer):
+    """ARL 指纹序列化器
+    
+    字段映射:
+    - name: 指纹名称 (必填, 唯一)
+    - rule: 匹配规则表达式 (必填)
+    """
+    
+    class Meta:
+        model = ARLFingerprint
+        fields = ['id', 'name', 'rule', 'created_at']
+        read_only_fields = ['id', 'created_at']
+    
+    def validate_name(self, value):
+        """校验 name 字段"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("name 字段不能为空")
+        return value.strip()
+    
+    def validate_rule(self, value):
+        """校验 rule 字段"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("rule 字段不能为空")
+        return value.strip()

backend/apps/engine/serializers/fingerprints/fingerprinthub.py

@@ -0,0 +1,50 @@
+"""FingerPrintHub 指纹 Serializer"""
+
+from rest_framework import serializers
+
+from apps.engine.models import FingerPrintHubFingerprint
+
+
+class FingerPrintHubFingerprintSerializer(serializers.ModelSerializer):
+    """FingerPrintHub 指纹序列化器
+    
+    字段映射:
+    - fp_id: 指纹ID (必填, 唯一)
+    - name: 指纹名称 (必填)
+    - author: 作者 (可选)
+    - tags: 标签字符串 (可选)
+    - severity: 严重程度 (可选, 默认 'info')
+    - metadata: 元数据 JSON (可选)
+    - http: HTTP 匹配规则数组 (必填)
+    - source_file: 来源文件 (可选)
+    """
+    
+    class Meta:
+        model = FingerPrintHubFingerprint
+        fields = ['id', 'fp_id', 'name', 'author', 'tags', 'severity',
+                  'metadata', 'http', 'source_file', 'created_at']
+        read_only_fields = ['id', 'created_at']
+    
+    def validate_fp_id(self, value):
+        """校验 fp_id 字段"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("fp_id 字段不能为空")
+        return value.strip()
+    
+    def validate_name(self, value):
+        """校验 name 字段"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("name 字段不能为空")
+        return value.strip()
+    
+    def validate_http(self, value):
+        """校验 http 字段"""
+        if not isinstance(value, list):
+            raise serializers.ValidationError("http 必须是数组")
+        return value
+    
+    def validate_metadata(self, value):
+        """校验 metadata 字段"""
+        if not isinstance(value, dict):
+            raise serializers.ValidationError("metadata 必须是对象")
+        return value

backend/apps/engine/serializers/fingerprints/fingers.py

@@ -0,0 +1,48 @@
+"""Fingers 指纹 Serializer"""
+
+from rest_framework import serializers
+
+from apps.engine.models import FingersFingerprint
+
+
+class FingersFingerprintSerializer(serializers.ModelSerializer):
+    """Fingers 指纹序列化器
+    
+    字段映射:
+    - name: 指纹名称 (必填, 唯一)
+    - link: 相关链接 (可选)
+    - rule: 匹配规则数组 (必填)
+    - tag: 标签数组 (可选)
+    - focus: 是否重点关注 (可选, 默认 False)
+    - default_port: 默认端口数组 (可选)
+    """
+    
+    class Meta:
+        model = FingersFingerprint
+        fields = ['id', 'name', 'link', 'rule', 'tag', 'focus', 
+                  'default_port', 'created_at']
+        read_only_fields = ['id', 'created_at']
+    
+    def validate_name(self, value):
+        """校验 name 字段"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("name 字段不能为空")
+        return value.strip()
+    
+    def validate_rule(self, value):
+        """校验 rule 字段"""
+        if not isinstance(value, list):
+            raise serializers.ValidationError("rule 必须是数组")
+        return value
+    
+    def validate_tag(self, value):
+        """校验 tag 字段"""
+        if not isinstance(value, list):
+            raise serializers.ValidationError("tag 必须是数组")
+        return value
+    
+    def validate_default_port(self, value):
+        """校验 default_port 字段"""
+        if not isinstance(value, list):
+            raise serializers.ValidationError("default_port 必须是数组")
+        return value

backend/apps/engine/services/deploy_service.py

@@ -66,6 +66,7 @@ def get_start_agent_script(
     # 替换变量
     script = script.replace("{{HEARTBEAT_API_URL}}", heartbeat_api_url or '')
     script = script.replace("{{WORKER_ID}}", str(worker_id) if worker_id else '')
+    script = script.replace("{{WORKER_API_KEY}}", getattr(settings, 'WORKER_API_KEY', ''))
     
     # 注入镜像版本配置（确保远程节点使用相同版本）
     docker_user = getattr(settings, 'DOCKER_USER', 'yyhuni')

backend/apps/engine/services/fingerprints/__init__.py

@@ -7,10 +7,16 @@ from .base import BaseFingerprintService
 from .ehole import EholeFingerprintService
 from .goby import GobyFingerprintService
 from .wappalyzer import WappalyzerFingerprintService
+from .fingers_service import FingersFingerprintService
+from .fingerprinthub_service import FingerPrintHubFingerprintService
+from .arl_service import ARLFingerprintService
 
 __all__ = [
     "BaseFingerprintService",
     "EholeFingerprintService",
     "GobyFingerprintService",
     "WappalyzerFingerprintService",
+    "FingersFingerprintService",
+    "FingerPrintHubFingerprintService",
+    "ARLFingerprintService",
 ]

backend/apps/engine/services/fingerprints/arl_service.py

@@ -0,0 +1,110 @@
+"""ARL 指纹管理 Service
+
+实现 ARL 格式指纹的校验、转换和导出逻辑
+支持 YAML 格式的导入导出
+"""
+
+import logging
+import yaml
+
+from apps.engine.models import ARLFingerprint
+from .base import BaseFingerprintService
+
+logger = logging.getLogger(__name__)
+
+
+class ARLFingerprintService(BaseFingerprintService):
+    """ARL 指纹管理服务（继承基类，实现 ARL 特定逻辑）"""
+    
+    model = ARLFingerprint
+    
+    def validate_fingerprint(self, item: dict) -> bool:
+        """
+        校验单条 ARL 指纹
+        
+        校验规则：
+        - name 字段必须存在且非空
+        - rule 字段必须存在且非空
+        
+        Args:
+            item: 单条指纹数据
+            
+        Returns:
+            bool: 是否有效
+        """
+        name = item.get('name', '')
+        rule = item.get('rule', '')
+        return bool(name and str(name).strip()) and bool(rule and str(rule).strip())
+    
+    def to_model_data(self, item: dict) -> dict:
+        """
+        转换 ARL YAML 格式为 Model 字段
+        
+        Args:
+            item: 原始 ARL YAML 数据
+            
+        Returns:
+            dict: Model 字段数据
+        """
+        return {
+            'name': str(item.get('name', '')).strip(),
+            'rule': str(item.get('rule', '')).strip(),
+        }
+    
+    def get_export_data(self) -> list:
+        """
+        获取导出数据（ARL 格式 - 数组，用于 YAML 导出）
+        
+        Returns:
+            list: ARL 格式的数据（数组格式）
+            [
+                {"name": "...", "rule": "..."},
+                ...
+            ]
+        """
+        fingerprints = self.model.objects.all()
+        return [
+            {
+                'name': fp.name,
+                'rule': fp.rule,
+            }
+            for fp in fingerprints
+        ]
+    
+    def export_to_yaml(self, output_path: str) -> int:
+        """
+        导出所有指纹到 YAML 文件
+        
+        Args:
+            output_path: 输出文件路径
+            
+        Returns:
+            int: 导出的指纹数量
+        """
+        data = self.get_export_data()
+        with open(output_path, 'w', encoding='utf-8') as f:
+            yaml.dump(data, f, allow_unicode=True, default_flow_style=False, sort_keys=False)
+        count = len(data)
+        logger.info("导出 ARL 指纹文件: %s, 数量: %d", output_path, count)
+        return count
+    
+    def parse_yaml_import(self, yaml_content: str) -> list:
+        """
+        解析 YAML 格式的导入内容
+        
+        Args:
+            yaml_content: YAML 格式的字符串内容
+            
+        Returns:
+            list: 解析后的指纹数据列表
+            
+        Raises:
+            ValueError: 当 YAML 格式无效时
+        """
+        try:
+            data = yaml.safe_load(yaml_content)
+            if not isinstance(data, list):
+                raise ValueError("ARL YAML 文件必须是数组格式")
+            return data
+        except yaml.YAMLError as e:
+            raise ValueError(f"无效的 YAML 格式: {e}")

backend/apps/engine/services/fingerprints/fingerprinthub_service.py

@@ -0,0 +1,110 @@
+"""FingerPrintHub 指纹管理 Service
+
+实现 FingerPrintHub 格式指纹的校验、转换和导出逻辑
+"""
+
+from apps.engine.models import FingerPrintHubFingerprint
+from .base import BaseFingerprintService
+
+
+class FingerPrintHubFingerprintService(BaseFingerprintService):
+    """FingerPrintHub 指纹管理服务（继承基类，实现 FingerPrintHub 特定逻辑）"""
+    
+    model = FingerPrintHubFingerprint
+    
+    def validate_fingerprint(self, item: dict) -> bool:
+        """
+        校验单条 FingerPrintHub 指纹
+        
+        校验规则：
+        - id 字段必须存在且非空
+        - info 字段必须存在且包含 name
+        - http 字段必须是数组
+        
+        Args:
+            item: 单条指纹数据
+            
+        Returns:
+            bool: 是否有效
+        """
+        fp_id = item.get('id', '')
+        info = item.get('info', {})
+        http = item.get('http')
+        
+        if not fp_id or not str(fp_id).strip():
+            return False
+        if not isinstance(info, dict) or not info.get('name'):
+            return False
+        if not isinstance(http, list):
+            return False
+        
+        return True
+    
+    def to_model_data(self, item: dict) -> dict:
+        """
+        转换 FingerPrintHub JSON 格式为 Model 字段
+        
+        字段映射（嵌套结构转扁平）：
+        - id (JSON) → fp_id (Model)
+        - info.name (JSON) → name (Model)
+        - info.author (JSON) → author (Model)
+        - info.tags (JSON) → tags (Model)
+        - info.severity (JSON) → severity (Model)
+        - info.metadata (JSON) → metadata (Model)
+        - http (JSON) → http (Model)
+        - _source_file (JSON) → source_file (Model)
+        
+        Args:
+            item: 原始 FingerPrintHub JSON 数据
+            
+        Returns:
+            dict: Model 字段数据
+        """
+        info = item.get('info', {})
+        return {
+            'fp_id': str(item.get('id', '')).strip(),
+            'name': str(info.get('name', '')).strip(),
+            'author': info.get('author', ''),
+            'tags': info.get('tags', ''),
+            'severity': info.get('severity', 'info'),
+            'metadata': info.get('metadata', {}),
+            'http': item.get('http', []),
+            'source_file': item.get('_source_file', ''),
+        }
+    
+    def get_export_data(self) -> list:
+        """
+        获取导出数据（FingerPrintHub JSON 格式 - 数组）
+        
+        Returns:
+            list: FingerPrintHub 格式的 JSON 数据（数组格式）
+            [
+                {
+                    "id": "...",
+                    "info": {"name": "...", "author": "...", "tags": "...", 
+                             "severity": "...", "metadata": {...}},
+                    "http": [...],
+                    "_source_file": "..."
+                },
+                ...
+            ]
+        """
+        fingerprints = self.model.objects.all()
+        data = []
+        for fp in fingerprints:
+            item = {
+                'id': fp.fp_id,
+                'info': {
+                    'name': fp.name,
+                    'author': fp.author,
+                    'tags': fp.tags,
+                    'severity': fp.severity,
+                    'metadata': fp.metadata,
+                },
+                'http': fp.http,
+            }
+            # 只有当 source_file 非空时才添加该字段
+            if fp.source_file:
+                item['_source_file'] = fp.source_file
+            data.append(item)
+        return data

backend/apps/engine/services/fingerprints/fingers_service.py

@@ -0,0 +1,83 @@
+"""Fingers 指纹管理 Service
+
+实现 Fingers 格式指纹的校验、转换和导出逻辑
+"""
+
+from apps.engine.models import FingersFingerprint
+from .base import BaseFingerprintService
+
+
+class FingersFingerprintService(BaseFingerprintService):
+    """Fingers 指纹管理服务（继承基类，实现 Fingers 特定逻辑）"""
+    
+    model = FingersFingerprint
+    
+    def validate_fingerprint(self, item: dict) -> bool:
+        """
+        校验单条 Fingers 指纹
+        
+        校验规则：
+        - name 字段必须存在且非空
+        - rule 字段必须是数组
+        
+        Args:
+            item: 单条指纹数据
+            
+        Returns:
+            bool: 是否有效
+        """
+        name = item.get('name', '')
+        rule = item.get('rule')
+        return bool(name and str(name).strip()) and isinstance(rule, list)
+    
+    def to_model_data(self, item: dict) -> dict:
+        """
+        转换 Fingers JSON 格式为 Model 字段
+        
+        字段映射：
+        - default_port (JSON) → default_port (Model)
+        
+        Args:
+            item: 原始 Fingers JSON 数据
+            
+        Returns:
+            dict: Model 字段数据
+        """
+        return {
+            'name': str(item.get('name', '')).strip(),
+            'link': item.get('link', ''),
+            'rule': item.get('rule', []),
+            'tag': item.get('tag', []),
+            'focus': item.get('focus', False),
+            'default_port': item.get('default_port', []),
+        }
+    
+    def get_export_data(self) -> list:
+        """
+        获取导出数据（Fingers JSON 格式 - 数组）
+        
+        Returns:
+            list: Fingers 格式的 JSON 数据（数组格式）
+            [
+                {"name": "...", "link": "...", "rule": [...], "tag": [...], 
+                 "focus": false, "default_port": [...]},
+                ...
+            ]
+        """
+        fingerprints = self.model.objects.all()
+        data = []
+        for fp in fingerprints:
+            item = {
+                'name': fp.name,
+                'link': fp.link,
+                'rule': fp.rule,
+                'tag': fp.tag,
+            }
+            # 只有当 focus 为 True 时才添加该字段（保持与原始格式一致）
+            if fp.focus:
+                item['focus'] = fp.focus
+            # 只有当 default_port 非空时才添加该字段
+            if fp.default_port:
+                item['default_port'] = fp.default_port
+            data.append(item)
+        return data

backend/apps/engine/services/fingerprints/goby.py

@@ -16,10 +16,9 @@ class GobyFingerprintService(BaseFingerprintService):
         """
         校验单条 Goby 指纹
         
-        校验规则：
+        支持两种格式：
-        - name 字段必须存在且非空
+        1. 标准格式: {"name": "...", "logic": "...", "rule": [...]}
-        - logic 字段必须存在
+        2. JSONL 格式: {"product": "...", "rule": "..."}
-        - rule 字段必须是数组
         
         Args:
             item: 单条指纹数据
@@ -27,25 +26,43 @@ class GobyFingerprintService(BaseFingerprintService):
         Returns:
             bool: 是否有效
         """
+        # 标准格式：name + logic + rule(数组)
         name = item.get('name', '')
-        logic = item.get('logic', '')
+        if name and item.get('logic') is not None and isinstance(item.get('rule'), list):
-        rule = item.get('rule')
+            return bool(str(name).strip())
-        return bool(name and str(name).strip()) and bool(logic) and isinstance(rule, list)
+        
+        # JSONL 格式：product + rule(字符串)
+        product = item.get('product', '')
+        rule = item.get('rule', '')
+        return bool(product and str(product).strip() and rule and str(rule).strip())
     
     def to_model_data(self, item: dict) -> dict:
         """
         转换 Goby JSON 格式为 Model 字段
         
+        支持两种输入格式：
+        1. 标准格式: {"name": "...", "logic": "...", "rule": [...]}
+        2. JSONL 格式: {"product": "...", "rule": "..."}
+        
         Args:
             item: 原始 Goby JSON 数据
             
         Returns:
             dict: Model 字段数据
         """
+        # 标准格式
+        if 'name' in item and isinstance(item.get('rule'), list):
+            return {
+                'name': str(item.get('name', '')).strip(),
+                'logic': item.get('logic', ''),
+                'rule': item.get('rule', []),
+            }
+        
+        # JSONL 格式：将 rule 字符串转为单元素数组
         return {
-            'name': str(item.get('name', '')).strip(),
+            'name': str(item.get('product', '')).strip(),
-            'logic': item.get('logic', ''),
+            'logic': 'or',  # JSONL 格式默认 or 逻辑
-            'rule': item.get('rule', []),
+            'rule': [item.get('rule', '')] if item.get('rule') else [],
         }
     
     def get_export_data(self) -> list:

backend/apps/engine/services/nuclei_template_repo_service.py

@@ -186,7 +186,6 @@ class NucleiTemplateRepoService:
             RuntimeError: Git 命令执行失败
         """
         import subprocess
-        from apps.common.utils.git_proxy import get_git_proxy_url
 
         obj = self._get_repo_obj(repo_id)
 
@@ -197,14 +196,12 @@ class NucleiTemplateRepoService:
         cmd: List[str]
         action: str
 
-        # 获取代理后的 URL（如果启用了 Git 加速）
+        # 直接使用原始 URL（不再使用 Git 加速）
-        proxied_url = get_git_proxy_url(obj.repo_url)
+        repo_url = obj.repo_url
-        if proxied_url != obj.repo_url:
-            logger.info("使用 Git 加速: %s -> %s", obj.repo_url, proxied_url)
 
         # 判断是 clone 还是 pull
         if git_dir.is_dir():
-            # 检查远程地址是否变化（比较原始 URL，不是代理 URL）
+            # 检查远程地址是否变化
             current_remote = subprocess.run(
                 ["git", "-C", str(local_path), "remote", "get-url", "origin"],
                 check=False,
@@ -214,13 +211,13 @@ class NucleiTemplateRepoService:
             )
             current_url = current_remote.stdout.strip() if current_remote.returncode == 0 else ""
             
-            # 检查是否需要重新 clone（原始 URL 或代理 URL 变化都需要）
+            # 检查是否需要重新 clone
-            if current_url not in [obj.repo_url, proxied_url]:
+            if current_url != repo_url:
                 # 远程地址变化，删除旧目录重新 clone
-                logger.info("nuclei 模板仓库 %s 远程地址变化，重新 clone: %s -> %s", obj.id, current_url, obj.repo_url)
+                logger.info("nuclei 模板仓库 %s 远程地址变化，重新 clone: %s -> %s", obj.id, current_url, repo_url)
                 shutil.rmtree(local_path)
                 local_path.mkdir(parents=True, exist_ok=True)
-                cmd = ["git", "clone", "--depth", "1", proxied_url, str(local_path)]
+                cmd = ["git", "clone", "--depth", "1", repo_url, str(local_path)]
                 action = "clone"
             else:
                 # 已有仓库且地址未变，执行 pull
@@ -231,7 +228,7 @@ class NucleiTemplateRepoService:
             if local_path.exists() and not local_path.is_dir():
                 raise RuntimeError(f"本地路径已存在且不是目录: {local_path}")
             # --depth 1 浅克隆，只获取最新提交，节省空间和时间
-            cmd = ["git", "clone", "--depth", "1", proxied_url, str(local_path)]
+            cmd = ["git", "clone", "--depth", "1", repo_url, str(local_path)]
             action = "clone"
 
         # 执行 Git 命令

backend/apps/engine/services/task_distributor.py

@@ -156,9 +156,9 @@ class TaskDistributor:
         # 降级策略：如果没有正常负载的，循环等待后重新检测
         if not scored_workers:
             if high_load_workers:
-                # 高负载等待参数（默认每 60 秒检测一次，最多 10 次）
+                # 高负载等待参数（每 2 分钟检测一次，最多等待 2 小时）
-                high_load_wait = getattr(settings, 'HIGH_LOAD_WAIT_SECONDS', 60)
+                high_load_wait = getattr(settings, 'HIGH_LOAD_WAIT_SECONDS', 120)
-                high_load_max_retries = getattr(settings, 'HIGH_LOAD_MAX_RETRIES', 10)
+                high_load_max_retries = getattr(settings, 'HIGH_LOAD_MAX_RETRIES', 60)
 
