chore: improve version detection and update deployment configuration

- Update version detection to support IMAGE_TAG environment variable for Docker containers
- Add fallback mechanism to check multiple version file paths (/app/VERSION and project root)
- Add IMAGE_TAG environment variable to docker-compose.dev.yml and docker-compose.yml
- Fix frontend access URL in start.sh to include correct port (8083)
- Update upgrade warning message in update.sh to recommend fresh installation with latest code
- Improve robustness of version retrieval with better error handling for missing files

.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 ==="
-          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 rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /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
@@ -94,45 +195,76 @@ jobs:
             echo "IS_RELEASE=false" >> $GITHUB_OUTPUT
           fi
 
-      - name: Build and push
-        uses: docker/build-push-action@v5
-        with:
-          context: ${{ matrix.context }}
-          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
-          cache-to: type=gha,mode=max
-          provenance: false
-          sbom: false
+      - name: Create and push multi-arch manifest
+        run: |
+          VERSION=${{ steps.version.outputs.VERSION }}
+          IMAGE=${{ env.IMAGE_PREFIX }}/${{ matrix.image }}
+          
+          docker manifest create ${IMAGE}:${VERSION} \
+            ${IMAGE}:${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
 
-  # 所有镜像构建成功后，更新 VERSION 文件
+  # 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
+      - name: Checkout repository
         uses: actions/checkout@v4
         with:
-          ref: main
+          fetch-depth: 0  # 获取完整历史，用于判断 tag 所在分支
           token: ${{ secrets.GITHUB_TOKEN }}
 
+      - name: Determine source branch and version
+        id: branch
+        run: |
+          VERSION="${GITHUB_REF#refs/tags/}"
+          
+          # 查找包含此 tag 的分支
+          BRANCHES=$(git branch -r --contains ${{ github.ref_name }})
+          echo "Branches containing tag: $BRANCHES"
+          
+          # 判断 tag 来自哪个分支
+          if echo "$BRANCHES" | grep -q "origin/main"; then
+            TARGET_BRANCH="main"
+            UPDATE_LATEST="true"
+          elif echo "$BRANCHES" | grep -q "origin/dev"; then
+            TARGET_BRANCH="dev"
+            UPDATE_LATEST="false"
+          else
+            echo "Warning: Tag not found in main or dev branch, defaulting to main"
+            TARGET_BRANCH="main"
+            UPDATE_LATEST="false"
+          fi
+          
+          echo "BRANCH=$TARGET_BRANCH" >> $GITHUB_OUTPUT
+          echo "VERSION=$VERSION" >> $GITHUB_OUTPUT
+          echo "UPDATE_LATEST=$UPDATE_LATEST" >> $GITHUB_OUTPUT
+          echo "Will update VERSION on branch: $TARGET_BRANCH"
+
+      - name: Checkout target branch
+        run: |
+          git checkout ${{ steps.branch.outputs.BRANCH }}
+
       - name: Update VERSION file
         run: |
-          VERSION="${GITHUB_REF#refs/tags/}"
+          VERSION="${{ steps.branch.outputs.VERSION }}"
           echo "$VERSION" > VERSION
-          echo "Updated VERSION to $VERSION"
+          echo "Updated VERSION to $VERSION on branch ${{ steps.branch.outputs.BRANCH }}"
 
       - name: Commit and push
         run: |
           git config user.name "github-actions[bot]"
           git config user.email "github-actions[bot]@users.noreply.github.com"
           git add VERSION
-          git diff --staged --quiet || git commit -m "chore: bump version to ${GITHUB_REF#refs/tags/}"
-          git push
+          git diff --staged --quiet || git commit -m "chore: bump version to ${{ steps.branch.outputs.VERSION }}"
+          git push origin ${{ steps.branch.outputs.BRANCH }}

.gitignore

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

README.md

@@ -13,18 +13,25 @@
 
 <p align="center">
   <a href="#-功能特性">功能特性</a> •
+  <a href="#-全局资产搜索">资产搜索</a> •
   <a href="#-快速开始">快速开始</a> •
   <a href="#-文档">文档</a> •
-  <a href="#-技术栈">技术栈</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>
@@ -51,20 +58,35 @@
 