                 # 开始等待前发送高负载通知
                 high_load_workers.sort(key=lambda x: x[1])
@@ -204,17 +204,17 @@ class TaskDistributor:
                         logger.info("检测到正常负载 Worker，结束等待")
                         break
 
-                # 超时或仍然高负载，选择负载最低的
+                # 超时后强制派发到负载最低的 Worker
                 if not scored_workers and high_load_workers:
                     high_load_workers.sort(key=lambda x: x[1])
                     best_worker, _, cpu, mem = high_load_workers[0]
 
                     logger.warning(
-                        "等待超时，强制分发到高负载 Worker: %s (CPU: %.1f%%, MEM: %.1f%%)",
+                        "等待 %d 分钟后仍高负载，强制分发到 Worker: %s (CPU: %.1f%%, MEM: %.1f%%)",
+                        (high_load_wait * high_load_max_retries) // 60,
                         best_worker.name, cpu, mem
                     )
                     return best_worker
-                    return best_worker
             else:
                 logger.warning("没有可用的 Worker")
                 return None
@@ -274,21 +274,16 @@ class TaskDistributor:
             network_arg = ""
             server_url = f"https://{settings.PUBLIC_HOST}:{settings.PUBLIC_PORT}"
         
-        # 挂载路径（统一挂载 /opt/xingrin）
+        # 挂载路径（统一挂载 /opt/xingrin，扫描工具在 /opt/xingrin-tools/bin 不受影响）
         host_xingrin_dir = "/opt/xingrin"
         
         # 环境变量：SERVER_URL + IS_LOCAL，其他配置容器启动时从配置中心获取
         # IS_LOCAL 用于 Worker 向配置中心声明身份，决定返回的数据库地址
-        # Prefect 本地模式配置：启用 ephemeral server（本地临时服务器）
         is_local_str = "true" if worker.is_local else "false"
         env_vars = [
             f"-e SERVER_URL={shlex.quote(server_url)}",
             f"-e IS_LOCAL={is_local_str}",
-            "-e PREFECT_HOME=/tmp/.prefect",  # 设置 Prefect 数据目录到可写位置
+            f"-e WORKER_API_KEY={shlex.quote(settings.WORKER_API_KEY)}",  # Worker API 认证密钥
-            "-e PREFECT_SERVER_EPHEMERAL_ENABLED=true",  # 启用 ephemeral server（本地临时服务器）
-            "-e PREFECT_SERVER_EPHEMERAL_STARTUP_TIMEOUT_SECONDS=120",  # 增加启动超时时间
-            "-e PREFECT_SERVER_DATABASE_CONNECTION_URL=sqlite+aiosqlite:////tmp/.prefect/prefect.db",  # 使用 /tmp 下的 SQLite
-            "-e PREFECT_LOGGING_LEVEL=WARNING",  # 日志级别（减少 DEBUG 噪音）
         ]
         
         # 挂载卷（统一挂载整个 /opt/xingrin 目录）
@@ -311,11 +306,14 @@ class TaskDistributor:
         # - 本地 Worker：install.sh 已预拉取镜像，直接使用本地版本
         # - 远程 Worker：deploy 时已预拉取镜像，直接使用本地版本
         # - 避免每次任务都检查 Docker Hub，提升性能和稳定性
-        # 使用双引号包裹 sh -c 命令，内部 shlex.quote 生成的单引号参数可正确解析
+        # OOM 优先级：--oom-score-adj=1000 让 Worker 在内存不足时优先被杀
-        cmd = f'''docker run --rm -d --pull=missing {network_arg} \
+        # - 范围 -1000 到 1000，值越大越容易被 OOM Killer 选中
-            {' '.join(env_vars)} \
+        # - 保护 server/nginx/frontend 等核心服务，确保 Web 界面可用
-            {' '.join(volumes)} \
+        cmd = f'''docker run --rm -d --pull=missing {network_arg} \\
-            {self.docker_image} \
+            --oom-score-adj=1000 \\
+            {' '.join(env_vars)} \\
+            {' '.join(volumes)} \\
+            {self.docker_image} \\
             sh -c "{inner_cmd}"'''
         
         return cmd
@@ -445,8 +443,8 @@ class TaskDistributor:
     def execute_scan_flow(
         self,
         scan_id: int,
-        target_name: str,
         target_id: int,
+        target_name: str,
         scan_workspace_dir: str,
         engine_name: str,
         scheduled_scan_name: str | None = None,
@@ -456,7 +454,6 @@ class TaskDistributor:
 
         Args:
             scan_id: 扫描任务 ID
-            target_name: 目标名称
             target_id: 目标 ID
             scan_workspace_dir: 扫描工作目录
             engine_name: 引擎名称
@@ -471,8 +468,8 @@ class TaskDistributor:
         logger.info("="*60)
         logger.info("execute_scan_flow 开始")
         logger.info("  scan_id: %s", scan_id)
-        logger.info("  target_name: %s", target_name)
         logger.info("  target_id: %s", target_id)
+        logger.info("  target_name: %s", target_name)
         logger.info("  scan_workspace_dir: %s", scan_workspace_dir)
         logger.info("  engine_name: %s", engine_name)
         logger.info("  docker_image: %s", self.docker_image)
@@ -491,7 +488,6 @@ class TaskDistributor:
         # 3. 构建 docker run 命令
         script_args = {
             'scan_id': scan_id,
-            'target_name': target_name,
             'target_id': target_id,
             'scan_workspace_dir': scan_workspace_dir,
             'engine_name': engine_name,
@@ -506,8 +502,8 @@ class TaskDistributor:
         )
 
         logger.info(
-            "提交扫描任务到 Worker: %s - Scan ID: %d, Target: %s",
+            "提交扫描任务到 Worker: %s - Scan ID: %d, Target: %s (ID: %d)",
-            worker.name, scan_id, target_name
+            worker.name, scan_id, target_name, target_id
         )
         
         # 4. 执行 docker run（本地直接执行，远程通过 SSH）

backend/apps/engine/urls.py

@@ -11,6 +11,9 @@ from .views.fingerprints import (
     EholeFingerprintViewSet,
     GobyFingerprintViewSet,
     WappalyzerFingerprintViewSet,
+    FingersFingerprintViewSet,
+    FingerPrintHubFingerprintViewSet,
+    ARLFingerprintViewSet,
 )
 
 
@@ -24,6 +27,9 @@ router.register(r"nuclei/repos", NucleiTemplateRepoViewSet, basename="nuclei-rep
 router.register(r"fingerprints/ehole", EholeFingerprintViewSet, basename="ehole-fingerprint")
 router.register(r"fingerprints/goby", GobyFingerprintViewSet, basename="goby-fingerprint")
 router.register(r"fingerprints/wappalyzer", WappalyzerFingerprintViewSet, basename="wappalyzer-fingerprint")
+router.register(r"fingerprints/fingers", FingersFingerprintViewSet, basename="fingers-fingerprint")
+router.register(r"fingerprints/fingerprinthub", FingerPrintHubFingerprintViewSet, basename="fingerprinthub-fingerprint")
+router.register(r"fingerprints/arl", ARLFingerprintViewSet, basename="arl-fingerprint")
 
 urlpatterns = [
     path("", include(router.urls)),

backend/apps/engine/views/fingerprints/__init__.py

@@ -7,10 +7,16 @@ from .base import BaseFingerprintViewSet
 from .ehole import EholeFingerprintViewSet
 from .goby import GobyFingerprintViewSet
 from .wappalyzer import WappalyzerFingerprintViewSet
+from .fingers import FingersFingerprintViewSet
+from .fingerprinthub import FingerPrintHubFingerprintViewSet
+from .arl import ARLFingerprintViewSet
 
 __all__ = [
     "BaseFingerprintViewSet",
     "EholeFingerprintViewSet",
     "GobyFingerprintViewSet",
     "WappalyzerFingerprintViewSet",
+    "FingersFingerprintViewSet",
+    "FingerPrintHubFingerprintViewSet",
+    "ARLFingerprintViewSet",
 ]

backend/apps/engine/views/fingerprints/arl.py

@@ -0,0 +1,122 @@
+"""ARL 指纹管理 ViewSet"""
+
+import yaml
+from django.http import HttpResponse
+from rest_framework.decorators import action
+from rest_framework.exceptions import ValidationError
+
+from apps.common.pagination import BasePagination
+from apps.common.response_helpers import success_response
+from apps.engine.models import ARLFingerprint
+from apps.engine.serializers.fingerprints import ARLFingerprintSerializer
+from apps.engine.services.fingerprints import ARLFingerprintService
+
+from .base import BaseFingerprintViewSet
+
+
+class ARLFingerprintViewSet(BaseFingerprintViewSet):
+    """ARL 指纹管理 ViewSet
+    
+    继承自 BaseFingerprintViewSet，提供以下 API：
+    
+    标准 CRUD（ModelViewSet）：
+    - GET    /                  列表查询（分页）
+    - POST   /                  创建单条
+    - GET    /{id}/             获取详情
+    - PUT    /{id}/             更新
+    - DELETE /{id}/             删除
+    
+    批量操作（继承自基类）：
+    - POST   /batch_create/     批量创建（JSON body）
+    - POST   /import_file/      文件导入（multipart/form-data，支持 YAML）
+    - POST   /bulk-delete/      批量删除
+    - POST   /delete-all/       删除所有
+    - GET    /export/           导出下载（YAML 格式）
+    
+    智能过滤语法（filter 参数）：
+    - name="word"        模糊匹配 name 字段
+    - name=="WordPress"  精确匹配
+    - rule="body="       按规则内容筛选
+    """
+    
+    queryset = ARLFingerprint.objects.all()
+    serializer_class = ARLFingerprintSerializer
+    pagination_class = BasePagination
+    service_class = ARLFingerprintService
+    
+    # 排序配置
+    ordering_fields = ['created_at', 'name']
+    ordering = ['-created_at']
+    
+    # ARL 过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'name': 'name',
+        'rule': 'rule',
+    }
+    
+    def parse_import_data(self, json_data) -> list:
+        """
+        解析 ARL 格式的导入数据（JSON 格式）
+        
+        输入格式：[{...}, {...}] 数组格式
+        返回：指纹列表
+        """
+        if isinstance(json_data, list):
+            return json_data
+        return []
+    
+    def get_export_filename(self) -> str:
+        """导出文件名"""
+        return 'ARL.yaml'
+    
+    @action(detail=False, methods=['post'])
+    def import_file(self, request):
+        """
+        文件导入（支持 YAML 和 JSON 格式）
+        POST /api/engine/fingerprints/arl/import_file/
+        
+        请求格式：multipart/form-data
+        - file: YAML 或 JSON 文件
+        
+        返回：同 batch_create
+        """
+        file = request.FILES.get('file')
+        if not file:
+            raise ValidationError('缺少文件')
+        
+        filename = file.name.lower()
+        content = file.read().decode('utf-8')
+        
+        try:
+            if filename.endswith('.yaml') or filename.endswith('.yml'):
+                # YAML 格式
+                fingerprints = yaml.safe_load(content)
+            else:
+                # JSON 格式
+                import json
+                fingerprints = json.loads(content)
+        except (yaml.YAMLError, json.JSONDecodeError) as e:
+            raise ValidationError(f'无效的文件格式: {e}')
+        
+        if not isinstance(fingerprints, list):
+            raise ValidationError('文件内容必须是数组格式')
+        
+        if not fingerprints:
+            raise ValidationError('文件中没有有效的指纹数据')
+        
+        result = self.get_service().batch_create_fingerprints(fingerprints)
+        return success_response(data=result)
+    
+    @action(detail=False, methods=['get'])
+    def export(self, request):
+        """
+        导出指纹（YAML 格式）
+        GET /api/engine/fingerprints/arl/export/
+        
+        返回：YAML 文件下载
+        """
+        data = self.get_service().get_export_data()
+        content = yaml.dump(data, allow_unicode=True, default_flow_style=False, sort_keys=False)
+        response = HttpResponse(content, content_type='application/x-yaml')
+        response['Content-Disposition'] = f'attachment; filename="{self.get_export_filename()}"'
+        return response

backend/apps/engine/views/fingerprints/base.py

@@ -13,6 +13,7 @@ from rest_framework.response import Response
 from rest_framework.exceptions import ValidationError
 
 from apps.common.pagination import BasePagination
+from apps.common.response_helpers import success_response
 from apps.common.utils.filter_utils import apply_filters
 
 logger = logging.getLogger(__name__)
@@ -129,7 +130,7 @@ class BaseFingerprintViewSet(viewsets.ModelViewSet):
             raise ValidationError('fingerprints 必须是数组')
         
         result = self.get_service().batch_create_fingerprints(fingerprints)
-        return Response(result, status=status.HTTP_201_CREATED)
+        return success_response(data=result, status_code=status.HTTP_201_CREATED)
     
     @action(detail=False, methods=['post'])
     def import_file(self, request):
@@ -138,7 +139,7 @@ class BaseFingerprintViewSet(viewsets.ModelViewSet):
         POST /api/engine/fingerprints/{type}/import_file/
         
         请求格式：multipart/form-data
-        - file: JSON 文件
+        - file: JSON 文件（支持标准 JSON 和 JSONL 格式）
         
         返回：同 batch_create
         """
@@ -147,16 +148,54 @@ class BaseFingerprintViewSet(viewsets.ModelViewSet):
             raise ValidationError('缺少文件')
         
         try:
-            json_data = json.load(file)
+            content = file.read().decode('utf-8')
+            json_data = self._parse_json_content(content)
         except json.JSONDecodeError as e:
             raise ValidationError(f'无效的 JSON 格式: {e}')
+        except UnicodeDecodeError as e:
+            raise ValidationError(f'文件编码错误: {e}')
         
         fingerprints = self.parse_import_data(json_data)
         if not fingerprints:
             raise ValidationError('文件中没有有效的指纹数据')
         
         result = self.get_service().batch_create_fingerprints(fingerprints)
-        return Response(result, status=status.HTTP_201_CREATED)
+        return success_response(data=result, status_code=status.HTTP_201_CREATED)
+    
+    def _parse_json_content(self, content: str):
+        """
+        解析 JSON 内容，支持标准 JSON 和 JSONL 格式
+        
+        Args:
+            content: 文件内容字符串
+            
+        Returns:
+            解析后的数据（list 或 dict）
+        """
+        content = content.strip()
+        
+        # 尝试标准 JSON 解析
+        try:
+            return json.loads(content)
+        except json.JSONDecodeError:
+            pass
+        
+        # 尝试 JSONL 格式（每行一个 JSON 对象）
+        lines = content.split('\n')
+        result = []
+        for i, line in enumerate(lines):
+            line = line.strip()
+            if not line:
+                continue
+            try:
+                result.append(json.loads(line))
+            except json.JSONDecodeError as e:
+                raise json.JSONDecodeError(f'第 {i + 1} 行解析失败: {e.msg}', e.doc, e.pos)
+        
+        if not result:
+            raise json.JSONDecodeError('文件为空或格式无效', content, 0)
+        
+        return result
     
     @action(detail=False, methods=['post'], url_path='bulk-delete')
     def bulk_delete(self, request):
@@ -174,7 +213,7 @@ class BaseFingerprintViewSet(viewsets.ModelViewSet):
             raise ValidationError('ids 必须是数组')
         
         deleted_count = self.queryset.model.objects.filter(id__in=ids).delete()[0]
-        return Response({'deleted': deleted_count})
+        return success_response(data={'deleted': deleted_count})
     
     @action(detail=False, methods=['post'], url_path='delete-all')
     def delete_all(self, request):
@@ -185,7 +224,7 @@ class BaseFingerprintViewSet(viewsets.ModelViewSet):
         返回：{"deleted": 1000}
         """
         deleted_count = self.queryset.model.objects.all().delete()[0]
-        return Response({'deleted': deleted_count})
+        return success_response(data={'deleted': deleted_count})
     
     @action(detail=False, methods=['get'])
     def export(self, request):

backend/apps/engine/views/fingerprints/fingerprinthub.py

@@ -0,0 +1,73 @@
+"""FingerPrintHub 指纹管理 ViewSet"""
+
+from apps.common.pagination import BasePagination
+from apps.engine.models import FingerPrintHubFingerprint
+from apps.engine.serializers.fingerprints import FingerPrintHubFingerprintSerializer
+from apps.engine.services.fingerprints import FingerPrintHubFingerprintService
+
+from .base import BaseFingerprintViewSet
+
+
+class FingerPrintHubFingerprintViewSet(BaseFingerprintViewSet):
+    """FingerPrintHub 指纹管理 ViewSet
+    
+    继承自 BaseFingerprintViewSet，提供以下 API：
+    
+    标准 CRUD（ModelViewSet）：
+    - GET    /                  列表查询（分页）
+    - POST   /                  创建单条
+    - GET    /{id}/             获取详情
+    - PUT    /{id}/             更新
+    - DELETE /{id}/             删除
+    
+    批量操作（继承自基类）：
+    - POST   /batch_create/     批量创建（JSON body）
+    - POST   /import_file/      文件导入（multipart/form-data）
+    - POST   /bulk-delete/      批量删除
+    - POST   /delete-all/       删除所有
+    - GET    /export/           导出下载
+    
+    智能过滤语法（filter 参数）：
+    - name="word"        模糊匹配 name 字段
+    - fp_id=="xxx"       精确匹配指纹ID
+    - author="xxx"       按作者筛选
+    - severity="info"    按严重程度筛选
+    - tags="cms"         按标签筛选
+    """
+    
+    queryset = FingerPrintHubFingerprint.objects.all()
+    serializer_class = FingerPrintHubFingerprintSerializer
+    pagination_class = BasePagination
+    service_class = FingerPrintHubFingerprintService
+    
+    # 排序配置
+    ordering_fields = ['created_at', 'name', 'severity']
+    ordering = ['-created_at']
+    
+    # FingerPrintHub 过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'fp_id': 'fp_id',
+        'name': 'name',
+        'author': 'author',
+        'tags': 'tags',
+        'severity': 'severity',
+        'source_file': 'source_file',
+    }
+    
+    # JSON 数组字段（使用 __contains 查询）
+    JSON_ARRAY_FIELDS = ['http']
+    
+    def parse_import_data(self, json_data) -> list:
+        """
+        解析 FingerPrintHub JSON 格式的导入数据
+        
+        输入格式：[{...}, {...}] 数组格式
+        返回：指纹列表
+        """
+        if isinstance(json_data, list):
+            return json_data
+        return []
+    
+    def get_export_filename(self) -> str:
+        """导出文件名"""
+        return 'fingerprinthub_web.json'

backend/apps/engine/views/fingerprints/fingers.py

@@ -0,0 +1,69 @@
+"""Fingers 指纹管理 ViewSet"""
+
+from apps.common.pagination import BasePagination
+from apps.engine.models import FingersFingerprint
+from apps.engine.serializers.fingerprints import FingersFingerprintSerializer
+from apps.engine.services.fingerprints import FingersFingerprintService
+
+from .base import BaseFingerprintViewSet
+
+
+class FingersFingerprintViewSet(BaseFingerprintViewSet):
+    """Fingers 指纹管理 ViewSet
+    
+    继承自 BaseFingerprintViewSet，提供以下 API：
+    
+    标准 CRUD（ModelViewSet）：
+    - GET    /                  列表查询（分页）
+    - POST   /                  创建单条
+    - GET    /{id}/             获取详情
+    - PUT    /{id}/             更新
+    - DELETE /{id}/             删除
+    
+    批量操作（继承自基类）：
+    - POST   /batch_create/     批量创建（JSON body）
+    - POST   /import_file/      文件导入（multipart/form-data）
+    - POST   /bulk-delete/      批量删除
+    - POST   /delete-all/       删除所有
+    - GET    /export/           导出下载
+    
+    智能过滤语法（filter 参数）：
+    - name="word"        模糊匹配 name 字段
+    - name=="WordPress"  精确匹配
+    - tag="cms"          按标签筛选
+    - focus="true"       按重点关注筛选
+    """
+    
+    queryset = FingersFingerprint.objects.all()
+    serializer_class = FingersFingerprintSerializer
+    pagination_class = BasePagination
+    service_class = FingersFingerprintService
+    
+    # 排序配置
+    ordering_fields = ['created_at', 'name']
+    ordering = ['-created_at']
+    
+    # Fingers 过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'name': 'name',
+        'link': 'link',
+        'focus': 'focus',
+    }
+    
+    # JSON 数组字段（使用 __contains 查询）
+    JSON_ARRAY_FIELDS = ['tag', 'rule', 'default_port']
+    
+    def parse_import_data(self, json_data) -> list:
+        """
+        解析 Fingers JSON 格式的导入数据
+        
+        输入格式：[{...}, {...}] 数组格式
+        返回：指纹列表
+        """
+        if isinstance(json_data, list):
+            return json_data
+        return []
+    
+    def get_export_filename(self) -> str:
+        """导出文件名"""
+        return 'fingers_http.json'

backend/apps/engine/views/nuclei_template_repo_views.py

@@ -31,6 +31,8 @@ from rest_framework.decorators import action
 from rest_framework.request import Request
 from rest_framework.response import Response
 
+from apps.common.response_helpers import success_response, error_response
+from apps.common.error_codes import ErrorCodes
 from apps.engine.models import NucleiTemplateRepo
 from apps.engine.serializers import NucleiTemplateRepoSerializer
 from apps.engine.services import NucleiTemplateRepoService
@@ -107,18 +109,30 @@ class NucleiTemplateRepoViewSet(viewsets.ModelViewSet):
         try:
             repo_id = int(pk) if pk is not None else None
         except (TypeError, ValueError):
-            return Response({"message": "无效的仓库 ID"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Invalid repository ID',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         # 调用 Service 层
         try:
             result = self.service.refresh_repo(repo_id)
         except ValidationError as exc:
-            return Response({"message": str(exc)}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message=str(exc),
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
         except Exception as exc:  # noqa: BLE001
             logger.error("刷新 Nuclei 模板仓库失败: %s", exc, exc_info=True)
-            return Response({"message": f"刷新仓库失败: {exc}"}, status=status.HTTP_500_INTERNAL_SERVER_ERROR)
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message=f'Refresh failed: {exc}',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )
 
-        return Response({"message": "刷新成功", "result": result}, status=status.HTTP_200_OK)
+        return success_response(data={'result': result})
 
     # ==================== 自定义 Action: 模板只读浏览 ====================
 
@@ -142,18 +156,30 @@ class NucleiTemplateRepoViewSet(viewsets.ModelViewSet):
         try:
             repo_id = int(pk) if pk is not None else None
         except (TypeError, ValueError):
-            return Response({"message": "无效的仓库 ID"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Invalid repository ID',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         # 调用 Service 层，仅从当前本地目录读取目录树
         try:
             roots = self.service.get_template_tree(repo_id)
         except ValidationError as exc:
-            return Response({"message": str(exc)}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message=str(exc),
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
         except Exception as exc:  # noqa: BLE001
             logger.error("获取 Nuclei 模板目录树失败: %s", exc, exc_info=True)
-            return Response({"message": "获取模板目录树失败"}, status=status.HTTP_500_INTERNAL_SERVER_ERROR)
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Failed to get template tree',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )
 
-        return Response({"roots": roots})
+        return success_response(data={'roots': roots})
 
     @action(detail=True, methods=["get"], url_path="templates/content")
     def templates_content(self, request: Request, pk: str | None = None) -> Response:
@@ -174,23 +200,43 @@ class NucleiTemplateRepoViewSet(viewsets.ModelViewSet):
         try:
             repo_id = int(pk) if pk is not None else None
         except (TypeError, ValueError):
-            return Response({"message": "无效的仓库 ID"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Invalid repository ID',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         # 解析 path 参数
         rel_path = (request.query_params.get("path", "") or "").strip()
         if not rel_path:
-            return Response({"message": "缺少 path 参数"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Missing path parameter',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         # 调用 Service 层
         try:
             result = self.service.get_template_content(repo_id, rel_path)
         except ValidationError as exc:
-            return Response({"message": str(exc)}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message=str(exc),
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
         except Exception as exc:  # noqa: BLE001
             logger.error("获取 Nuclei 模板内容失败: %s", exc, exc_info=True)
-            return Response({"message": "获取模板内容失败"}, status=status.HTTP_500_INTERNAL_SERVER_ERROR)
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Failed to get template content',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )
 
         # 文件不存在
         if result is None:
-            return Response({"message": "模板不存在或无法读取"}, status=status.HTTP_404_NOT_FOUND)
+            return error_response(
-        return Response(result)
+                code=ErrorCodes.NOT_FOUND,
+                message='Template not found or unreadable',
+                status_code=status.HTTP_404_NOT_FOUND
+            )
+        return success_response(data=result)

backend/apps/engine/views/wordlist_views.py

@@ -9,6 +9,8 @@ from rest_framework.decorators import action
 from rest_framework.response import Response
 
 from apps.common.pagination import BasePagination
+from apps.common.response_helpers import success_response, error_response
+from apps.common.error_codes import ErrorCodes
 from apps.engine.serializers.wordlist_serializer import WordlistSerializer
 from apps.engine.services.wordlist_service import WordlistService
 
@@ -46,7 +48,11 @@ class WordlistViewSet(viewsets.ViewSet):
         uploaded_file = request.FILES.get("file")
 
         if not uploaded_file:
-            return Response({"error": "缺少字典文件"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Missing wordlist file',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         try:
             wordlist = self.service.create_wordlist(
@@ -55,21 +61,32 @@ class WordlistViewSet(viewsets.ViewSet):
                 uploaded_file=uploaded_file,
             )
         except ValidationError as exc:
-            return Response({"error": str(exc)}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message=str(exc),
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         serializer = WordlistSerializer(wordlist)
-        return Response(serializer.data, status=status.HTTP_201_CREATED)
+        return success_response(data=serializer.data, status_code=status.HTTP_201_CREATED)
 
     def destroy(self, request, pk=None):
         """删除字典记录"""
         try:
             wordlist_id = int(pk)
         except (TypeError, ValueError):
-            return Response({"error": "无效的 ID"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Invalid ID',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         success = self.service.delete_wordlist(wordlist_id)
         if not success:
-            return Response({"error": "字典不存在"}, status=status.HTTP_404_NOT_FOUND)
+            return error_response(
+                code=ErrorCodes.NOT_FOUND,
+                status_code=status.HTTP_404_NOT_FOUND
+            )
 
         return Response(status=status.HTTP_204_NO_CONTENT)
 
@@ -82,15 +99,27 @@ class WordlistViewSet(viewsets.ViewSet):
         """
         name = (request.query_params.get("wordlist", "") or "").strip()
         if not name:
-            return Response({"error": "缺少参数 wordlist"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Missing parameter: wordlist',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         wordlist = self.service.get_wordlist_by_name(name)
         if not wordlist:
-            return Response({"error": "字典不存在"}, status=status.HTTP_404_NOT_FOUND)
+            return error_response(
+                code=ErrorCodes.NOT_FOUND,
+                message='Wordlist not found',
+                status_code=status.HTTP_404_NOT_FOUND
+            )
 
         file_path = wordlist.file_path
         if not file_path or not os.path.exists(file_path):
-            return Response({"error": "字典文件不存在"}, status=status.HTTP_404_NOT_FOUND)
+            return error_response(
+                code=ErrorCodes.NOT_FOUND,
+                message='Wordlist file not found',
+                status_code=status.HTTP_404_NOT_FOUND
+            )
 
         filename = os.path.basename(file_path)
         response = FileResponse(open(file_path, "rb"), as_attachment=True, filename=filename)
@@ -106,22 +135,38 @@ class WordlistViewSet(viewsets.ViewSet):
         try:
             wordlist_id = int(pk)
         except (TypeError, ValueError):
-            return Response({"error": "无效的 ID"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Invalid ID',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         if request.method == "GET":
             content = self.service.get_wordlist_content(wordlist_id)
             if content is None:
-                return Response({"error": "字典不存在或文件无法读取"}, status=status.HTTP_404_NOT_FOUND)
+                return error_response(
-            return Response({"content": content})
+                    code=ErrorCodes.NOT_FOUND,
+                    message='Wordlist not found or file unreadable',
+                    status_code=status.HTTP_404_NOT_FOUND
+                )
+            return success_response(data={"content": content})
 
         elif request.method == "PUT":
             content = request.data.get("content")
             if content is None:
-                return Response({"error": "缺少 content 参数"}, status=status.HTTP_400_BAD_REQUEST)
+                return error_response(
+                    code=ErrorCodes.VALIDATION_ERROR,
+                    message='Missing content parameter',
+                    status_code=status.HTTP_400_BAD_REQUEST
+                )
 
             wordlist = self.service.update_wordlist_content(wordlist_id, content)
             if not wordlist:
-                return Response({"error": "字典不存在或更新失败"}, status=status.HTTP_404_NOT_FOUND)
+                return error_response(
+                    code=ErrorCodes.NOT_FOUND,
+                    message='Wordlist not found or update failed',
+                    status_code=status.HTTP_404_NOT_FOUND
+                )
 
             serializer = WordlistSerializer(wordlist)
-            return Response(serializer.data)
+            return success_response(data=serializer.data)

backend/apps/engine/views/worker_views.py

@@ -9,6 +9,8 @@ from rest_framework import viewsets, status
 from rest_framework.decorators import action
 from rest_framework.response import Response
 
+from apps.common.response_helpers import success_response, error_response
+from apps.common.error_codes import ErrorCodes
 from apps.engine.serializers import WorkerNodeSerializer
 from apps.engine.services import WorkerService
 from apps.common.signals import worker_delete_failed
@@ -111,9 +113,8 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
         threading.Thread(target=_async_remote_uninstall, daemon=True).start()
         
         # 3. 立即返回成功
-        return Response(
+        return success_response(
-            {"message": f"节点 {worker_name} 已删除"},
+            data={'name': worker_name}
-            status=status.HTTP_200_OK
         )
     
     @action(detail=True, methods=['post'])
@@ -190,11 +191,13 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
                     worker.status = 'online'
                     worker.save(update_fields=['status'])
         
-        return Response({
+        return success_response(
-            'status': 'ok',
+            data={
-            'need_update': need_update,
+                'status': 'ok',
-            'server_version': server_version
+                'needUpdate': need_update,
-        })
+                'serverVersion': server_version
+            }
+        )
     
     def _trigger_remote_agent_update(self, worker, target_version: str):
         """
@@ -304,9 +307,10 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
         is_local = request.data.get('is_local', True)
         
         if not name:
-            return Response(
+            return error_response(
-                {'error': '缺少 name 参数'},
+                code=ErrorCodes.VALIDATION_ERROR,
-                status=status.HTTP_400_BAD_REQUEST
+                message='Missing name parameter',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         worker, created = self.worker_service.register_worker(
@@ -314,11 +318,13 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
             is_local=is_local
         )
         
-        return Response({
+        return success_response(
-            'worker_id': worker.id,
+            data={
-            'name': worker.name,
+                'workerId': worker.id,
-            'created': created
+                'name': worker.name,
-        })
+                'created': created
+            }
+        )
     
     @action(detail=False, methods=['get'])
     def config(self, request):
@@ -334,13 +340,12 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
         返回:
         {
             "db": {"host": "...", "port": "...", ...},
-            "redisUrl": "...",
             "paths": {"results": "...", "logs": "..."}
         }
         
         配置逻辑:
-            - 本地 Worker (is_local=true): db_host=postgres, redis=redis:6379
+            - 本地 Worker (is_local=true): db_host=postgres
-            - 远程 Worker (is_local=false): db_host=PUBLIC_HOST, redis=PUBLIC_HOST:6379
+            - 远程 Worker (is_local=false): db_host=PUBLIC_HOST
         """
         from django.conf import settings
         import logging
@@ -365,39 +370,35 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
             if is_local_worker:
                 # 本地 Worker：直接用 Docker 内部服务名
                 worker_db_host = 'postgres'
-                worker_redis_url = 'redis://redis:6379/0'
             else:
                 # 远程 Worker：通过公网 IP 访问
                 public_host = settings.PUBLIC_HOST
                 if public_host in ('server', 'localhost', '127.0.0.1'):
                     logger.warning("远程 Worker 请求配置，但 PUBLIC_HOST=%s 不是有效的公网地址", public_host)
                 worker_db_host = public_host
-                worker_redis_url = f'redis://{public_host}:6379/0'
         else:
             # 远程数据库场景：所有 Worker 都用 DB_HOST
             worker_db_host = db_host
-            worker_redis_url = getattr(settings, 'WORKER_REDIS_URL', 'redis://redis:6379/0')
         
-        logger.info("返回 Worker 配置 - db_host: %s, redis_url: %s", worker_db_host, worker_redis_url)
+        logger.info("返回 Worker 配置 - db_host: %s", worker_db_host)
         
-        return Response({
+        return success_response(
-            'db': {
+            data={
-                'host': worker_db_host,
+                'db': {
-                'port': str(settings.DATABASES['default']['PORT']),
+                    'host': worker_db_host,
-                'name': settings.DATABASES['default']['NAME'],
+                    'port': str(settings.DATABASES['default']['PORT']),
-                'user': settings.DATABASES['default']['USER'],
+                    'name': settings.DATABASES['default']['NAME'],
-                'password': settings.DATABASES['default']['PASSWORD'],
+                    'user': settings.DATABASES['default']['USER'],
-            },
+                    'password': settings.DATABASES['default']['PASSWORD'],
-            'redisUrl': worker_redis_url,
+                },
-            'paths': {
+                'paths': {
-                'results': getattr(settings, 'CONTAINER_RESULTS_MOUNT', '/opt/xingrin/results'),
+                    'results': getattr(settings, 'CONTAINER_RESULTS_MOUNT', '/opt/xingrin/results'),
-                'logs': getattr(settings, 'CONTAINER_LOGS_MOUNT', '/opt/xingrin/logs'),
+                    'logs': getattr(settings, 'CONTAINER_LOGS_MOUNT', '/opt/xingrin/logs'),
-            },
+                },
-            'logging': {
+                'logging': {
-                'level': os.getenv('LOG_LEVEL', 'INFO'),
+                    'level': os.getenv('LOG_LEVEL', 'INFO'),
-                'enableCommandLogging': os.getenv('ENABLE_COMMAND_LOGGING', 'true').lower() == 'true',
+                    'enableCommandLogging': os.getenv('ENABLE_COMMAND_LOGGING', 'true').lower() == 'true',
-            },
+                },
-            'debug': settings.DEBUG,
+                'debug': settings.DEBUG,
-            # Git 加速配置（用于 Git clone 加速，如 Nuclei 模板仓库）
+            }
-            'gitMirror': settings.GIT_MIRROR,
+        )
-        })

backend/apps/scan/configs/command_templates.py

@@ -7,35 +7,25 @@
 from django.conf import settings
 
 # ==================== 路径配置 ====================
-SCAN_TOOLS_BASE_PATH = getattr(settings, 'SCAN_TOOLS_BASE_PATH', '/opt/xingrin/tools')
+SCAN_TOOLS_BASE_PATH = getattr(settings, 'SCAN_TOOLS_BASE_PATH', '/usr/local/bin')
 
 # ==================== 子域名发现 ====================
 
 SUBDOMAIN_DISCOVERY_COMMANDS = {
     'subfinder': {
-        # 默认使用所有数据源（更全面，略慢），并始终开启递归
+        # 使用所有数据源（包括付费源，只要配置了 API key）
-        # -all       使用所有数据源
+        # -all       使用所有数据源（slow 但全面）
-        # -recursive 对支持递归的源启用递归枚举（默认开启）
+        # -v         显示详细输出，包括使用的数据源（调试用）
-        'base': "subfinder -d {domain} -all -recursive -o '{output_file}' -silent",
+        # 注意：不要加 -recursive，它会排除不支持递归的源（如 fofa）
+        'base': "subfinder -d {domain} -all -o '{output_file}' -v",
         'optional': {
             'threads': '-t {threads}',              # 控制并发 goroutine 数
+            'provider_config': "-pc '{provider_config}'",  # Provider 配置文件路径
         }
     },
     
-    'amass_passive': {
-        # 先执行被动枚举，将结果写入 amass 内部数据库，然后从数据库中导出纯域名（names）到 output_file
-        # -silent 禁用进度条和其他输出
-        'base': "amass enum -passive -silent -d {domain} && amass subs -names -d {domain} > '{output_file}'"
-    },
-    
-    'amass_active': {
-        # 先执行主动枚举 + 爆破，将结果写入 amass 内部数据库，然后从数据库中导出纯域名（names）到 output_file
-        # -silent 禁用进度条和其他输出
-        'base': "amass enum -active -silent -d {domain} -brute && amass subs -names -d {domain} > '{output_file}'"
-    },
-    
     'sublist3r': {
-        'base': "python3 '{scan_tools_base}/Sublist3r/sublist3r.py' -d {domain} -o '{output_file}'",
+        'base': "python3 '/usr/local/share/Sublist3r/sublist3r.py' -d {domain} -o '{output_file}'",
         'optional': {
             'threads': '-t {threads}'
         }
@@ -97,9 +87,11 @@ SITE_SCAN_COMMANDS = {
         'base': (
             "'{scan_tools_base}/httpx' -l '{url_file}' "
             '-status-code -content-type -content-length '
-            '-location -title -server -body-preview '
+            '-location -title -server '
             '-tech-detect -cdn -vhost '
-            '-random-agent -no-color -json'
+            '-include-response '
+            '-rstr 2000 '
+            '-random-agent -no-color -json -silent'
         ),
         'optional': {
             'threads': '-threads {threads}',
@@ -115,7 +107,7 @@ SITE_SCAN_COMMANDS = {
 
 DIRECTORY_SCAN_COMMANDS = {
     'ffuf': {
-        'base': "ffuf -u '{url}FUZZ' -se -ac -sf -json -w '{wordlist}'",  
+        'base': "'{scan_tools_base}/ffuf' -u '{url}FUZZ' -se -ac -sf -json -w '{wordlist}'",  
         'optional': {
             'delay': '-p {delay}',
             'threads': '-t {threads}',
@@ -169,9 +161,11 @@ URL_FETCH_COMMANDS = {
         'base': (
             "'{scan_tools_base}/httpx' -l '{url_file}' "
             '-status-code -content-type -content-length '
-            '-location -title -server -body-preview '
+            '-location -title -server '
             '-tech-detect -cdn -vhost '
-            '-random-agent -no-color -json'
+            '-include-response '
+            '-rstr 2000 '
+            '-random-agent -no-color -json -silent'
         ),
         'optional': {
             'threads': '-threads {threads}',
@@ -209,7 +203,7 @@ VULN_SCAN_COMMANDS = {
         # -silent: 静默模式
         # -l: 输入 URL 列表文件
         # -t: 模板目录路径（支持多个仓库，多次 -t 由 template_args 直接拼接）
-        'base': "nuclei -j -silent -l '{endpoints_file}' {template_args}",
+        'base': "nuclei -j -silent -l '{input_file}' {template_args}",
         'optional': {
             'concurrency': '-c {concurrency}',           # 并发数（默认 25）
             'rate_limit': '-rl {rate_limit}',            # 每秒请求数限制
@@ -220,7 +214,12 @@ VULN_SCAN_COMMANDS = {
             'tags': '-tags {tags}',                      # 过滤标签
             'exclude_tags': '-etags {exclude_tags}',     # 排除标签
         },
-        'input_type': 'endpoints_file',
+        # 支持多种输入类型，用户通过 scan_endpoints/scan_websites 选择
+        'input_types': ['endpoints_file', 'websites_file'],
+        'defaults': {
+            'scan_endpoints': False,  # 默认不扫描 endpoints
+            'scan_websites': True,    # 默认扫描 websites
+        },
     },
 }
 