 ## ✨ 功能特性
 
-### 🎯 目标与资产管理
-- **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
+### 扫描能力
 
-### 🔍 漏洞扫描
-- **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
-- **定时扫描** - Cron 表达式配置，自动化周期扫描
+| 功能 | 状态 | 工具 | 说明 |
+|------|------|------|------|
+| 子域名扫描 | ✅ | Subfinder, Amass, PureDNS | 被动收集 + 主动爆破，聚合 50+ 数据源 |
+| 端口扫描 | ✅ | Naabu | 自定义端口范围 |
+| 站点发现 | ✅ | HTTPX | HTTP 探测，自动获取标题、状态码、技术栈 |
+| 指纹识别 | ✅ | XingFinger | 2.7W+ 指纹规则，多源指纹库 |
+| URL 收集 | ✅ | Waymore, Katana | 历史数据 + 主动爬取 |
+| 目录扫描 | ✅ | FFUF | 高速爆破，智能字典 |
+| 漏洞扫描 | ✅ | Nuclei, Dalfox | 9000+ POC 模板，XSS 检测 |
+| 站点截图 | ✅ | 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 | ✅ | 多层级组织，支持域名/IP 目标 |
+| 资产快照 | ✅ | 扫描结果对比，追踪资产变化 |
+| 黑名单过滤 | ✅ | 全局 + Target 级，支持通配符/CIDR |
+| 定时任务 | ✅ | Cron 表达式，自动化周期扫描 |
+| 分布式扫描 | ✅ | 多 Worker 节点，负载感知调度 |
+| 全局搜索 | ✅ | 表达式语法，多字段组合查询 |
+| 通知推送 | ✅ | 企业微信、Telegram、Discord |
+| API 密钥管理 | ✅ | 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
     
@@ -103,8 +127,10 @@ 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
 ```
 
@@ -155,9 +181,34 @@ flowchart TB
     W3 -.心跳上报.-> REDIS
 ```
 
+### 🔎 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
 
 ---
 
@@ -165,7 +216,8 @@ flowchart TB
 
 ### 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
@@ -177,11 +229,19 @@ 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（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**
+> - 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）
+
 ### 访问服务
 
-- **Web 界面**: `https://localhost` 
+- **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
 