@@ -239,6 +238,9 @@ FINGERPRINT_DETECT_COMMANDS = {
             'ehole': '--ehole {ehole}',
             'goby': '--goby {goby}',
             'wappalyzer': '--wappalyzer {wappalyzer}',
+            'fingers': '--fingers {fingers}',
+            'fingerprinthub': '--fingerprint {fingerprinthub}',
+            'arl': '--arl {arl}',
         }
     },
 }
@@ -254,11 +256,16 @@ COMMAND_TEMPLATES = {
     'directory_scan': DIRECTORY_SCAN_COMMANDS,
     'url_fetch': URL_FETCH_COMMANDS,
     'vuln_scan': VULN_SCAN_COMMANDS,
+    'screenshot': {},  # 使用 Python 原生库（Playwright），无命令模板
 }
 
 # ==================== 扫描类型配置 ====================
 
 # 执行阶段定义（按顺序执行）
+# Stage 1: 资产发现 - 子域名 → 端口 → 站点探测 → 指纹识别
+# Stage 2: URL 收集 - URL 获取 + 目录扫描（并行）
+# Stage 3: 截图 - 在 URL 收集完成后执行，捕获更多发现的页面
+# Stage 4: 漏洞扫描 - 最后执行
 EXECUTION_STAGES = [
     {
         'mode': 'sequential',
@@ -268,6 +275,10 @@ EXECUTION_STAGES = [
         'mode': 'parallel',
         'flows': ['url_fetch', 'directory_scan']
     },
+    {
+        'mode': 'sequential',
+        'flows': ['screenshot']
+    },
     {
         'mode': 'sequential',
         'flows': ['vuln_scan']

backend/apps/scan/configs/engine_config_example.yaml

@@ -4,14 +4,12 @@
 # 必需参数：enabled（是否启用）
 # 可选参数：timeout（超时秒数，默认 auto 自动计算）
 
-# ==================== 子域名发现 ====================
-# 
-# Stage 1: 被动收集（并行） - 必选，至少启用一个工具
-# Stage 2: 字典爆破（可选） - 使用字典暴力枚举子域名
-# Stage 3: 变异生成 + 验证（可选） - 基于已发现域名生成变异，流式验证存活
-# Stage 4: DNS 存活验证（可选） - 验证所有候选域名是否能解析
-#
 subdomain_discovery:
+  # ==================== 子域名发现 ====================
+  # Stage 1: 被动收集（并行） - 必选，至少启用一个工具
+  # Stage 2: 字典爆破（可选） - 使用字典暴力枚举子域名
+  # Stage 3: 变异生成 + 验证（可选） - 基于已发现域名生成变异，流式验证存活
+  # Stage 4: DNS 存活验证（可选） - 验证所有候选域名是否能解析
   # === Stage 1: 被动收集工具（并行执行）===
   passive_tools:
     subfinder:
@@ -19,14 +17,6 @@ subdomain_discovery:
       timeout: 3600      # 1小时
       # threads: 10      # 并发 goroutine 数
       
-    amass_passive:
-      enabled: true
-      timeout: 3600
-      
-    amass_active:
-      enabled: true      # 主动枚举 + 爆破
-      timeout: 3600
-      
     sublist3r:
       enabled: true
       timeout: 3600
@@ -53,10 +43,10 @@ subdomain_discovery:
   resolve:
     enabled: true
     subdomain_resolve:
-      # timeout: auto    # 自动根据候选子域数量计算
+      timeout: auto    # 自动根据候选子域数量计算
 
-# ==================== 端口扫描 ====================
 port_scan:
+  # ==================== 端口扫描 ====================
   tools:
     naabu_active:
       enabled: true
@@ -64,14 +54,14 @@ port_scan:
       threads: 200       # 并发连接数（默认 5）
       # ports: 1-65535   # 扫描端口范围（默认 1-65535）
       top-ports: 100     # 扫描 nmap top 100 端口
-      rate: 10           # 扫描速率（默认 10）
+      rate: 50           # 扫描速率
       
     naabu_passive:
       enabled: true
       # timeout: auto    # 被动扫描通常较快
 
-# ==================== 站点扫描 ====================
 site_scan:
+  # ==================== 站点扫描 ====================
   tools:
     httpx:
       enabled: true
@@ -81,16 +71,16 @@ site_scan:
       # request-timeout: 10  # 单个请求超时秒数（默认 10）
       # retries: 2           # 请求失败重试次数
 
-# ==================== 指纹识别 ====================
-# 在 site_scan 后串行执行，识别 WebSite 的技术栈
 fingerprint_detect:
+  # ==================== 指纹识别 ====================
+  # 在 站点扫描 后串行执行，识别 WebSite 的技术栈
   tools:
     xingfinger:
       enabled: true
-      fingerprint-libs: [ehole, goby, wappalyzer]  # 启用的指纹库：ehole, goby, wappalyzer, fingers, fingerprinthub
+      fingerprint-libs: [ehole, goby, wappalyzer, fingers, fingerprinthub, arl]  # 默认启动全部指纹库
 
-# ==================== 目录扫描 ====================
 directory_scan:
+  # ==================== 目录扫描 ====================
   tools:
     ffuf:
       enabled: true
@@ -103,8 +93,18 @@ directory_scan:
       match-codes: 200,201,301,302,401,403  # 匹配的 HTTP 状态码
       # rate: 0                           # 每秒请求数（默认 0 不限制）
 
-# ==================== URL 获取 ====================
+screenshot:
+  # ==================== 网站截图 ====================
+  # 使用 Playwright 对网站进行截图，保存为 WebP 格式
+  # 在 Stage 2 与 url_fetch、directory_scan 并行执行
+  tools:
+    playwright:
+      enabled: true
+      concurrency: 5                        # 并发截图数（默认 5）
+      url_sources: [websites]               # URL 来源，当前对website截图，还可以用 [websites, endpoints]
+
 url_fetch:
+  # ==================== URL 获取 ====================
   tools:
     waymore:
       enabled: true
@@ -142,8 +142,8 @@ url_fetch:
       # request-timeout: 10  # 单个请求超时秒数（默认 10）
       # retries: 2           # 请求失败重试次数
 
-# ==================== 漏洞扫描 ====================
 vuln_scan:
+  # ==================== 漏洞扫描 ====================
   tools:
     dalfox_xss:
       enabled: true
@@ -158,7 +158,9 @@ vuln_scan:
 
     nuclei:
       enabled: true
-      # timeout: auto        # 自动计算（根据 endpoints 行数）
+      # timeout: auto        # 自动计算（根据输入 URL 行数）
+      scan-endpoints: false  # 是否扫描 endpoints（默认关闭）
+      scan-websites: true    # 是否扫描 websites（默认开启）
       template-repo-names:   # 模板仓库列表，对应「Nuclei 模板」中的仓库名
         - nuclei-templates
         # - nuclei-custom    # 可追加自定义仓库

backend/apps/scan/decorators.py

@@ -0,0 +1,200 @@
+"""
+扫描流程装饰器模块
+
+提供轻量级的 @scan_flow 和 @scan_task 装饰器，替代 Prefect 的 @flow 和 @task。
+
+核心功能：
+- @scan_flow: 状态管理、通知、性能追踪
+- @scan_task: 重试逻辑（大部分 task 不需要重试，可直接移除装饰器）
+
+设计原则：
+- 保持与 Prefect 装饰器相同的使用方式
+- 零依赖，无额外内存开销
+- 保留原函数签名和返回值
+"""
+
+import functools
+import logging
+import time
+from dataclasses import dataclass, field
+from datetime import datetime
+from typing import Any, Callable, Optional
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class FlowContext:
+    """
+    Flow 执行上下文
+
+    替代 Prefect 的 Flow、FlowRun、State 参数，传递给回调函数。
+    """
+    flow_name: str
+    stage_name: str
+    scan_id: Optional[int] = None
+    target_id: Optional[int] = None
+    target_name: Optional[str] = None
+    parameters: dict = field(default_factory=dict)
+    start_time: datetime = field(default_factory=datetime.now)
+    end_time: Optional[datetime] = None
+    result: Any = None
+    error: Optional[Exception] = None
+    error_message: Optional[str] = None
+
+
+def scan_flow(
+    name: Optional[str] = None,
+    stage_name: Optional[str] = None,
+    on_running: Optional[list[Callable]] = None,
+    on_completion: Optional[list[Callable]] = None,
+    on_failure: Optional[list[Callable]] = None,
+    log_prints: bool = True,  # 保持与 Prefect 兼容，但不使用
+):
+    """
+    扫描流程装饰器
+
+    替代 Prefect 的 @flow 装饰器，提供：
+    - 自动状态管理（start_stage/complete_stage/fail_stage）
+    - 生命周期回调（on_running/on_completion/on_failure）
+    - 性能追踪（FlowPerformanceTracker）
+    - 失败通知
+
+    Args:
+        name: Flow 名称，默认使用函数名
+        stage_name: 阶段名称，默认使用 name
+        on_running: 流程开始时的回调列表
+        on_completion: 流程完成时的回调列表
+        on_failure: 流程失败时的回调列表
+        log_prints: 保持与 Prefect 兼容，不使用
+
+    Usage:
+        @scan_flow(name="site_scan", on_running=[on_scan_flow_running])
+        def site_scan_flow(scan_id: int, target_id: int, ...):
+            ...
+    """
+    def decorator(func: Callable) -> Callable:
+        flow_name = name or func.__name__
+        actual_stage_name = stage_name or flow_name
+
+        @functools.wraps(func)
+        def wrapper(*args, **kwargs) -> Any:
+            # 提取参数
+            scan_id = kwargs.get('scan_id')
+            target_id = kwargs.get('target_id')
+            target_name = kwargs.get('target_name')
+
+            # 创建上下文
+            context = FlowContext(
+                flow_name=flow_name,
+                stage_name=actual_stage_name,
+                scan_id=scan_id,
+                target_id=target_id,
+                target_name=target_name,
+                parameters=kwargs.copy(),
+                start_time=datetime.now(),
+            )
+
+            # 执行 on_running 回调
+            if on_running:
+                for callback in on_running:
+                    try:
+                        callback(context)
+                    except Exception as e:
+                        logger.warning("on_running 回调执行失败: %s", e)
+
+            try:
+                # 执行原函数
+                result = func(*args, **kwargs)
+
+                # 更新上下文
+                context.end_time = datetime.now()
+                context.result = result
+
+                # 执行 on_completion 回调
+                if on_completion:
+                    for callback in on_completion:
+                        try:
+                            callback(context)
+                        except Exception as e:
+                            logger.warning("on_completion 回调执行失败: %s", e)
+
+                return result
+
+            except Exception as e:
+                # 更新上下文
+                context.end_time = datetime.now()
+                context.error = e
+                context.error_message = str(e)
+
+                # 执行 on_failure 回调
+                if on_failure:
+                    for callback in on_failure:
+                        try:
+                            callback(context)
+                        except Exception as cb_error:
+                            logger.warning("on_failure 回调执行失败: %s", cb_error)
+
+                # 重新抛出异常
+                raise
+
+        return wrapper
+    return decorator
+
+
+def scan_task(
+    retries: int = 0,
+    retry_delay: float = 1.0,
+    name: Optional[str] = None,  # 保持与 Prefect 兼容
+):
+    """
+    扫描任务装饰器
+
+    替代 Prefect 的 @task 装饰器，提供重试能力。
+
+    注意：当前代码中大部分 @task 都是 retries=0，可以直接移除装饰器。
+    只有需要重试的 task 才需要使用此装饰器。
+
+    Args:
+        retries: 失败后重试次数，默认 0（不重试）
+        retry_delay: 重试间隔（秒），默认 1.0
+        name: 任务名称，保持与 Prefect 兼容，不使用
+
+    Usage:
+        @scan_task(retries=3, retry_delay=2.0)
+        def run_scan_tool(command: str, timeout: int):
+            ...
+    """
+    def decorator(func: Callable) -> Callable:
+        task_name = name or func.__name__
+
+        @functools.wraps(func)
+        def wrapper(*args, **kwargs) -> Any:
+            last_exception = None
+
+            for attempt in range(retries + 1):
+                try:
+                    return func(*args, **kwargs)
+                except Exception as e:
+                    last_exception = e
+                    if attempt < retries:
+                        logger.warning(
+                            "任务 %s 重试 %d/%d: %s",
+                            task_name, attempt + 1, retries, e
+                        )
+                        time.sleep(retry_delay)
+                    else:
+                        logger.error(
+                            "任务 %s 重试耗尽 (%d 次): %s",
+                            task_name, retries + 1, e
+                        )
+
+            # 重试耗尽，抛出最后一个异常
+            raise last_exception
+
+        # 添加 submit 方法以保持与 Prefect task.submit() 的兼容性
+        # 注意：这只是为了迁移过渡，最终应该使用 ThreadPoolExecutor
+        wrapper.fn = func
+
+        return wrapper
+    return decorator

backend/apps/scan/flows/directory_scan_flow.py

@@ -10,30 +10,31 @@
 - 配置由 YAML 解析
 """
 
-# Django 环境初始化（导入即生效）
-from apps.common.prefect_django_setup import setup_django_for_prefect
-
-from prefect import flow
-from prefect.task_runners import ThreadPoolTaskRunner
-
 import hashlib
 import logging
-import os
 import subprocess
 from datetime import datetime
 from pathlib import Path
 from typing import List, Tuple
 
-from apps.scan.tasks.directory_scan import (
+from concurrent.futures import ThreadPoolExecutor
-    export_sites_task,
+
-    run_and_stream_save_directories_task
+from apps.scan.decorators import scan_flow
-)
 from apps.scan.handlers.scan_flow_handlers import (
-    on_scan_flow_running,
     on_scan_flow_completed,
     on_scan_flow_failed,
+    on_scan_flow_running,
+)
+from apps.scan.tasks.directory_scan import (
+    export_sites_task,
+    run_and_stream_save_directories_task,
+)
+from apps.scan.utils import (
+    build_scan_command,
+    ensure_wordlist_local,
+    user_log,
+    wait_for_system_load,
 )
-from apps.scan.utils import config_parser, build_scan_command, ensure_wordlist_local
 
 logger = logging.getLogger(__name__)
 
@@ -45,130 +46,91 @@ def calculate_directory_scan_timeout(
     tool_config: dict,
     base_per_word: float = 1.0,
     min_timeout: int = 60,
-    max_timeout: int = 7200
 ) -> int:
     """
     根据字典行数计算目录扫描超时时间
 
     计算公式：超时时间 = 字典行数 × 每个单词基础时间
-    超时范围：60秒 ~ 2小时（7200秒）
+    超时范围：最小 60 秒，无上限
 
     Args:
         tool_config: 工具配置字典，包含 wordlist 路径
         base_per_word: 每个单词的基础时间（秒），默认 1.0秒
         min_timeout: 最小超时时间（秒），默认 60秒
-        max_timeout: 最大超时时间（秒），默认 7200秒（2小时）
 
     Returns:
-        int: 计算出的超时时间（秒），范围：60 ~ 7200
+        int: 计算出的超时时间（秒）
-    
-    Example:
-        # 1000行字典 × 1.0秒 = 1000秒 → 限制为7200秒中的 1000秒
-        # 10000行字典 × 1.0秒 = 10000秒 → 限制为7200秒（最大值）
-        timeout = calculate_directory_scan_timeout(
-            tool_config={'wordlist': '/path/to/wordlist.txt'}
-        )
     """
+    import os
+
+    wordlist_path = tool_config.get('wordlist')
+    if not wordlist_path:
+        logger.warning("工具配置中未指定 wordlist，使用默认超时: %d秒", min_timeout)
+        return min_timeout
+
+    wordlist_path = os.path.expanduser(wordlist_path)
+
+    if not os.path.exists(wordlist_path):
+        logger.warning("字典文件不存在: %s，使用默认超时: %d秒", wordlist_path, min_timeout)
+        return min_timeout
+
     try:
-        # 从 tool_config 中获取 wordlist 路径
-        wordlist_path = tool_config.get('wordlist')
-        if not wordlist_path:
-            logger.warning("工具配置中未指定 wordlist，使用默认超时: %d秒", min_timeout)
-            return min_timeout
-        
-        # 展开用户目录（~）
-        wordlist_path = os.path.expanduser(wordlist_path)
-        
-        # 检查文件是否存在
-        if not os.path.exists(wordlist_path):
-            logger.warning("字典文件不存在: %s，使用默认超时: %d秒", wordlist_path, min_timeout)
-            return min_timeout
-        
-        # 使用 wc -l 快速统计字典行数
         result = subprocess.run(
             ['wc', '-l', wordlist_path],
             capture_output=True,
             text=True,
             check=True
         )
-        # wc -l 输出格式：行数 + 空格 + 文件名
         line_count = int(result.stdout.strip().split()[0])
-        
+        timeout = max(min_timeout, int(line_count * base_per_word))
-        # 计算超时时间
-        timeout = int(line_count * base_per_word)
-        
-        # 设置合理的下限（不再设置上限）
-        timeout = max(min_timeout, timeout)
 
         logger.info(
             "目录扫描超时计算 - 字典: %s, 行数: %d, 基础时间: %.3f秒/词, 计算超时: %d秒",
             wordlist_path, line_count, base_per_word, timeout
         )
-        
         return timeout
 
-    except subprocess.CalledProcessError as e:
+    except (subprocess.CalledProcessError, ValueError, IndexError) as e:
-        logger.error("统计字典行数失败: %s", e)
+        logger.error("计算超时时间失败: %s", e)
-        # 失败时返回默认超时
-        return min_timeout
-    except (ValueError, IndexError) as e:
-        logger.error("解析字典行数失败: %s", e)
-        return min_timeout
-    except Exception as e:
-        logger.error("计算超时时间异常: %s", e)
         return min_timeout
 
 
 def _get_max_workers(tool_config: dict, default: int = DEFAULT_MAX_WORKERS) -> int:
-    """
+    """从单个工具配置中获取 max_workers 参数"""
-    从单个工具配置中获取 max_workers 参数
-    
-    Args:
-        tool_config: 单个工具的配置字典，如 {'max_workers': 10, 'threads': 5, ...}
-        default: 默认值，默认为 5
-        
-    Returns:
-        int: max_workers 值
-    """
     if not isinstance(tool_config, dict):
         return default
 
-    # 支持 max_workers 和 max-workers（YAML 中划线会被转换）
     max_workers = tool_config.get('max_workers') or tool_config.get('max-workers')
-    if max_workers is not None and isinstance(max_workers, int) and max_workers > 0:
+    if isinstance(max_workers, int) and max_workers > 0:
         return max_workers
     return default
 
 
-
+def _export_site_urls(
-
+    target_id: int,
-
+    directory_scan_dir: Path,
-def _export_site_urls(target_id: int, target_name: str, directory_scan_dir: Path) -> tuple[str, int]:
+    provider,
+) -> Tuple[str, int]:
     """
-    导出目标下的所有站点 URL 到文件（支持懒加载）
+    导出目标下的所有站点 URL 到文件
 
     Args:
         target_id: 目标 ID
-        target_name: 目标名称（用于懒加载创建默认站点）
         directory_scan_dir: 目录扫描目录
+        provider: TargetProvider 实例
 
     Returns:
         tuple: (sites_file, site_count)
-        
-    Raises:
-        ValueError: 站点数量为 0
     """
     logger.info("Step 1: 导出目标的所有站点 URL")
 
     sites_file = str(directory_scan_dir / 'sites.txt')
     export_result = export_sites_task(
-        target_id=target_id,
         output_file=sites_file,
-        batch_size=1000  # 每次读取 1000 条，优化内存占用
+        provider=provider,
     )
 
     site_count = export_result['total_count']
-    
     logger.info(
         "✓ 站点 URL 导出完成 - 文件: %s, 数量: %d",
         export_result['output_file'],
@@ -177,209 +139,142 @@ def _export_site_urls(target_id: int, target_name: str, directory_scan_dir: Path
 
     if site_count == 0:
         logger.warning("目标下没有站点，无法执行目录扫描")
-        # 不抛出异常，由上层决定如何处理
-        # raise ValueError("目标下没有站点，无法执行目录扫描")
 
     return export_result['output_file'], site_count
 
 
-def _run_scans_sequentially(
+def _generate_log_filename(
-    enabled_tools: dict,
+    tool_name: str,
-    sites_file: str,
+    site_url: str,
-    directory_scan_dir: Path,
+    directory_scan_dir: Path
-    scan_id: int,
+) -> Path:
-    target_id: int,
+    """生成唯一的日志文件名（使用 URL 的 hash 确保并发时不会冲突）"""
-    site_count: int,
+    url_hash = hashlib.md5(
-    target_name: str
+        site_url.encode(),
-) -> tuple[int, int, list]:
+        usedforsecurity=False
-    """
+    ).hexdigest()[:8]
-    串行执行目录扫描任务（支持多工具）- 已废弃，保留用于兼容
-    
-    Args:
-        enabled_tools: 启用的工具配置字典
-        sites_file: 站点文件路径
-        directory_scan_dir: 目录扫描目录
-        scan_id: 扫描任务 ID
-        target_id: 目标 ID
-        site_count: 站点数量
-        target_name: 目标名称（用于错误日志）
-        
-    Returns:
-        tuple: (total_directories, processed_sites, failed_sites)
-    """
-    # 读取站点列表
-    sites = []
-    with open(sites_file, 'r', encoding='utf-8') as f:
-        for line in f:
-            site_url = line.strip()
-            if site_url:
-                sites.append(site_url)
-    
-    logger.info("准备扫描 %d 个站点，使用工具: %s", len(sites), ', '.join(enabled_tools.keys()))
-    
-    total_directories = 0
-    processed_sites_set = set()  # 使用 set 避免重复计数
-    failed_sites = []
-    
-    # 遍历每个工具
-    for tool_name, tool_config in enabled_tools.items():
-        logger.info("="*60)
-        logger.info("使用工具: %s", tool_name)
-        logger.info("="*60)
-
-        # 如果配置了 wordlist_name，则先确保本地存在对应的字典文件（含 hash 校验）
-        wordlist_name = tool_config.get('wordlist_name')
-        if wordlist_name:
-            try:
-                local_wordlist_path = ensure_wordlist_local(wordlist_name)
-                tool_config['wordlist'] = local_wordlist_path
-            except Exception as exc:
-                logger.error("为工具 %s 准备字典失败: %s", tool_name, exc)
-                # 当前工具无法执行，将所有站点视为失败，继续下一个工具
-                failed_sites.extend(sites)
-                continue
-        
-        # 逐个站点执行扫描
-        for idx, site_url in enumerate(sites, 1):
-            logger.info(
-                "[%d/%d] 开始扫描站点: %s (工具: %s)",
-                idx, len(sites), site_url, tool_name
-            )
-            
-            # 使用统一的命令构建器
-            try:
-                command = build_scan_command(
-                    tool_name=tool_name,
-                    scan_type='directory_scan',
-                    command_params={
-                        'url': site_url
-                    },
-                    tool_config=tool_config
-                )
-            except Exception as e:
-                logger.error(
-                    "✗ [%d/%d] 构建 %s 命令失败: %s - 站点: %s",
-                    idx, len(sites), tool_name, e, site_url
-                )
-                failed_sites.append(site_url)
-                continue
-            
-            # 单个站点超时：从配置中获取（支持 'auto' 动态计算）
-            # ffuf 逐个站点扫描，timeout 就是单个站点的超时时间
-            site_timeout = tool_config.get('timeout', 300)
-            if site_timeout == 'auto':
-                # 动态计算超时时间（基于字典行数）
-                site_timeout = calculate_directory_scan_timeout(tool_config)
-                logger.info(f"✓ 工具 {tool_name} 动态计算 timeout: {site_timeout}秒")
-            
-            # 生成日志文件路径
-            from datetime import datetime
-            timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
-            log_file = directory_scan_dir / f"{tool_name}_{timestamp}_{idx}.log"
-            
-            try:
-                # 直接调用 task（串行执行）
-                result = run_and_stream_save_directories_task(
-                    cmd=command,
-                    tool_name=tool_name,  # 新增：工具名称
-                    scan_id=scan_id,
-                    target_id=target_id,
-                    site_url=site_url,
-                    cwd=str(directory_scan_dir),
-                    shell=True,
-                    batch_size=1000,
-                    timeout=site_timeout,
-                    log_file=str(log_file)  # 新增：日志文件路径
-                )
-                
-                total_directories += result.get('created_directories', 0)
-                processed_sites_set.add(site_url)  # 使用 set 记录成功的站点
-                
-                logger.info(
-                    "✓ [%d/%d] 站点扫描完成: %s - 发现 %d 个目录",
-                    idx, len(sites), site_url,
-                    result.get('created_directories', 0)
-                )
-                
-            except subprocess.TimeoutExpired as exc:
-                # 超时异常单独处理
-                failed_sites.append(site_url)
-                logger.warning(
-                    "⚠️ [%d/%d] 站点扫描超时: %s - 超时配置: %d秒\n"
-                    "注意：超时前已解析的目录数据已保存到数据库，但扫描未完全完成。",
-                    idx, len(sites), site_url, site_timeout
-                )
-            except Exception as exc:
-                # 其他异常
-                failed_sites.append(site_url)
-                logger.error(
-                    "✗ [%d/%d] 站点扫描失败: %s - 错误: %s",
-                    idx, len(sites), site_url, exc
-                )
-            
-            # 每 10 个站点输出进度
-            if idx % 10 == 0:
-                logger.info(
-                    "进度: %d/%d (%.1f%%) - 已发现 %d 个目录",
-                    idx, len(sites), idx/len(sites)*100, total_directories
-                )
-    
-    # 计算成功和失败的站点数
-    processed_count = len(processed_sites_set)
-    
-    if failed_sites:
-        logger.warning(
-            "部分站点扫描失败: %d/%d",
-            len(failed_sites), len(sites)
-        )
-    
-    logger.info(
-        "✓ 串行目录扫描执行完成 - 成功: %d/%d, 失败: %d, 总目录数: %d",
-        processed_count, len(sites), len(failed_sites), total_directories
-    )
-    
-    return total_directories, processed_count, failed_sites
-
-
-def _generate_log_filename(tool_name: str, site_url: str, directory_scan_dir: Path) -> Path:
-    """
-    生成唯一的日志文件名
-    
-    使用 URL 的 hash 确保并发时不会冲突
-    
-    Args:
-        tool_name: 工具名称
-        site_url: 站点 URL
-        directory_scan_dir: 目录扫描目录
-        
-    Returns:
-        Path: 日志文件路径
-    """
-    url_hash = hashlib.md5(site_url.encode()).hexdigest()[:8]
     timestamp = datetime.now().strftime('%Y%m%d_%H%M%S_%f')
     return directory_scan_dir / f"{tool_name}_{url_hash}_{timestamp}.log"
 
 
+def _prepare_tool_wordlist(tool_name: str, tool_config: dict) -> bool:
+    """准备工具的字典文件，返回是否成功"""
+    wordlist_name = tool_config.get('wordlist_name')
+    if not wordlist_name:
+        return True
+
+    try:
+        local_wordlist_path = ensure_wordlist_local(wordlist_name)
+        tool_config['wordlist'] = local_wordlist_path
+        return True
+    except Exception as exc:
+        logger.error("为工具 %s 准备字典失败: %s", tool_name, exc)
+        return False
+
+
+def _build_scan_params(
+    tool_name: str,
+    tool_config: dict,
+    sites: List[str],
+    directory_scan_dir: Path,
+    site_timeout: int
+) -> Tuple[List[dict], List[str]]:
+    """构建所有站点的扫描参数，返回 (scan_params_list, failed_sites)"""
+    scan_params_list = []
+    failed_sites = []
+
+    for idx, site_url in enumerate(sites, 1):
+        try:
+            command = build_scan_command(
+                tool_name=tool_name,
+                scan_type='directory_scan',
+                command_params={'url': site_url},
+                tool_config=tool_config
+            )
+            log_file = _generate_log_filename(tool_name, site_url, directory_scan_dir)
+            scan_params_list.append({
+                'idx': idx,
+                'site_url': site_url,
+                'command': command,
+                'log_file': str(log_file),
+                'timeout': site_timeout
+            })
+        except Exception as e:
+            logger.error(
+                "✗ [%d/%d] 构建 %s 命令失败: %s - 站点: %s",
+                idx, len(sites), tool_name, e, site_url
+            )
+            failed_sites.append(site_url)
+
+    return scan_params_list, failed_sites
+
+
+def _execute_batch(
+    batch_params: List[dict],
+    tool_name: str,
+    scan_id: int,
+    target_id: int,
+    directory_scan_dir: Path,
+    total_sites: int
+) -> Tuple[int, List[str]]:
+    """执行一批扫描任务，返回 (directories_found, failed_sites)"""
+    directories_found = 0
+    failed_sites = []
+
+    # 使用 ThreadPoolExecutor 并行执行
+    with ThreadPoolExecutor(max_workers=len(batch_params)) as executor:
+        futures = []
+        for params in batch_params:
+            future = executor.submit(
+                run_and_stream_save_directories_task,
+                cmd=params['command'],
+                tool_name=tool_name,
+                scan_id=scan_id,
+                target_id=target_id,
+                site_url=params['site_url'],
+                cwd=str(directory_scan_dir),
+                shell=True,
+                batch_size=1000,
+                timeout=params['timeout'],
+                log_file=params['log_file']
+            )
+            futures.append((params['idx'], params['site_url'], future))
+
+        # 等待结果
+        for idx, site_url, future in futures:
+            try:
+                result = future.result()
+                dirs_count = result.get('created_directories', 0)
+                directories_found += dirs_count
+                logger.info(
+                    "✓ [%d/%d] 站点扫描完成: %s - 发现 %d 个目录",
+                    idx, total_sites, site_url, dirs_count
+                )
+            except Exception as exc:
+                failed_sites.append(site_url)
+                if 'timeout' in str(exc).lower():
+                    logger.warning(
+                        "⚠️ [%d/%d] 站点扫描超时: %s - 错误: %s",
+                        idx, total_sites, site_url, exc
+                    )
+                else:
+                    logger.error(
+                        "✗ [%d/%d] 站点扫描失败: %s - 错误: %s",
+                        idx, total_sites, site_url, exc
+                    )
+
+    return directories_found, failed_sites
+
+
 def _run_scans_concurrently(
     enabled_tools: dict,
     sites_file: str,
     directory_scan_dir: Path,
     scan_id: int,
     target_id: int,
-    site_count: int,
-    target_name: str
 ) -> Tuple[int, int, List[str]]:
     """
-    并发执行目录扫描任务（使用 ThreadPoolTaskRunner）
+    并发执行目录扫描任务
-    
-    Args:
-        enabled_tools: 启用的工具配置字典
-        sites_file: 站点文件路径
-        directory_scan_dir: 目录扫描目录
-        scan_id: 扫描任务 ID
-        target_id: 目标 ID
-        site_count: 站点数量
-        target_name: 目标名称（用于错误日志）
 
     Returns:
         tuple: (total_directories, processed_sites, failed_sites)
@@ -387,10 +282,7 @@ def _run_scans_concurrently(
     # 读取站点列表
     sites: List[str] = []
     with open(sites_file, 'r', encoding='utf-8') as f:
-        for line in f:
+        sites = [line.strip() for line in f if line.strip()]
-            site_url = line.strip()
-            if site_url:
-                sites.append(site_url)
 
     if not sites:
         logger.warning("站点列表为空")
@@ -405,125 +297,84 @@ def _run_scans_concurrently(
     processed_sites_count = 0
     failed_sites: List[str] = []
 
-    # 遍历每个工具
     for tool_name, tool_config in enabled_tools.items():
-        # 每个工具独立获取 max_workers 配置
         max_workers = _get_max_workers(tool_config)
 
-        logger.info("="*60)
+        logger.info("=" * 60)
         logger.info("使用工具: %s (并发模式, max_workers=%d)", tool_name, max_workers)
-        logger.info("="*60)
+        logger.info("=" * 60)
+        user_log(scan_id, "directory_scan", f"Running {tool_name}")
 
-        # 如果配置了 wordlist_name，则先确保本地存在对应的字典文件（含 hash 校验）
+        # 准备字典文件
-        wordlist_name = tool_config.get('wordlist_name')
+        if not _prepare_tool_wordlist(tool_name, tool_config):
-        if wordlist_name:
+            failed_sites.extend(sites)
-            try:
+            continue
-                local_wordlist_path = ensure_wordlist_local(wordlist_name)
-                tool_config['wordlist'] = local_wordlist_path
-            except Exception as exc:
-                logger.error("为工具 %s 准备字典失败: %s", tool_name, exc)
-                # 当前工具无法执行，将所有站点视为失败，继续下一个工具
-                failed_sites.extend(sites)
-                continue
 
-        # 计算超时时间（所有站点共用）
+        # 计算超时时间
         site_timeout = tool_config.get('timeout', 300)
         if site_timeout == 'auto':
             site_timeout = calculate_directory_scan_timeout(tool_config)
-            logger.info(f"✓ 工具 {tool_name} 动态计算 timeout: {site_timeout}秒")
+            logger.info("✓ 工具 %s 动态计算 timeout: %d秒", tool_name, site_timeout)
 
-        # 准备所有站点的扫描参数
+        # 构建扫描参数
-        scan_params_list = []
+        scan_params_list, build_failed = _build_scan_params(
-        for idx, site_url in enumerate(sites, 1):
+            tool_name, tool_config, sites, directory_scan_dir, site_timeout
-            try:
+        )
-                command = build_scan_command(
+        failed_sites.extend(build_failed)
-                    tool_name=tool_name,
-                    scan_type='directory_scan',
-                    command_params={'url': site_url},
-                    tool_config=tool_config
-                )
-                log_file = _generate_log_filename(tool_name, site_url, directory_scan_dir)
-                scan_params_list.append({
-                    'idx': idx,
-                    'site_url': site_url,
-                    'command': command,
-                    'log_file': str(log_file),
-                    'timeout': site_timeout
-                })
-            except Exception as e:
-                logger.error(
-                    "✗ [%d/%d] 构建 %s 命令失败: %s - 站点: %s",
-                    idx, len(sites), tool_name, e, site_url
-                )
-                failed_sites.append(site_url)
 
         if not scan_params_list:
             logger.warning("没有有效的扫描任务")
             continue
 
-        # ============================================================
+        # 分批执行
-        # 分批执行策略：控制实际并发的 ffuf 进程数
-        # ============================================================
         total_tasks = len(scan_params_list)
         logger.info("开始分批执行 %d 个扫描任务（每批 %d 个）...", total_tasks, max_workers)
 
-        batch_num = 0
+        last_progress_percent = 0
+        tool_directories = 0
+        tool_processed = 0
+
         for batch_start in range(0, total_tasks, max_workers):
             batch_end = min(batch_start + max_workers, total_tasks)
             batch_params = scan_params_list[batch_start:batch_end]
-            batch_num += 1
+            batch_num = batch_start // max_workers + 1
 
-            logger.info("执行第 %d 批任务（%d-%d/%d）...", batch_num, batch_start + 1, batch_end, total_tasks)
+            logger.info(
+                "执行第 %d 批任务（%d-%d/%d）...",
+                batch_num, batch_start + 1, batch_end, total_tasks
+            )
 
-            # 提交当前批次的任务（非阻塞，立即返回 future）
+            dirs_found, batch_failed = _execute_batch(
-            futures = []
+                batch_params, tool_name, scan_id, target_id,
-            for params in batch_params:
+                directory_scan_dir, len(sites)
-                future = run_and_stream_save_directories_task.submit(
+            )
-                    cmd=params['command'],
+
-                    tool_name=tool_name,
+            total_directories += dirs_found
-                    scan_id=scan_id,
+            tool_directories += dirs_found
-                    target_id=target_id,
+            tool_processed += len(batch_params) - len(batch_failed)
-                    site_url=params['site_url'],
+            processed_sites_count += len(batch_params) - len(batch_failed)
-                    cwd=str(directory_scan_dir),
+            failed_sites.extend(batch_failed)
-                    shell=True,
+
-                    batch_size=1000,
+            # 进度里程碑：每 20% 输出一次
-                    timeout=params['timeout'],
+            current_progress = int((batch_end / total_tasks) * 100)
-                    log_file=params['log_file']
+            if current_progress >= last_progress_percent + 20:
+                user_log(
+                    scan_id, "directory_scan",
+                    f"Progress: {batch_end}/{total_tasks} sites scanned"
                 )
-                futures.append((params['idx'], params['site_url'], future))
+                last_progress_percent = (current_progress // 20) * 20
 
-            # 等待当前批次所有任务完成（阻塞，确保本批完成后再启动下一批）
+        logger.info(
-            for idx, site_url, future in futures:
+            "✓ 工具 %s 执行完成 - 已处理站点: %d/%d, 发现目录: %d",
-                try:
+            tool_name, tool_processed, total_tasks, tool_directories
-                    result = future.result()  # 阻塞等待单个任务完成
-                    directories_found = result.get('created_directories', 0)
-                    total_directories += directories_found
-                    processed_sites_count += 1
-                    
-                    logger.info(
-                        "✓ [%d/%d] 站点扫描完成: %s - 发现 %d 个目录",
-                        idx, len(sites), site_url, directories_found
-                    )
-                    
-                except Exception as exc:
-                    failed_sites.append(site_url)
-                    if 'timeout' in str(exc).lower() or isinstance(exc, subprocess.TimeoutExpired):
-                        logger.warning(
-                            "⚠️ [%d/%d] 站点扫描超时: %s - 错误: %s",
-                            idx, len(sites), site_url, exc
-                        )
-                    else:
-                        logger.error(
-                            "✗ [%d/%d] 站点扫描失败: %s - 错误: %s",
-                            idx, len(sites), site_url, exc
-                        )
-    
-    # 输出汇总信息
-    if failed_sites:
-        logger.warning(
-            "部分站点扫描失败: %d/%d",
-            len(failed_sites), len(sites)
         )
+        user_log(
+            scan_id, "directory_scan",
+            f"{tool_name} completed: found {tool_directories} directories"
+        )
+
+    if failed_sites:
+        logger.warning("部分站点扫描失败: %d/%d", len(failed_sites), len(sites))
 
     logger.info(
         "✓ 并发目录扫描执行完成 - 成功: %d/%d, 失败: %d, 总目录数: %d",
@@ -533,19 +384,18 @@ def _run_scans_concurrently(
     return total_directories, processed_sites_count, failed_sites
 
 
-@flow(
+@scan_flow(
     name="directory_scan",
-    log_prints=True,
     on_running=[on_scan_flow_running],
     on_completion=[on_scan_flow_completed],
     on_failure=[on_scan_flow_failed],
 )
 def directory_scan_flow(
     scan_id: int,
-    target_name: str,
     target_id: int,
     scan_workspace_dir: str,
-    enabled_tools: dict
+    enabled_tools: dict,
+    provider,
 ) -> dict:
     """
     目录扫描 Flow
@@ -555,61 +405,33 @@ def directory_scan_flow(
         2. 对每个站点 URL 执行目录扫描（支持 ffuf 等工具）
         3. 流式保存扫描结果到数据库 Directory 表
 
-    工作流程：
-        Step 0: 创建工作目录
-        Step 1: 导出站点 URL 列表到文件（供扫描工具使用）
-        Step 2: 验证工具配置
-        Step 3: 并发执行扫描工具并实时保存结果（使用 ThreadPoolTaskRunner）
-    
-    ffuf 输出字段：
-        - url: 发现的目录/文件 URL
-        - length: 响应内容长度
-        - status: HTTP 状态码
-        - words: 响应内容单词数
-        - lines: 响应内容行数
-        - content_type: 内容类型
-        - duration: 请求耗时
-    
     Args:
         scan_id: 扫描任务 ID
-        target_name: 目标名称
         target_id: 目标 ID
         scan_workspace_dir: 扫描工作空间目录
         enabled_tools: 启用的工具配置字典
+        provider: TargetProvider 实例
 