@@ -197,25 +257,44 @@ sudo ./restart.sh
 
 # 卸载
 sudo ./uninstall.sh
-
-# 更新
-sudo ./update.sh
 ```
 
 ## 🤝 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)
-- 💡 **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
+- 💡 **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
 
 ## 📧 联系
-- 目前版本就我个人使用，可能会有很多边界问题
-- 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
-
-- 微信公众号: **洋洋的小黑屋**
+- 微信公众号: **塔罗安全学苑**
+- 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
 
 <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
+
+| 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>
+
+### 🙏 感谢以下赞助
+
+| 昵称 | 金额 |
+|------|------|
+| X（闭关中） | ¥88 |
+
 
 ## ⚠️ 免责声明
 

VERSION

@@ -1 +1 @@
-v1.1.8
+v1.5.6-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,
-            vhost=self.vhost
+            response_body=self.response_body,
+            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(
-        max_length=1000,
+    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.CharField(
-        max_length=1000,
+    title = models.TextField(
         blank=True,
         default='',
         help_text='网页标题（HTML <title> 标签内容）'
     )
-    webserver = models.CharField(
-        max_length=200,
+    webserver = models.TextField(
         blank=True,
         default='',
         help_text='服务器类型（HTTP 响应头 Server 值）'
     )
-    body_preview = models.CharField(
-        max_length=1000,
+    response_body = models.TextField(
         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(
-        max_length=200,
+    content_type = models.TextField(
         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(
-        max_length=1000,
+    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.CharField(
-        max_length=1000,
+    title = models.TextField(
         blank=True,
         default='',
         help_text='网页标题（HTML <title> 标签内容）'
     )
-    webserver = models.CharField(
-        max_length=200,
+    webserver = models.TextField(
         blank=True,
         default='',
         help_text='服务器类型（HTTP 响应头 Server 值）'
     )
-    body_preview = models.CharField(
-        max_length=1000,
+    response_body = models.TextField(
         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(
-        max_length=200,
+    content_type = models.TextField(
         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')
-    status = models.IntegerField(null=True, blank=True, help_text='HTTP状态码')
+    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.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')
-    web_server = models.CharField(max_length=200, 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')
+    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 = 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')
-    webserver = models.CharField(max_length=200, 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')
+    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 = 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',
-                        'vhost', 'location', 'matched_gf_patterns'
+                        'webserver', 'response_body', 'content_type', 'tech',
+                        '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',
-                        'status_code', 'content_length', 'vhost'
+                        'response_body', 'content_type', 'tech',
+                        '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/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,
-                    vhost=item.vhost
+                    response_body=item.response_body,
+                    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',
-                'content_length', 'content_type', 'web_server', 'tech',
-                'body_preview', 'vhost', 'created_at'
+                'url', 'host', 'location', 'title', 'status_code',
+                'content_length', 'content_type', 'webserver', 'tech',
+                '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 {
-                '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'],
-            }
+            yield row

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',
         ]
@@ -134,12 +137,13 @@ class VulnerabilitySnapshotSerializer(serializers.ModelSerializer):
 class EndpointListSerializer(serializers.ModelSerializer):
     """端点列表序列化器（用于目标端点列表页）"""
 
-    # 将 GF 匹配模式映射为前端使用的 tags 字段
-    tags = serializers.ListField(
+    # GF 匹配模式（gf-patterns 工具匹配的敏感 URL 模式）
+    gfPatterns = serializers.ListField(
         child=serializers.CharField(),
         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
@@ -152,10 +156,11 @@ class EndpointListSerializer(serializers.ModelSerializer):
             'content_length',
             'content_type',
             'webserver',
-            'body_preview',
+            'response_body',
             'tech',
             'vhost',
-            'tags',
+            'responseHeaders',  # HTTP响应头
+            'gfPatterns',
             'created_at',
         ]
         read_only_fields = fields
@@ -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
-    status_code = serializers.IntegerField(source='status', read_only=True)  # 映射字段名
+    responseHeaders = serializers.CharField(source='response_headers', read_only=True)  # 原始HTTP响应头
     
     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',
         ]
@@ -258,12 +263,13 @@ class DirectorySnapshotSerializer(serializers.ModelSerializer):
 class EndpointSnapshotSerializer(serializers.ModelSerializer):
     """端点快照序列化器（用于扫描历史）"""
 
-    # 将 GF 匹配模式映射为前端使用的 tags 字段
-    tags = serializers.ListField(
+    # GF 匹配模式（gf-patterns 工具匹配的敏感 URL 模式）
+    gfPatterns = serializers.ListField(
         child=serializers.CharField(),
         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',
-            'tags',