     Returns:
-        dict: {
+        dict: 扫描结果
-            'success': bool,
-            'scan_id': int,
-            'target': str,
-            'scan_workspace_dir': str,
-            'sites_file': str,
-            'site_count': int,
-            'total_directories': int,  # 发现的总目录数
-            'processed_sites': int,  # 成功处理的站点数
-            'failed_sites_count': int,  # 失败的站点数
-            'executed_tasks': list
-        }
-    
-    Raises:
-        ValueError: 参数错误
-        RuntimeError: 执行失败
     """
     try:
+        wait_for_system_load(context="directory_scan_flow")
+
+        # 从 provider 获取 target_name
+        target_name = provider.get_target_name()
+        if not target_name:
+            raise ValueError("无法获取 Target 名称")
+
         logger.info(
-            "="*60 + "\n" +
+            "开始目录扫描 - Scan ID: %s, Target: %s, Workspace: %s",
-            "开始目录扫描\n" +
+            scan_id, target_name, scan_workspace_dir
-            f"  Scan ID: {scan_id}\n" +
-            f"  Target: {target_name}\n" +
-            f"  Workspace: {scan_workspace_dir}\n" +
-            "="*60
         )
+        user_log(scan_id, "directory_scan", "Starting directory scan")
 
         # 参数验证
         if scan_id is None:
             raise ValueError("scan_id 不能为空")
-        if not target_name:
-            raise ValueError("target_name 不能为空")
         if target_id is None:
             raise ValueError("target_id 不能为空")
         if not scan_workspace_dir:
@@ -621,11 +443,14 @@ def directory_scan_flow(
         from apps.scan.utils import setup_scan_directory
         directory_scan_dir = setup_scan_directory(scan_workspace_dir, 'directory_scan')
 
-        # Step 1: 导出站点 URL（支持懒加载）
+        # Step 1: 导出站点 URL
-        sites_file, site_count = _export_site_urls(target_id, target_name, directory_scan_dir)
+        sites_file, site_count = _export_site_urls(
+            target_id, directory_scan_dir, provider
+        )
 
         if site_count == 0:
-            logger.warning("目标下没有站点，跳过目录扫描")
+            logger.warning("跳过目录扫描：没有站点可扫描 - Scan ID: %s", scan_id)
+            user_log(scan_id, "directory_scan", "Skipped: no sites to scan", "warning")
             return {
                 'success': True,
                 'scan_id': scan_id,
@@ -641,13 +466,13 @@ def directory_scan_flow(
 
         # Step 2: 工具配置信息
         logger.info("Step 2: 工具配置信息")
-        tool_info = []
+        tool_info = [
-        for tool_name, tool_config in enabled_tools.items():
+            f"{name}(max_workers={_get_max_workers(cfg)})"
-            mw = _get_max_workers(tool_config)
+            for name, cfg in enabled_tools.items()
-            tool_info.append(f"{tool_name}(max_workers={mw})")
+        ]
         logger.info("✓ 启用工具: %s", ', '.join(tool_info))
 
-        # Step 3: 并发执行扫描工具并实时保存结果
+        # Step 3: 并发执行扫描
         logger.info("Step 3: 并发执行扫描工具并实时保存结果")
         total_directories, processed_sites, failed_sites = _run_scans_concurrently(
             enabled_tools=enabled_tools,
@@ -655,16 +480,19 @@ def directory_scan_flow(
             directory_scan_dir=directory_scan_dir,
             scan_id=scan_id,
             target_id=target_id,
-            site_count=site_count,
-            target_name=target_name
         )
 
-        # 检查是否所有站点都失败
         if processed_sites == 0 and site_count > 0:
-            logger.warning("所有站点扫描均失败 - 总站点数: %d, 失败数: %d", site_count, len(failed_sites))
+            logger.warning(
-            # 不抛出异常，让扫描继续
+                "所有站点扫描均失败 - 总站点数: %d, 失败数: %d",
+                site_count, len(failed_sites)
+            )
 
-        logger.info("="*60 + "\n✓ 目录扫描完成\n" + "="*60)
+        logger.info("✓ 目录扫描完成 - 发现目录: %d", total_directories)
+        user_log(
+            scan_id, "directory_scan",
+            f"directory_scan completed: found {total_directories} directories"
+        )
 
         return {
             'success': True,

backend/apps/scan/flows/fingerprint_detect_flow.py

@@ -10,201 +10,160 @@
 - 流式处理输出，批量更新数据库
 """
 
-# Django 环境初始化（导入即生效）
-from apps.common.prefect_django_setup import setup_django_for_prefect
-
 import logging
-import os
+from dataclasses import dataclass
 from datetime import datetime
 from pathlib import Path
+from typing import Optional
 
-from prefect import flow
+from apps.scan.decorators import scan_flow
-
 from apps.scan.handlers.scan_flow_handlers import (
-    on_scan_flow_running,
     on_scan_flow_completed,
     on_scan_flow_failed,
+    on_scan_flow_running,
 )
 from apps.scan.tasks.fingerprint_detect import (
-    export_urls_for_fingerprint_task,
+    export_site_urls_for_fingerprint_task,
     run_xingfinger_and_stream_update_tech_task,
 )
-from apps.scan.utils import build_scan_command
+from apps.scan.utils import build_scan_command, setup_scan_directory, user_log, wait_for_system_load
 from apps.scan.utils.fingerprint_helpers import get_fingerprint_paths
 
 logger = logging.getLogger(__name__)
 
 
+@dataclass
+class FingerprintContext:
+    """指纹识别上下文，用于在各函数间传递状态"""
+    scan_id: int
+    target_id: int
+    target_name: str
+    scan_workspace_dir: str
+    fingerprint_dir: Optional[Path] = None
+    urls_file: str = ""
+    url_count: int = 0
+    source: str = "website"
+
+
 def calculate_fingerprint_detect_timeout(
     url_count: int,
-    base_per_url: float = 3.0,
+    base_per_url: float = 10.0,
-    min_timeout: int = 60
+    min_timeout: int = 300
 ) -> int:
-    """
+    """根据 URL 数量计算超时时间（最小 300 秒）"""
-    根据 URL 数量计算超时时间
+    return max(min_timeout, int(url_count * base_per_url))
-    
-    公式：超时时间 = URL 数量 × 每 URL 基础时间
-    最小值：60秒
-    无上限
-    
-    Args:
-        url_count: URL 数量
-        base_per_url: 每 URL 基础时间（秒），默认 3秒
-        min_timeout: 最小超时时间（秒），默认 60秒
-        
-    Returns:
-        int: 计算出的超时时间（秒）
-        
-    示例：
-        100 URL × 3秒 = 300秒
-        1000 URL × 3秒 = 3000秒（50分钟）
-        10000 URL × 3秒 = 30000秒（8.3小时）
-    """
-    timeout = int(url_count * base_per_url)
-    return max(min_timeout, timeout)
 
 
 
-
+def _export_urls(fingerprint_dir: Path, provider) -> tuple[str, int]:
-
+    """导出 URL 到文件，返回 (urls_file, total_count)"""
-def _export_urls(
+    logger.info("Step 1: 导出 URL 列表")
-    target_id: int,
-    fingerprint_dir: Path,
-    source: str = 'website'
-) -> tuple[str, int]:
-    """
-    导出 URL 到文件
-    
-    Args:
-        target_id: 目标 ID
-        fingerprint_dir: 指纹识别目录
-        source: 数据源类型
-        
-    Returns:
-        tuple: (urls_file, total_count)
-    """
-    logger.info("Step 1: 导出 URL 列表 (source=%s)", source)
 
     urls_file = str(fingerprint_dir / 'urls.txt')
-    export_result = export_urls_for_fingerprint_task(
+    export_result = export_site_urls_for_fingerprint_task(
-        target_id=target_id,
         output_file=urls_file,
-        source=source,
+        provider=provider,
-        batch_size=1000
     )
 
     total_count = export_result['total_count']
-    
+    logger.info("✓ URL 导出完成 - 文件: %s, 数量: %d", export_result['output_file'], total_count)
-    logger.info(
-        "✓ URL 导出完成 - 文件: %s, 数量: %d",
-        export_result['output_file'],
-        total_count
-    )
 
     return export_result['output_file'], total_count
 
 
-def _run_fingerprint_detect(
+def _run_single_tool(
-    enabled_tools: dict,
+    tool_name: str,
-    urls_file: str,
+    tool_config: dict,
-    url_count: int,
+    ctx: FingerprintContext
-    fingerprint_dir: Path,
+) -> tuple[Optional[dict], Optional[dict]]:
-    scan_id: int,
+    """执行单个指纹识别工具，返回 (stats, failed_info)"""
-    target_id: int,
+    # 获取指纹库路径
-    source: str
+    lib_names = tool_config.get('fingerprint_libs', ['ehole'])
-) -> tuple[dict, list]:
+    fingerprint_paths = get_fingerprint_paths(lib_names)
-    """
-    执行指纹识别任务
 
-    Args:
+    if not fingerprint_paths:
-        enabled_tools: 已启用的工具配置字典
+        reason = f"没有可用的指纹库: {lib_names}"
-        urls_file: URL 文件路径
+        logger.warning(reason)
-        url_count: URL 总数
+        return None, {'tool': tool_name, 'reason': reason}
-        fingerprint_dir: 指纹识别目录
-        scan_id: 扫描任务 ID
-        target_id: 目标 ID
-        source: 数据源类型
 
-    Returns:
+    # 构建命令
-        tuple: (tool_stats, failed_tools)
+    tool_config_with_paths = {**tool_config, **fingerprint_paths}
-    """
+    try:
+        command = build_scan_command(
+            tool_name=tool_name,
+            scan_type='fingerprint_detect',
+            command_params={'urls_file': ctx.urls_file},
+            tool_config=tool_config_with_paths
+        )
+    except Exception as e:
+        reason = f"命令构建失败: {e}"
+        logger.error("构建 %s 命令失败: %s", tool_name, e)
+        return None, {'tool': tool_name, 'reason': reason}
+
+    # 计算超时时间和日志文件
+    timeout = calculate_fingerprint_detect_timeout(ctx.url_count)
+    timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
+    log_file = ctx.fingerprint_dir / f"{tool_name}_{timestamp}.log"
+
+    logger.info(
+        "开始执行 %s 指纹识别 - URL数: %d, 超时: %ds, 指纹库: %s",
+        tool_name, ctx.url_count, timeout, list(fingerprint_paths.keys())
+    )
+    user_log(ctx.scan_id, "fingerprint_detect", f"Running {tool_name}: {command}")
+
+    # 执行扫描任务
+    try:
+        result = run_xingfinger_and_stream_update_tech_task(
+            cmd=command,
+            tool_name=tool_name,
+            scan_id=ctx.scan_id,
+            target_id=ctx.target_id,
+            source=ctx.source,
+            cwd=str(ctx.fingerprint_dir),
+            timeout=timeout,
+            log_file=str(log_file),
+            batch_size=100
+        )
+
+        stats = {
+            'command': command,
+            'result': result,
+            'timeout': timeout,
+            'fingerprint_libs': list(fingerprint_paths.keys())
+        }
+
+        tool_updated = result.get('updated_count', 0)
+        logger.info(
+            "✓ 工具 %s 执行完成 - 处理记录: %d, 更新: %d, 未找到: %d",
+            tool_name,
+            result.get('processed_records', 0),
+            tool_updated,
+            result.get('not_found_count', 0)
+        )
+        user_log(
+            ctx.scan_id, "fingerprint_detect",
+            f"{tool_name} completed: identified {tool_updated} fingerprints"
+        )
+        return stats, None
+
+    except Exception as exc:
+        reason = str(exc)
+        logger.error("工具 %s 执行失败: %s", tool_name, exc, exc_info=True)
+        user_log(ctx.scan_id, "fingerprint_detect", f"{tool_name} failed: {reason}", "error")
+        return None, {'tool': tool_name, 'reason': reason}
+
+
+def _run_fingerprint_detect(enabled_tools: dict, ctx: FingerprintContext) -> tuple[dict, list]:
+    """执行指纹识别任务，返回 (tool_stats, failed_tools)"""
     tool_stats = {}
     failed_tools = []
 
     for tool_name, tool_config in enabled_tools.items():
-        # 1. 获取指纹库路径
+        stats, failed_info = _run_single_tool(tool_name, tool_config, ctx)
-        lib_names = tool_config.get('fingerprint_libs', ['ehole'])
+        if stats:
-        fingerprint_paths = get_fingerprint_paths(lib_names)
+            tool_stats[tool_name] = stats
-        
+        if failed_info:
-        if not fingerprint_paths:
+            failed_tools.append(failed_info)
-            reason = f"没有可用的指纹库: {lib_names}"
-            logger.warning(reason)
-            failed_tools.append({'tool': tool_name, 'reason': reason})
-            continue
-        
-        # 2. 将指纹库路径合并到 tool_config（用于命令构建）
-        tool_config_with_paths = {**tool_config, **fingerprint_paths}
-        
-        # 3. 构建命令
-        try:
-            command = build_scan_command(
-                tool_name=tool_name,
-                scan_type='fingerprint_detect',
-                command_params={
-                    'urls_file': urls_file
-                },
-                tool_config=tool_config_with_paths
-            )
-        except Exception as e:
-            reason = f"命令构建失败: {str(e)}"
-            logger.error("构建 %s 命令失败: %s", tool_name, e)
-            failed_tools.append({'tool': tool_name, 'reason': reason})
-            continue
-        
-        # 4. 计算超时时间
-        timeout = calculate_fingerprint_detect_timeout(url_count)
-        
-        # 5. 生成日志文件路径
-        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
-        log_file = fingerprint_dir / f"{tool_name}_{timestamp}.log"
-        
-        logger.info(
-            "开始执行 %s 指纹识别 - URL数: %d, 超时: %ds, 指纹库: %s",
-            tool_name, url_count, timeout, list(fingerprint_paths.keys())
-        )
-        
-        # 6. 执行扫描任务
-        try:
-            result = run_xingfinger_and_stream_update_tech_task(
-                cmd=command,
-                tool_name=tool_name,
-                scan_id=scan_id,
-                target_id=target_id,
-                source=source,
-                cwd=str(fingerprint_dir),
-                timeout=timeout,
-                log_file=str(log_file),
-                batch_size=100
-            )
-            
-            tool_stats[tool_name] = {
-                'command': command,
-                'result': result,
-                'timeout': timeout,
-                'fingerprint_libs': list(fingerprint_paths.keys())
-            }
-            
-            logger.info(
-                "✓ 工具 %s 执行完成 - 处理记录: %d, 更新: %d, 未找到: %d",
-                tool_name,
-                result.get('processed_records', 0),
-                result.get('updated_count', 0),
-                result.get('not_found_count', 0)
-            )
-            
-        except Exception as exc:
-            failed_tools.append({'tool': tool_name, 'reason': str(exc)})
-            logger.error("工具 %s 执行失败: %s", tool_name, exc, exc_info=True)
 
     if failed_tools:
         logger.warning(
@@ -215,19 +174,36 @@ def _run_fingerprint_detect(
     return tool_stats, failed_tools
 
 
-@flow(
+def _aggregate_results(tool_stats: dict) -> dict:
+    """汇总所有工具的结果"""
+    return {
+        'processed_records': sum(
+            s['result'].get('processed_records', 0) for s in tool_stats.values()
+        ),
+        'updated_count': sum(
+            s['result'].get('updated_count', 0) for s in tool_stats.values()
+        ),
+        'created_count': sum(
+            s['result'].get('created_count', 0) for s in tool_stats.values()
+        ),
+        'snapshot_count': sum(
+            s['result'].get('snapshot_count', 0) for s in tool_stats.values()
+        ),
+    }
+
+
+@scan_flow(
     name="fingerprint_detect",
-    log_prints=True,
     on_running=[on_scan_flow_running],
     on_completion=[on_scan_flow_completed],
     on_failure=[on_scan_flow_failed],
 )
 def fingerprint_detect_flow(
     scan_id: int,
-    target_name: str,
     target_id: int,
     scan_workspace_dir: str,
-    enabled_tools: dict
+    enabled_tools: dict,
+    provider,
 ) -> dict:
     """
     指纹识别 Flow
@@ -236,87 +212,45 @@ def fingerprint_detect_flow(
         1. 从数据库导出目标下所有 WebSite URL 到文件
         2. 使用 xingfinger 进行技术栈识别
         3. 解析结果并更新 WebSite.tech 字段（合并去重）
-    
-    工作流程：
-        Step 0: 创建工作目录
-        Step 1: 导出 URL 列表
-        Step 2: 解析配置，获取启用的工具
-        Step 3: 执行 xingfinger 并解析结果
-    
-    Args:
-        scan_id: 扫描任务 ID
-        target_name: 目标名称
-        target_id: 目标 ID
-        scan_workspace_dir: 扫描工作空间目录
-        enabled_tools: 启用的工具配置（xingfinger）
-        
-    Returns:
-        dict: {
-            'success': bool,
-            'scan_id': int,
-            'target': str,
-            'scan_workspace_dir': str,
-            'urls_file': str,
-            'url_count': int,
-            'processed_records': int,
-            'updated_count': int,
-            'not_found_count': int,
-            'executed_tasks': list,
-            'tool_stats': dict
-        }
     """
     try:
-        logger.info(
+        wait_for_system_load(context="fingerprint_detect_flow")
-            "="*60 + "\n" +
+
-            "开始指纹识别\n" +
+        # 从 provider 获取 target_name
-            f"  Scan ID: {scan_id}\n" +
+        target_name = provider.get_target_name()
-            f"  Target: {target_name}\n" +
+        if not target_name:
-            f"  Workspace: {scan_workspace_dir}\n" +
+            raise ValueError("无法获取 Target 名称")
-            "="*60
-        )
 
         # 参数验证
         if scan_id is None:
             raise ValueError("scan_id 不能为空")
-        if not target_name:
-            raise ValueError("target_name 不能为空")
         if target_id is None:
             raise ValueError("target_id 不能为空")
         if not scan_workspace_dir:
             raise ValueError("scan_workspace_dir 不能为空")
 
-        # 数据源类型（当前只支持 website）
+        logger.info(
-        source = 'website'
+            "开始指纹识别 - Scan ID: %s, Target: %s, Workspace: %s",
+            scan_id, target_name, scan_workspace_dir
+        )
+        user_log(scan_id, "fingerprint_detect", "Starting fingerprint detection")
 
-        # Step 0: 创建工作目录
+        # 创建上下文
-        from apps.scan.utils import setup_scan_directory
+        ctx = FingerprintContext(
-        fingerprint_dir = setup_scan_directory(scan_workspace_dir, 'fingerprint_detect')
+            scan_id=scan_id,
+            target_id=target_id,
+            target_name=target_name,
+            scan_workspace_dir=scan_workspace_dir,
+            fingerprint_dir=setup_scan_directory(scan_workspace_dir, 'fingerprint_detect')
+        )
 
-        # Step 1: 导出 URL（支持懒加载）
+        # Step 1: 导出 URL
-        urls_file, url_count = _export_urls(target_id, fingerprint_dir, source)
+        ctx.urls_file, ctx.url_count = _export_urls(ctx.fingerprint_dir, provider)
 
-        if url_count == 0:
+        if ctx.url_count == 0:
-            logger.warning("目标下没有可用的 URL，跳过指纹识别")
+            logger.warning("跳过指纹识别：没有 URL 可扫描 - Scan ID: %s", scan_id)
-            return {
+            user_log(scan_id, "fingerprint_detect", "Skipped: no URLs to scan", "warning")
-                'success': True,
+            return _build_empty_result(scan_id, target_name, scan_workspace_dir, ctx.urls_file)
-                'scan_id': scan_id,
-                'target': target_name,
-                'scan_workspace_dir': scan_workspace_dir,
-                'urls_file': urls_file,
-                'url_count': 0,
-                'processed_records': 0,
-                'updated_count': 0,
-                'created_count': 0,
-                'executed_tasks': ['export_urls_for_fingerprint'],
-                'tool_stats': {
-                    'total': 0,
-                    'successful': 0,
-                    'failed': 0,
-                    'successful_tools': [],
-                    'failed_tools': [],
-                    'details': {}
-                }
-            }
 
         # Step 2: 工具配置信息
         logger.info("Step 2: 工具配置信息")
@@ -324,40 +258,30 @@ def fingerprint_detect_flow(
 
         # Step 3: 执行指纹识别
         logger.info("Step 3: 执行指纹识别")
-        tool_stats, failed_tools = _run_fingerprint_detect(
+        tool_stats, failed_tools = _run_fingerprint_detect(enabled_tools, ctx)
-            enabled_tools=enabled_tools,
+
-            urls_file=urls_file,
+        # 汇总结果
-            url_count=url_count,
+        totals = _aggregate_results(tool_stats)
-            fingerprint_dir=fingerprint_dir,
+        failed_tool_names = {f['tool'] for f in failed_tools}
-            scan_id=scan_id,
+        successful_tools = [name for name in enabled_tools if name not in failed_tool_names]
-            target_id=target_id,
+
-            source=source
+        logger.info("✓ 指纹识别完成 - 识别指纹: %d", totals['updated_count'])
+        user_log(
+            scan_id, "fingerprint_detect",
+            f"fingerprint_detect completed: identified {totals['updated_count']} fingerprints"
         )
 
-        logger.info("="*60 + "\n✓ 指纹识别完成\n" + "="*60)
+        executed_tasks = ['export_site_urls_for_fingerprint']
-        
+        executed_tasks.extend([f'run_xingfinger ({tool})' for tool in tool_stats])
-        # 动态生成已执行的任务列表
-        executed_tasks = ['export_urls_for_fingerprint']
-        executed_tasks.extend([f'run_xingfinger ({tool})' for tool in tool_stats.keys()])
-        
-        # 汇总所有工具的结果
-        total_processed = sum(stats['result'].get('processed_records', 0) for stats in tool_stats.values())
-        total_updated = sum(stats['result'].get('updated_count', 0) for stats in tool_stats.values())
-        total_created = sum(stats['result'].get('created_count', 0) for stats in tool_stats.values())
-        
-        successful_tools = [name for name in enabled_tools.keys() 
-                           if name not in [f['tool'] for f in failed_tools]]
 
         return {
             'success': True,
             'scan_id': scan_id,
             'target': target_name,
             'scan_workspace_dir': scan_workspace_dir,
-            'urls_file': urls_file,
+            'urls_file': ctx.urls_file,
-            'url_count': url_count,
+            'url_count': ctx.url_count,
-            'processed_records': total_processed,
+            **totals,
-            'updated_count': total_updated,
-            'created_count': total_created,
             'executed_tasks': executed_tasks,
             'tool_stats': {
                 'total': len(enabled_tools),
@@ -378,3 +302,33 @@ def fingerprint_detect_flow(
     except Exception as e:
         logger.exception("指纹识别失败: %s", e)
         raise
+
+
+def _build_empty_result(
+    scan_id: int,
+    target_name: str,
+    scan_workspace_dir: str,
+    urls_file: str
+) -> dict:
+    """构建空结果（无 URL 可扫描时）"""
+    return {
+        'success': True,
+        'scan_id': scan_id,
+        'target': target_name,
+        'scan_workspace_dir': scan_workspace_dir,
+        'urls_file': urls_file,
+        'url_count': 0,
+        'processed_records': 0,
+        'updated_count': 0,
+        'created_count': 0,
+        'snapshot_count': 0,
+        'executed_tasks': ['export_site_urls_for_fingerprint'],
+        'tool_stats': {
+            'total': 0,
+            'successful': 0,
+            'failed': 0,
+            'successful_tools': [],
+            'failed_tools': [],
+            'details': {}
+        }
+    }

backend/apps/scan/flows/initiate_scan_flow.py

@@ -5,12 +5,13 @@
 
 职责：
 - 使用 FlowOrchestrator 解析 YAML 配置
-- 在 Prefect Flow 中执行子 Flow（Subflow）
+- 执行子 Flow（Subflow）
 - 按照 YAML 顺序编排工作流
+- 根据 scan_mode 创建对应的 Provider
 - 不包含具体业务逻辑（由 Tasks 和 FlowOrchestrator 实现）
 
 架构：
-- Flow: Prefect 编排层（本文件）
+- Flow: 编排层（本文件）
 - FlowOrchestrator: 配置解析和执行计划（apps/scan/services/）
 - Tasks: 执行层（apps/scan/tasks/）
 - Handlers: 状态管理（apps/scan/handlers/）
@@ -18,46 +19,102 @@
 
 # Django 环境初始化（导入即生效）
 # 注意：动态扫描容器应使用 run_initiate_scan.py 启动，以便在导入前设置环境变量
-from apps.common.prefect_django_setup import setup_django_for_prefect
+import apps.common.django_setup  # noqa: F401
 
-from prefect import flow, task
-from pathlib import Path
 import logging
+from concurrent.futures import ThreadPoolExecutor
 
+from apps.scan.decorators import scan_flow
 from apps.scan.handlers import (
     on_initiate_scan_flow_running,
     on_initiate_scan_flow_completed,
     on_initiate_scan_flow_failed,
 )
-from prefect.futures import wait
-from apps.scan.utils import setup_scan_workspace
 from apps.scan.orchestrators import FlowOrchestrator
+from apps.scan.utils import setup_scan_workspace
 
 logger = logging.getLogger(__name__)
 
 
-@task(name="run_subflow")
+def _create_provider(scan, target_id: int, scan_id: int):
-def _run_subflow_task(scan_type: str, flow_func, flow_kwargs: dict):
+    """根据 scan_mode 创建对应的 Provider"""
-    """包装子 Flow 的 Task，用于在并行阶段并发执行子 Flow。"""
+    from apps.scan.models import Scan
-    logger.info("开始执行子 Flow: %s", scan_type)
+    from apps.scan.providers import (
-    return flow_func(**flow_kwargs)
+        DatabaseTargetProvider,
+        SnapshotTargetProvider,
+        ProviderContext,
+    )
+
+    provider_context = ProviderContext(target_id=target_id, scan_id=scan_id)
+
+    if scan.scan_mode == Scan.ScanMode.QUICK:
+        provider = SnapshotTargetProvider(scan_id=scan_id, context=provider_context)
+        logger.info("✓ 快速扫描模式 - 创建 SnapshotTargetProvider")
+    else:
+        provider = DatabaseTargetProvider(target_id=target_id, context=provider_context)
+        logger.info("✓ 完整扫描模式 - 使用 DatabaseTargetProvider")
+
+    return provider
 
 
-@flow(
+def _execute_sequential_flows(valid_flows: list, results: dict, executed_flows: list):
+    """顺序执行 Flow 列表"""
+    for scan_type, flow_func, flow_kwargs in valid_flows:
+        logger.info("=" * 60)
+        logger.info("执行 Flow: %s", scan_type)
+        logger.info("=" * 60)
+        try:
+            result = flow_func(**flow_kwargs)
+            executed_flows.append(scan_type)
+            results[scan_type] = result
+            logger.info("✓ %s 执行成功", scan_type)
+        except Exception as e:
+            logger.warning("%s 执行失败: %s", scan_type, e)
+            executed_flows.append(f"{scan_type} (失败)")
+            results[scan_type] = {'success': False, 'error': str(e)}
+
+
+def _execute_parallel_flows(valid_flows: list, results: dict, executed_flows: list):
+    """并行执行 Flow 列表（使用 ThreadPoolExecutor）"""
+    if not valid_flows:
+        return
+
+    logger.info("并行执行 %d 个 Flow", len(valid_flows))
+
+    with ThreadPoolExecutor(max_workers=len(valid_flows)) as executor:
+        futures = []
+        for scan_type, flow_func, flow_kwargs in valid_flows:
+            logger.info("=" * 60)
+            logger.info("提交并行子 Flow 任务: %s", scan_type)
+            logger.info("=" * 60)
+            future = executor.submit(flow_func, **flow_kwargs)
+            futures.append((scan_type, future))
+
+        # 收集结果
+        for scan_type, future in futures:
+            try:
+                result = future.result()
+                executed_flows.append(scan_type)
+                results[scan_type] = result
+                logger.info("✓ %s 执行成功", scan_type)
+            except Exception as e:
+                logger.warning("%s 执行失败: %s", scan_type, e)
+                executed_flows.append(f"{scan_type} (失败)")
+                results[scan_type] = {'success': False, 'error': str(e)}
+
+
+@scan_flow(
     name='initiate_scan',
-    description='扫描任务初始化流程',
-    log_prints=True,
     on_running=[on_initiate_scan_flow_running],
     on_completion=[on_initiate_scan_flow_completed],
     on_failure=[on_initiate_scan_flow_failed],
 )
 def initiate_scan_flow(
     scan_id: int,
-    target_name: str,
     target_id: int,
     scan_workspace_dir: str,
     engine_name: str,
-    scheduled_scan_name: str | None = None,
+    scheduled_scan_name: str | None = None,  # noqa: ARG001
 ) -> dict:
     """
     初始化扫描任务（动态工作流编排）
@@ -76,7 +133,6 @@ def initiate_scan_flow(
 
     Args:
         scan_id: 扫描任务 ID
-        target_name: 目标名称
         target_id: 目标 ID
         scan_workspace_dir: Scan 工作空间目录路径
         engine_name: 引擎名称（用于显示）
@@ -90,7 +146,7 @@ def initiate_scan_flow(
         RuntimeError: 执行失败
     """
     try:
-        # ==================== 参数验证 ====================
+        # 参数验证
         if not scan_id:
             raise ValueError("scan_id is required")
         if not scan_workspace_dir:
@@ -98,159 +154,88 @@ def initiate_scan_flow(
         if not engine_name:
             raise ValueError("engine_name is required")
 
-        
+        # 创建工作空间
-        logger.info(
-            "="*60 + "\n" +
-            "开始初始化扫描任务\n" +
-            f"  Scan ID: {scan_id}\n" +
-            f"  Target: {target_name}\n" +
-            f"  Engine: {engine_name}\n" +
-            f"  Workspace: {scan_workspace_dir}\n" +
-            "="*60
-        )
-        
-        # ==================== Task 1: 创建 Scan 工作空间 ====================
         scan_workspace_path = setup_scan_workspace(scan_workspace_dir)
 
-        # ==================== Task 2: 获取引擎配置 ====================
+        # 获取引擎配置
         from apps.scan.models import Scan
-        scan = Scan.objects.select_related('engine').get(id=scan_id)
+        scan = Scan.objects.get(id=scan_id)
-        engine_config = scan.engine.configuration
+        engine_config = scan.yaml_configuration
 
-        # ==================== Task 3: 解析配置，生成执行计划 ====================
+        # 创建 Provider
+        provider = _create_provider(scan, target_id, scan_id)
+
+        # 获取 target_name 用于日志显示
+        target_name = provider.get_target_name()
+        if not target_name:
+            raise ValueError("无法获取 Target 名称")
+
+        logger.info("=" * 60)
+        logger.info("开始初始化扫描任务")
+        logger.info("Scan ID: %s, Target: %s, Engine: %s", scan_id, target_name, engine_name)
+        logger.info("Workspace: %s", scan_workspace_dir)
+        logger.info("=" * 60)
+
+        # 解析配置，生成执行计划
         orchestrator = FlowOrchestrator(engine_config)
-        
-        # FlowOrchestrator 已经解析了所有工具配置
         enabled_tools_by_type = orchestrator.enabled_tools_by_type
 
-        logger.info(
+        logger.info("执行计划: %s (共 %d 个 Flow)",
-            f"执行计划生成成功：\n"
+                    ' → '.join(orchestrator.scan_types), len(orchestrator.scan_types))
-            f"  扫描类型: {' → '.join(orchestrator.scan_types)}\n"
-            f"  总共 {len(orchestrator.scan_types)} 个 Flow"
-        )
 
-        # ==================== 初始化阶段进度 ====================
+        # 初始化阶段进度
-        # 在解析完配置后立即初始化，此时已有完整的 scan_types 列表
         from apps.scan.services import ScanService
-        scan_service = ScanService()
+        ScanService().init_stage_progress(scan_id, orchestrator.scan_types)
-        scan_service.init_stage_progress(scan_id, orchestrator.scan_types)
+        logger.info("✓ 初始化阶段进度 - Stages: %s", orchestrator.scan_types)
-        logger.info(f"✓ 初始化阶段进度 - Stages: {orchestrator.scan_types}")
 
-        # ==================== 更新 Target 最后扫描时间 ====================
+        # 更新 Target 最后扫描时间
-        # 在开始扫描时更新，表示"最后一次扫描开始时间"
         from apps.targets.services import TargetService
-        target_service = TargetService()
+        TargetService().update_last_scanned_at(target_id)
-        target_service.update_last_scanned_at(target_id)
+        logger.info("✓ 更新 Target 最后扫描时间 - Target ID: %s", target_id)
-        logger.info(f"✓ 更新 Target 最后扫描时间 - Target ID: {target_id}")
 
-        # ==================== Task 3: 执行 Flow（动态阶段执行）====================
+        # 执行 Flow
-        # 注意：各阶段状态更新由 scan_flow_handlers.py 自动处理（running/completed/failed）
         executed_flows = []
         results = {}
-        
+        base_kwargs = {
-        # 通用执行参数
-        flow_kwargs = {
             'scan_id': scan_id,
-            'target_name': target_name,
             'target_id': target_id,
             'scan_workspace_dir': str(scan_workspace_path)
         }
 
-        def record_flow_result(scan_type, result=None, error=None):
+        def get_valid_flows(flow_names: list) -> list:
-            """
+            """获取有效的 Flow 函数列表"""
-            统一的结果记录函数
+            valid = []
-            
-            Args:
-                scan_type: 扫描类型名称
-                result: 执行结果（成功时）
-                error: 异常对象（失败时）
-            """
-            if error:
-                # 失败处理：记录错误但不抛出异常，让扫描继续执行后续阶段
-                error_msg = f"{scan_type} 执行失败: {str(error)}"
-                logger.warning(error_msg)
-                executed_flows.append(f"{scan_type} (失败)")
-                results[scan_type] = {'success': False, 'error': str(error)}
-                # 不再抛出异常，让扫描继续
-            else:
-                # 成功处理
-                executed_flows.append(scan_type)
-                results[scan_type] = result
-                logger.info(f"✓ {scan_type} 执行成功")
-
-        def get_valid_flows(flow_names):
-            """
-            获取有效的 Flow 函数列表，并为每个 Flow 准备专属参数
-            
-            Args:
-                flow_names: 扫描类型名称列表
-                
-            Returns:
-                list: [(scan_type, flow_func, flow_specific_kwargs), ...] 有效的函数列表
-            """
-            valid_flows = []
             for scan_type in flow_names:
                 flow_func = orchestrator.get_flow_function(scan_type)
-                if flow_func:
+                if not flow_func:
-                    # 为每个 Flow 准备专属的参数（包含对应的 enabled_tools）
+                    logger.warning("跳过未实现的 Flow: %s", scan_type)
-                    flow_specific_kwargs = dict(flow_kwargs)
+                    continue
-                    flow_specific_kwargs['enabled_tools'] = enabled_tools_by_type.get(scan_type, {})
+                kwargs = dict(base_kwargs)
-                    valid_flows.append((scan_type, flow_func, flow_specific_kwargs))
+                kwargs['enabled_tools'] = enabled_tools_by_type.get(scan_type, {})
-                else:
+                kwargs['provider'] = provider
-                    logger.warning(f"跳过未实现的 Flow: {scan_type}")
+                valid.append((scan_type, flow_func, kwargs))
-            return valid_flows
+            return valid
 
-        # ---------------------------------------------------------
+        # 动态阶段执行
-        # 动态阶段执行（基于 FlowOrchestrator 定义）
-        # ---------------------------------------------------------
         for mode, enabled_flows in orchestrator.get_execution_stages():
+            valid_flows = get_valid_flows(enabled_flows)
+            if not valid_flows:
+                continue
+
+            logger.info("=" * 60)
+            logger.info("%s执行阶段: %s", "顺序" if mode == 'sequential' else "并行",
+                        ', '.join(enabled_flows))
+            logger.info("=" * 60)
+
             if mode == 'sequential':
-                # 顺序执行
+                _execute_sequential_flows(valid_flows, results, executed_flows)
-                logger.info(f"\n{'='*60}\n顺序执行阶段: {', '.join(enabled_flows)}\n{'='*60}")
+            else:
-                for scan_type, flow_func, flow_specific_kwargs in get_valid_flows(enabled_flows):
+                _execute_parallel_flows(valid_flows, results, executed_flows)
-                    logger.info(f"\n{'='*60}\n执行 Flow: {scan_type}\n{'='*60}")
-                    try:
-                        result = flow_func(**flow_specific_kwargs)
-                        record_flow_result(scan_type, result=result)
-                    except Exception as e:
-                        record_flow_result(scan_type, error=e)
 
-            elif mode == 'parallel':
+        logger.info("=" * 60)
-                # 并行执行阶段：通过 Task 包装子 Flow，并使用 Prefect TaskRunner 并发运行
+        logger.info("✓ 扫描任务初始化完成 - 执行的 Flow: %s", ', '.join(executed_flows))
-                logger.info(f"\n{'='*60}\n并行执行阶段: {', '.join(enabled_flows)}\n{'='*60}")
+        logger.info("=" * 60)
-                futures = []
 
-                # 提交所有并行子 Flow 任务
-                for scan_type, flow_func, flow_specific_kwargs in get_valid_flows(enabled_flows):
-                    logger.info(f"\n{'='*60}\n提交并行子 Flow 任务: {scan_type}\n{'='*60}")
-                    future = _run_subflow_task.submit(
-                        scan_type=scan_type,
-                        flow_func=flow_func,
-                        flow_kwargs=flow_specific_kwargs,
-                    )
-                    futures.append((scan_type, future))
-
-                # 等待所有并行子 Flow 完成
-                if futures:
-                    wait([f for _, f in futures])
-
-                    # 检查结果（复用统一的结果处理逻辑）
-                    for scan_type, future in futures:
-                        try:
-                            result = future.result()
-                            record_flow_result(scan_type, result=result)
-                        except Exception as e:
-                            record_flow_result(scan_type, error=e)
-
-        # ==================== 完成 ====================
-        logger.info(
-            "="*60 + "\n" +
-            "✓ 扫描任务初始化完成\n" +
-            f"  执行的 Flow: {', '.join(executed_flows)}\n" +
-            "="*60
-        )
-        
-        # ==================== 返回结果 ====================
         return {
             'success': True,
             'scan_id': scan_id,
@@ -261,19 +246,14 @@ def initiate_scan_flow(
         }
 
     except ValueError as e:
-        # 参数错误
         logger.error("参数错误: %s", e)
         raise
     except RuntimeError as e:
-        # 执行失败
         logger.error("运行时错误: %s", e)
         raise
     except OSError as e:
-        # 文件系统错误（工作空间创建失败）
         logger.error("文件系统错误: %s", e)
         raise
     except Exception as e:
-        # 其他未预期错误
         logger.exception("初始化扫描任务失败: %s", e)
-        # 注意：失败状态更新由 Prefect State Handlers 自动处理
         raise

backend/apps/scan/flows/port_scan_flow.py

@@ -10,25 +10,22 @@
 - 配置由 YAML 解析
 """
 
-# Django 环境初始化（导入即生效）
-from apps.common.prefect_django_setup import setup_django_for_prefect
-
 import logging
-import os
 import subprocess
+from datetime import datetime
 from pathlib import Path
-from typing import Callable
+
-from prefect import flow
+from apps.scan.decorators import scan_flow
-from apps.scan.tasks.port_scan import (
-    export_scan_targets_task,
-    run_and_stream_save_ports_task
-)
 from apps.scan.handlers.scan_flow_handlers import (
-    on_scan_flow_running,
     on_scan_flow_completed,
     on_scan_flow_failed,
+    on_scan_flow_running,
 )
-from apps.scan.utils import config_parser, build_scan_command
+from apps.scan.tasks.port_scan import (
+    export_hosts_task,
+    run_and_stream_save_ports_task,
+)
+from apps.scan.utils import build_scan_command, user_log, wait_for_system_load
 
 logger = logging.getLogger(__name__)
 