+            '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 +1,185 @@
+"""
+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
+        
+        snapshots = ScreenshotSnapshot.objects.filter(scan_id=scan_id)
+        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

@@ -72,7 +72,7 @@ class EndpointSnapshotsService:
         'url': 'url',
         'host': 'host',
         'title': 'title',
-        'status': 'status_code',
+        'status_code': 'status_code',
         'webserver': 'webserver',
         'tech': 'tech',
     }

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

@@ -73,8 +73,8 @@ class WebsiteSnapshotsService:
         'url': 'url',
         'host': 'host',
         'title': 'title',
-        'status': 'status',
-        'webserver': 'web_server',
+        'status_code': 'status_code',
+        '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(
-                {'error': '获取统计数据失败'},
-                status=status.HTTP_500_INTERNAL_SERVER_ERROR
+            return error_response(
+                code=ErrorCodes.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(
-                {'error': '获取历史数据失败'},
-                status=status.HTTP_500_INTERNAL_SERVER_ERROR
+            return error_response(
+                code=ErrorCodes.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",
-            "createdCount": 10,
-            "skippedCount": 2,
-            "invalidCount": 1,
-            "mismatchedCount": 1,
-            "totalReceived": 14
+            "data": {
+                "createdCount": 10,
+                "skippedCount": 2,
+                "invalidCount": 1,
+                "mismatchedCount": 1,
+                "totalReceived": 14
+            }
         }
         """
         from apps.targets.models import Target
         
         target_pk = self.kwargs.get('target_pk')
         if not target_pk:
-            return Response(
-                {'error': '必须在目标下批量创建子域名'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                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(
-                {'error': '目标不存在'},
-                status=status.HTTP_404_NOT_FOUND
+            return error_response(
+                code=ErrorCodes.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(
-                {'error': '只有域名类型的目标支持导入子域名'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                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(
-                {'error': '请求体不能为空或格式错误'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                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(
-                {'error': '服务器内部错误'},
-                status=status.HTTP_500_INTERNAL_SERVER_ERROR
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Server internal error',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
             )
         
-        return Response({
-            'message': '批量创建完成',
+        return success_response(data={
             '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(
-            generate_csv_rows(data_iterator, headers, formatters),
-            content_type='text/csv; charset=utf-8'
+        return create_csv_export_response(
+            data_iterator=data_iterator,
+            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",
-            "createdCount": 10,
-            "mismatchedCount": 2
+            "data": {
+                "createdCount": 10
+            }
         }
         """
         from apps.targets.models import Target
         
         target_pk = self.kwargs.get('target_pk')
         if not target_pk:
-            return Response(
-                {'error': '必须在目标下批量创建网站'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                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(
-                {'error': '目标不存在'},
-                status=status.HTTP_404_NOT_FOUND
+            return error_response(
+                code=ErrorCodes.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(
-                {'error': '请求体不能为空或格式错误'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                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(
-                {'error': '服务器内部错误'},
-                status=status.HTTP_500_INTERNAL_SERVER_ERROR
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Server internal error',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
             )
         
-        return Response({
-            'message': '批量创建完成',
+        return success_response(data={
             '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(
-            generate_csv_rows(data_iterator, headers, formatters),
-            content_type='text/csv; charset=utf-8'
+        return create_csv_export_response(
+            data_iterator=data_iterator,
+            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",
-            "createdCount": 10,
-            "mismatchedCount": 2
+            "data": {
+                "createdCount": 10
+            }
         }
         """
         from apps.targets.models import Target
         
         target_pk = self.kwargs.get('target_pk')
         if not target_pk:
-            return Response(
-                {'error': '必须在目标下批量创建目录'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                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(
-                {'error': '目标不存在'},
-                status=status.HTTP_404_NOT_FOUND
+            return error_response(
+                code=ErrorCodes.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(
-                {'error': '请求体不能为空或格式错误'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                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(
-                {'error': '服务器内部错误'},
-                status=status.HTTP_500_INTERNAL_SERVER_ERROR