@@ -42,7 +39,7 @@ def calculate_port_scan_timeout(
     根据目标数量和端口数量计算超时时间
 
     计算公式：超时时间 = 目标数 × 端口数 × base_per_pair
-    超时范围：60秒 ~ 2天（172800秒）
+    超时范围：60秒 ~ 无上限
 
     Args:
         tool_config: 工具配置字典，包含端口配置（ports, top-ports等）
@@ -50,18 +47,9 @@ def calculate_port_scan_timeout(
         base_per_pair: 每个"端口-目标对"的基础时间（秒），默认 0.5秒
 
     Returns:
-        int: 计算出的超时时间（秒），范围：60 ~ 172800
+        int: 计算出的超时时间（秒），最小 60 秒
-    
-    Example:
-        # 100个目标 × 100个端口 × 0.5秒 = 5000秒
-        # 10个目标 × 1000个端口 × 0.5秒 = 5000秒
-        timeout = calculate_port_scan_timeout(
-            tool_config={'top-ports': 100},
-            file_path='/path/to/domains.txt'
-        )
     """
     try:
-        # 1. 统计目标数量
         result = subprocess.run(
             ['wc', '-l', file_path],
             capture_output=True,
@@ -69,30 +57,18 @@ def calculate_port_scan_timeout(
             check=True
         )
         target_count = int(result.stdout.strip().split()[0])
-        
-        # 2. 解析端口数量
         port_count = _parse_port_count(tool_config)
-        
-        # 3. 计算超时时间
-        # 总工作量 = 目标数 × 端口数
         total_work = target_count * port_count
-        timeout = int(total_work * base_per_pair)
+        timeout = max(60, int(total_work * base_per_pair))
-        
-        # 4. 设置合理的下限（不再设置上限）
-        min_timeout = 60       # 最小 60 秒
-        timeout = max(min_timeout, timeout)
 
         logger.info(
-            f"计算端口扫描 timeout - "
+            "计算端口扫描 timeout - 目标数: %d, 端口数: %d, 总工作量: %d, 超时: %d秒",
-            f"目标数: {target_count}, "
+            target_count, port_count, total_work, timeout
-            f"端口数: {port_count}, "
-            f"总工作量: {total_work}, "
-            f"超时: {timeout}秒"
         )
         return timeout
 
     except Exception as e:
-        logger.warning(f"计算 timeout 失败: {e}，使用默认值 600秒")
+        logger.warning("计算 timeout 失败: %s，使用默认值 600秒", e)
         return 600
 
 
@@ -113,89 +89,78 @@ def _parse_port_count(tool_config: dict) -> int:
     Returns:
         int: 端口数量
     """
-    # 1. 检查 top-ports 配置
+    # 检查 top-ports 配置
     if 'top-ports' in tool_config:
         top_ports = tool_config['top-ports']
         if isinstance(top_ports, int) and top_ports > 0:
             return top_ports
-        logger.warning(f"top-ports 配置无效: {top_ports}，使用默认值")
+        logger.warning("top-ports 配置无效: %s，使用默认值", top_ports)
 
-    # 2. 检查 ports 配置
+    # 检查 ports 配置
     if 'ports' in tool_config:
         ports_str = str(tool_config['ports']).strip()
 
-        # 2.1 逗号分隔的端口列表：80,443,8080
+        # 逗号分隔的端口列表：80,443,8080
         if ',' in ports_str:
-            port_list = [p.strip() for p in ports_str.split(',') if p.strip()]
+            return len([p.strip() for p in ports_str.split(',') if p.strip()])
-            return len(port_list)
 
-        # 2.2 端口范围：1-1000
+        # 端口范围：1-1000
         if '-' in ports_str:
             try:
                 start, end = ports_str.split('-', 1)
                 start_port = int(start.strip())
                 end_port = int(end.strip())
-                
                 if 1 <= start_port <= end_port <= 65535:
                     return end_port - start_port + 1
-                logger.warning(f"端口范围无效: {ports_str}，使用默认值")
+                logger.warning("端口范围无效: %s，使用默认值", ports_str)
             except ValueError:
-                logger.warning(f"端口范围解析失败: {ports_str}，使用默认值")
+                logger.warning("端口范围解析失败: %s，使用默认值", ports_str)
 
-        # 2.3 单个端口
+        # 单个端口
         try:
             port = int(ports_str)
             if 1 <= port <= 65535:
                 return 1
         except ValueError:
-            logger.warning(f"端口配置解析失败: {ports_str}，使用默认值")
+            logger.warning("端口配置解析失败: %s，使用默认值", ports_str)
 
-    # 3. 默认值：naabu 默认扫描 top 100 端口
+    # 默认值：naabu 默认扫描 top 100 端口
     return 100
 
 
 
 
 
-def _export_scan_targets(target_id: int, port_scan_dir: Path) -> tuple[str, int, str]:
+def _export_hosts(port_scan_dir: Path, provider) -> tuple[str, int]:
     """
-    导出扫描目标到文件
+    导出主机列表到文件
-    
-    根据 Target 类型自动决定导出内容：
-    - DOMAIN: 从 Subdomain 表导出子域名
-    - IP: 直接写入 target.name
-    - CIDR: 展开 CIDR 范围内的所有 IP
 
     Args:
-        target_id: 目标 ID
         port_scan_dir: 端口扫描目录
+        provider: TargetProvider 实例
 
     Returns:
-        tuple: (targets_file, target_count, target_type)
+        tuple: (hosts_file, host_count)
     """
-    logger.info("Step 1: 导出扫描目标列表")
+    logger.info("Step 1: 导出主机列表")
 
-    targets_file = str(port_scan_dir / 'targets.txt')
+    hosts_file = str(port_scan_dir / 'hosts.txt')
-    export_result = export_scan_targets_task(
+    export_result = export_hosts_task(
-        target_id=target_id,
+        output_file=hosts_file,
-        output_file=targets_file,
+        provider=provider,
-        batch_size=1000  # 每次读取 1000 条，优化内存占用
     )
 
-    target_count = export_result['total_count']
+    host_count = export_result['total_count']
-    target_type = export_result.get('target_type', 'unknown')
 
     logger.info(
-        "✓ 扫描目标导出完成 - 类型: %s, 文件: %s, 数量: %d",
+        "✓ 主机列表导出完成 - 文件: %s, 数量: %d",
-        target_type,
+        export_result['output_file'], host_count
-        export_result['output_file'],
-        target_count
     )
 
-    if target_count == 0:
+    if host_count == 0:
-        logger.warning("目标下没有可扫描的地址，无法执行端口扫描")
+        logger.warning("目标下没有可扫描的主机，无法执行端口扫描")
 
-    return export_result['output_file'], target_count, target_type
+    return export_result['output_file'], host_count
 
 
 def _run_scans_sequentially(
@@ -204,7 +169,7 @@ def _run_scans_sequentially(
     port_scan_dir: Path,
     scan_id: int,
     target_id: int,
-    target_name: str
+    target_name: str,
 ) -> tuple[dict, int, list, list]:
     """
     串行执行端口扫描任务
@@ -215,70 +180,55 @@ def _run_scans_sequentially(
         port_scan_dir: 端口扫描目录
         scan_id: 扫描任务 ID
         target_id: 目标 ID
-        target_name: 目标名称（用于错误日志）
+        target_name: 目标名称（用于日志显示）
 
     Returns:
         tuple: (tool_stats, processed_records, successful_tool_names, failed_tools)
-        注意：端口扫描是流式输出，不生成结果文件
-        
-    Raises:
-        RuntimeError: 所有工具均失败
     """
-    # ==================== 构建命令并串行执行 ====================
-    
     tool_stats = {}
     processed_records = 0
-    failed_tools = []      # 记录失败的工具（含原因）
+    failed_tools = []
 
-    # for循环执行工具：按顺序串行运行每个启用的端口扫描工具
     for tool_name, tool_config in enabled_tools.items():
-        # 1. 构建完整命令（变量替换）
+        # 构建命令
         try:
             command = build_scan_command(
                 tool_name=tool_name,
                 scan_type='port_scan',
-                command_params={
+                command_params={'domains_file': domains_file},
-                    'domains_file': domains_file  # 对应 {domains_file}
+                tool_config=tool_config
-                },
-                tool_config=tool_config     #yaml的工具配置
             )
         except Exception as e:
-            reason = f"命令构建失败: {str(e)}"
+            reason = f"命令构建失败: {e}"
-            logger.error(f"构建 {tool_name} 命令失败: {e}")
+            logger.error("构建 %s 命令失败: %s", tool_name, e)
             failed_tools.append({'tool': tool_name, 'reason': reason})
             continue
 
-        # 2. 获取超时时间（支持 'auto' 动态计算）
+        # 获取超时时间
         config_timeout = tool_config['timeout']
         if config_timeout == 'auto':
-            # 动态计算超时时间
+            config_timeout = calculate_port_scan_timeout(tool_config, str(domains_file))
-            config_timeout = calculate_port_scan_timeout(
+            logger.info("✓ 工具 %s 动态计算 timeout: %d秒", tool_name, config_timeout)
-                tool_config=tool_config,
-                file_path=str(domains_file)
-            )
-            logger.info(f"✓ 工具 {tool_name} 动态计算 timeout: {config_timeout}秒")
 
-        # 2.1 生成日志文件路径
+        # 生成日志文件路径
-        from datetime import datetime
         timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
         log_file = port_scan_dir / f"{tool_name}_{timestamp}.log"
 
-        # 3. 执行扫描任务
         logger.info("开始执行 %s 扫描（超时: %d秒）...", tool_name, config_timeout)
+        user_log(scan_id, "port_scan", f"Running {tool_name}: {command}")
 
+        # 执行扫描任务
         try:
-            # 直接调用 task（串行执行）
-            # 注意：端口扫描是流式输出到 stdout，不使用 output_file
             result = run_and_stream_save_ports_task(
                 cmd=command,
-                tool_name=tool_name,  # 工具名称
+                tool_name=tool_name,
                 scan_id=scan_id,
                 target_id=target_id,
                 cwd=str(port_scan_dir),
                 shell=True,
                 batch_size=1000,
                 timeout=config_timeout,
-                log_file=str(log_file)  # 新增：日志文件路径
+                log_file=str(log_file)
             )
 
             tool_stats[tool_name] = {
@@ -286,26 +236,25 @@ def _run_scans_sequentially(
                 'result': result,
                 'timeout': config_timeout
             }
-            processed_records += result.get('processed_records', 0)
+            tool_records = result.get('processed_records', 0)
-            logger.info(
+            processed_records += tool_records
-                "✓ 工具 %s 流式处理完成 - 记录数: %d",
+            logger.info("✓ 工具 %s 流式处理完成 - 记录数: %d", tool_name, tool_records)
-                tool_name, result.get('processed_records', 0)
+            user_log(scan_id, "port_scan", f"{tool_name} completed: found {tool_records} ports")
-            )
 
-        except subprocess.TimeoutExpired as exc:
+        except subprocess.TimeoutExpired:
-            # 超时异常单独处理
+            reason = f"timeout after {config_timeout}s"
-            # 注意：流式处理任务超时时，已解析的数据已保存到数据库
-            reason = f"执行超时（配置: {config_timeout}秒）"
             failed_tools.append({'tool': tool_name, 'reason': reason})
             logger.warning(
                 "⚠️ 工具 %s 执行超时 - 超时配置: %d秒\n"
                 "注意：超时前已解析的端口数据已保存到数据库，但扫描未完全完成。",
                 tool_name, config_timeout
             )
+            user_log(scan_id, "port_scan", f"{tool_name} failed: {reason}", "error")
         except Exception as exc:
-            # 其他异常
+            reason = str(exc)
-            failed_tools.append({'tool': tool_name, 'reason': str(exc)})
+            failed_tools.append({'tool': tool_name, 'reason': reason})
             logger.error("工具 %s 执行失败: %s", tool_name, exc, exc_info=True)
+            user_log(scan_id, "port_scan", f"{tool_name} failed: {reason}", "error")
 
     if failed_tools:
         logger.warning(
@@ -315,13 +264,13 @@ def _run_scans_sequentially(
 
     if not tool_stats:
         error_details = "; ".join([f"{f['tool']}: {f['reason']}" for f in failed_tools])
-        logger.warning("所有端口扫描工具均失败 - 目标: %s, 失败工具: %s", target_name, error_details)
+        logger.warning("所有端口扫描工具均失败 - Target: %s, 失败工具: %s", target_name, error_details)
-        # 返回空结果，不抛出异常，让扫描继续
         return {}, 0, [], failed_tools
 
-    # 动态计算成功的工具列表
+    successful_tool_names = [
-    successful_tool_names = [name for name in enabled_tools.keys() 
+        name for name in enabled_tools
-                              if name not in [f['tool'] for f in failed_tools]]
+        if name not in [f['tool'] for f in failed_tools]
+    ]
 
     logger.info(
         "✓ 串行端口扫描执行完成 - 成功: %d/%d (成功: %s, 失败: %s)",
@@ -333,19 +282,18 @@ def _run_scans_sequentially(
     return tool_stats, processed_records, successful_tool_names, failed_tools
 
 
-@flow(
+@scan_flow(
     name="port_scan",
-    log_prints=True,
     on_running=[on_scan_flow_running],
     on_completion=[on_scan_flow_completed],
     on_failure=[on_scan_flow_failed],
 )
 def port_scan_flow(
     scan_id: int,
-    target_name: str,
     target_id: int,
     scan_workspace_dir: str,
-    enabled_tools: dict
+    enabled_tools: dict,
+    provider,
 ) -> dict:
     """
     端口扫描 Flow
@@ -361,49 +309,32 @@ def port_scan_flow(
         Step 0: 创建工作目录
         Step 1: 导出域名列表到文件（供扫描工具使用）
         Step 2: 解析配置，获取启用的工具
-        Step 3: 串行执行扫描工具，运行端口扫描工具并实时解析输出到数据库（→ HostPortMapping）
+        Step 3: 串行执行扫描工具，运行端口扫描工具并实时解析输出到数据库
 
     Args:
         scan_id: 扫描任务 ID
-        target_name: 域名
         target_id: 目标 ID
         scan_workspace_dir: Scan 工作空间目录
         enabled_tools: 启用的工具配置字典
+        provider: TargetProvider 实例
 
     Returns:
-        dict: {
+        dict: 扫描结果
-            'success': bool,
-            'scan_id': int,
-            'target': str,
-            'scan_workspace_dir': str,
-            'domains_file': str,
-            'domain_count': int,
-            'processed_records': int,
-            'executed_tasks': list,
-            'tool_stats': {
-                'total': int,                    # 总工具数
-                'successful': int,               # 成功工具数
-                'failed': int,                   # 失败工具数
-                'successful_tools': list[str],   # 成功工具列表 ['naabu_active']
-                'failed_tools': list[dict],      # 失败工具列表 [{'tool': 'naabu_passive', 'reason': '超时'}]
-                'details': dict                  # 详细执行结果（保留向后兼容）
-            }
-        }
 
     Raises:
         ValueError: 配置错误
         RuntimeError: 执行失败
-    
-    Note:
-        端口扫描工具（如 naabu）会解析域名获取 IP，输出 host + ip + port 三元组。
-        同一 host 可能对应多个 IP（CDN、负载均衡），因此使用三元映射表存储。
     """
     try:
-        # 参数验证
+        wait_for_system_load(context="port_scan_flow")
+
+        # 从 provider 获取 target_name
+        target_name = provider.get_target_name()
+        if not target_name:
+            raise ValueError("无法获取 Target 名称")
+
         if scan_id is None:
             raise ValueError("scan_id 不能为空")
-        if not target_name:
-            raise ValueError("target_name 不能为空")
         if target_id is None:
             raise ValueError("target_id 不能为空")
         if not scan_workspace_dir:
@@ -412,33 +343,30 @@ def port_scan_flow(
             raise ValueError("enabled_tools 不能为空")
 
         logger.info(
-            "="*60 + "\n" +
+            "开始端口扫描 - Scan ID: %s, Target: %s, Workspace: %s",
-            "开始端口扫描\n" +
+            scan_id, target_name, scan_workspace_dir
-            f"  Scan ID: {scan_id}\n" +
-            f"  Target: {target_name}\n" +
-            f"  Workspace: {scan_workspace_dir}\n" +
-            "="*60
         )
+        user_log(scan_id, "port_scan", "Starting port scan")
 
         # Step 0: 创建工作目录
         from apps.scan.utils import setup_scan_directory
         port_scan_dir = setup_scan_directory(scan_workspace_dir, 'port_scan')
 
-        # Step 1: 导出扫描目标列表到文件（根据 Target 类型自动决定内容）
+        # Step 1: 导出主机列表
-        targets_file, target_count, target_type = _export_scan_targets(target_id, port_scan_dir)
+        hosts_file, host_count = _export_hosts(port_scan_dir, provider)
 
-        if target_count == 0:
+        if host_count == 0:
-            logger.warning("目标下没有可扫描的地址，跳过端口扫描")
+            logger.warning("跳过端口扫描：没有主机可扫描 - Scan ID: %s", scan_id)
+            user_log(scan_id, "port_scan", "Skipped: no hosts to scan", "warning")
             return {
                 'success': True,
                 'scan_id': scan_id,
                 'target': target_name,
                 'scan_workspace_dir': scan_workspace_dir,
-                'targets_file': targets_file,
+                'hosts_file': hosts_file,
-                'target_count': 0,
+                'host_count': 0,
-                'target_type': target_type,
                 'processed_records': 0,
-                'executed_tasks': ['export_scan_targets'],
+                'executed_tasks': ['export_hosts'],
                 'tool_stats': {
                     'total': 0,
                     'successful': 0,
@@ -451,36 +379,32 @@ def port_scan_flow(
 
         # Step 2: 工具配置信息
         logger.info("Step 2: 工具配置信息")
-        logger.info(
+        logger.info("✓ 启用工具: %s", ', '.join(enabled_tools.keys()))
-            "✓ 启用工具: %s",
-            ', '.join(enabled_tools.keys())
-        )
 
         # Step 3: 串行执行扫描工具
         logger.info("Step 3: 串行执行扫描工具")
         tool_stats, processed_records, successful_tool_names, failed_tools = _run_scans_sequentially(
             enabled_tools=enabled_tools,
-            domains_file=targets_file,  # 现在是 targets_file，兼容原参数名
+            domains_file=hosts_file,
             port_scan_dir=port_scan_dir,
             scan_id=scan_id,
             target_id=target_id,
-            target_name=target_name
+            target_name=target_name,
         )
 
-        logger.info("="*60 + "\n✓ 端口扫描完成\n" + "="*60)
+        logger.info("✓ 端口扫描完成 - 发现端口: %d", processed_records)
+        user_log(scan_id, "port_scan", f"port_scan completed: found {processed_records} ports")
 
-        # 动态生成已执行的任务列表
+        executed_tasks = ['export_hosts', 'parse_config']
-        executed_tasks = ['export_scan_targets', 'parse_config']
+        executed_tasks.extend([f'run_and_stream_save_ports ({tool})' for tool in tool_stats])
-        executed_tasks.extend([f'run_and_stream_save_ports ({tool})' for tool in tool_stats.keys()])
 
         return {
             'success': True,
             'scan_id': scan_id,
             'target': target_name,
             'scan_workspace_dir': scan_workspace_dir,
-            'targets_file': targets_file,
+            'hosts_file': hosts_file,
-            'target_count': target_count,
+            'host_count': host_count,
-            'target_type': target_type,
             'processed_records': processed_records,
             'executed_tasks': executed_tasks,
             'tool_stats': {
@@ -488,8 +412,8 @@ def port_scan_flow(
                 'successful': len(successful_tool_names),
                 'failed': len(failed_tools),
                 'successful_tools': successful_tool_names,
-                'failed_tools': failed_tools,  # [{'tool': 'naabu_active', 'reason': '超时'}]
+                'failed_tools': failed_tools,
-                'details': tool_stats  # 详细结果（保留向后兼容）
+                'details': tool_stats
             }
         }