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Server internal error',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
             )
         
-        return Response({
-            'message': '批量创建完成',
+        return success_response(data={
             '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(
-            generate_csv_rows(data_iterator, headers, formatters),
-            content_type='text/csv; charset=utf-8'
+        return create_csv_export_response(
+            data_iterator=data_iterator,
+            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",
-            "createdCount": 10,
-            "mismatchedCount": 2
+            "data": {
+                "createdCount": 10
+            }
         }
         """
         from apps.targets.models import Target
         
         target_pk = self.kwargs.get('target_pk')
         if not target_pk:
-            return Response(
-                {'error': '必须在目标下批量创建端点'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                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(
-                {'error': '目标不存在'},
-                status=status.HTTP_404_NOT_FOUND
+            return error_response(
+                code=ErrorCodes.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(
-                {'error': '请求体不能为空或格式错误'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                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(
-                {'error': '服务器内部错误'},
-                status=status.HTTP_500_INTERNAL_SERVER_ERROR
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Server internal error',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
             )
         
-        return Response({
-            'message': '批量创建完成',
+        return success_response(data={
             '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(
-            generate_csv_rows(data_iterator, headers, formatters),
-            content_type='text/csv; charset=utf-8'
+        return create_csv_export_response(
+            data_iterator=data_iterator,
+            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
-        response = StreamingHttpResponse(
-            generate_csv_rows(data_iterator, headers, formatters),
-            content_type='text/csv; charset=utf-8'
+        return create_csv_export_response(
+            data_iterator=data_iterator,
+            headers=headers,
+            filename=f"target-{target_pk}-ip-addresses.csv",
+            field_formatters=formatters
         )
-        response['Content-Disposition'] = f'attachment; filename="target-{target_pk}-ip-addresses.csv"'
+
+    @action(detail=False, methods=['post'], url_path='bulk-delete')
+    def bulk_delete(self, request, **kwargs):
+        """批量删除 IP 地址映射
         
-        return response
+        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(
-            generate_csv_rows(data_iterator, headers, formatters),
-            content_type='text/csv; charset=utf-8'
+        return create_csv_export_response(
+            data_iterator=data_iterator,
+            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(
-            generate_csv_rows(data_iterator, headers, formatters),
-            content_type='text/csv; charset=utf-8'
+        return create_csv_export_response(
+            data_iterator=data_iterator,
+            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(
-            generate_csv_rows(data_iterator, headers, formatters),
-            content_type='text/csv; charset=utf-8'
+        return create_csv_export_response(
+            data_iterator=data_iterator,
+            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(
-            generate_csv_rows(data_iterator, headers, formatters),
-            content_type='text/csv; charset=utf-8'
+        return create_csv_export_response(
+            data_iterator=data_iterator,
+            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
-        response = StreamingHttpResponse(
-            generate_csv_rows(data_iterator, headers, formatters),
-            content_type='text/csv; charset=utf-8'
+        return create_csv_export_response(
+            data_iterator=data_iterator,
+            headers=headers,
+            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()
         
@@ -57,9 +63,6 @@ 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'])
@@ -71,7 +74,6 @@ def fetch_config_and_setup_django():
         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']}")
         
     except Exception as e:
         print(f"[ERROR] 获取配置失败: {config_url} - {e}", file=sys.stderr)

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。
     """
     
+    # 日志文件分类规则
+    CATEGORY_RULES = [
+        ('xingrin.log', 'system'),
+        ('xingrin_error.log', 'error'),
+        ('performance.log', 'performance'),
+        ('container_*.log', 'container'),
+    ]
+    
     def __init__(self):
-        # 日志文件路径（容器内路径，通过 volume 挂载到宿主机 /opt/xingrin/logs）
-        self.log_file = "/app/backend/logs/xingrin.log"
-        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
+        # 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 get_logs_content(self, lines: int | None = None) -> str:
+    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/system/*   系统管理接口（日志查看等）
+- /api/health/       健康检查接口（无需认证）
+- /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

@@ -11,8 +11,14 @@ from .csv_utils import (
     generate_csv_rows,
     format_list_field,
     format_datetime,
+    create_csv_export_response,
     UTF8_BOM,
 )
+from .blacklist_filter import (
+    BlacklistFilter,
+    detect_rule_type,
+    extract_host,
+)
 
 __all__ = [
     'deduplicate_for_bulk',
@@ -24,5 +30,9 @@ __all__ = [
     'generate_csv_rows',
     'format_list_field',
     'format_datetime',
+    'create_csv_export_response',
     'UTF8_BOM',
+    '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:
-                # 尝试解析为过滤条件
-                match = cls.FILTER_PATTERN.match(token)
-                if match:
-                    field, operator, value = match.groups()
-                    groups.append(FilterGroup(
-                        filter=ParsedFilter(
-                            field=field.lower(),
-                            operator=operator,
-                            value=value
-                        ),
-                        logical_op=pending_op if groups else LogicalOp.AND  # 第一个条件默认 AND
-                    ))
-                    pending_op = LogicalOp.AND  # 重置为默认 AND
+            elif token.startswith('__FILTER_') and token.endswith('__'):
+                # 还原占位符为原始过滤条件
+                try:
+                    idx = int(token[9:-2])  # 提取索引
+                    original_filter = filters_found[idx]
+                    match = cls.FILTER_PATTERN.match(original_filter)
+                    if match:
+                        field, operator, value = match.groups()
+                        groups.append(FilterGroup(
+                            filter=ParsedFilter(
+                                field=field.lower(),
+                                operator=operator,
+                                value=value
+                            ),
+                            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
 
@@ -132,7 +158,8 @@ class QueryBuilder:
         cls,
         queryset: QuerySet,
         filter_groups: List[FilterGroup],
-        field_mapping: Dict[str, str]
+        field_mapping: Dict[str, str],
+        json_array_fields: List[str] = None
     ) -> QuerySet:
         """构建 Django ORM 查询
         
@@ -140,6 +167,7 @@ class QueryBuilder:
             queryset: Django QuerySet
             filter_groups: 解析后的过滤条件组列表
             field_mapping: 字段映射
+            json_array_fields: JSON 数组字段列表（使用 __contains 查询）
         
         Returns:
             过滤后的 QuerySet
@@ -147,6 +175,23 @@ class QueryBuilder:
         if not filter_groups:
             return queryset
         
+        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
         
@@ -159,8 +204,11 @@ class QueryBuilder:
                 logger.debug(f"忽略未知字段: {f.field}")
                 continue
             
+            # 判断是否为 JSON 数组字段
+            is_json_array = db_field in json_array_fields
+            
             # 构建单个条件的 Q 对象
-            q = cls._build_single_q(db_field, f.operator, f.value)
+            q = cls._build_single_q(db_field, f.operator, f.value, is_json_array)
             if q is None:
                 continue
             
@@ -177,8 +225,21 @@ class QueryBuilder:
         return queryset
     
     @classmethod
-    def _build_single_q(cls, field: str, operator: str, value: str) -> Optional[Q]:
+    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:
+            if operator == '==':
+                # 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)
         elif operator == '==':
@@ -219,7 +280,8 @@ class QueryBuilder:
 def apply_filters(
     queryset: QuerySet,
     query_string: str,
-    field_mapping: Dict[str, str]
+    field_mapping: Dict[str, str],
+    json_array_fields: List[str] = None
 ) -> QuerySet:
     """应用过滤条件到 QuerySet
     
@@ -227,6 +289,7 @@ def apply_filters(
         queryset: Django QuerySet
         query_string: 查询语法字符串
         field_mapping: 字段映射
+        json_array_fields: JSON 数组字段列表（使用 __contains 查询）
     
     Returns:
         过滤后的 QuerySet
@@ -242,6 +305,9 @@ def apply_filters(
         
         # 混合查询
         apply_filters(qs, 'type="xss" || type="sqli" && severity="high"', mapping)
+        
+        # JSON 数组字段查询
+        apply_filters(qs, 'implies="PHP"', mapping, json_array_fields=['implies'])
     """
     if not query_string or not query_string.strip():
         return queryset
@@ -253,7 +319,12 @@ def apply_filters(
             return queryset
         
         logger.debug(f"解析过滤条件: {filter_groups}")
-        return QueryBuilder.build_query(queryset, filter_groups, field_mapping)
+        return QueryBuilder.build_query(
+            queryset, 
+            filter_groups, 
+            field_mapping,
+            json_array_fields=json_array_fields
+        )
     
     except Exception as e:
         logger.warning(f"过滤解析错误: {e}, query: {query_string}")

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(
-                {'error': '请提供用户名和密码'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                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({
-                'message': '登录成功',
-                'user': {
-                    'id': user.id,
-                    'username': user.username,
-                    'isStaff': user.is_staff,
-                    'isSuperuser': user.is_superuser,
+            return success_response(
+                data={
+                    'user': {
+                        'id': user.id,
+                        'username': user.username,
+                        'isStaff': user.is_staff,
+                        '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(
-                {'error': '用户名或密码错误'},
-                status=status.HTTP_401_UNAUTHORIZED
+            return error_response(
+                code=ErrorCodes.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({
-                    'authenticated': True,
-                    'user': {
-                        'id': user.id,
-                        'username': user.username,
-                        'isStaff': user.is_staff,
-                        'isSuperuser': user.is_superuser,
+                return success_response(
+                    data={
+                        'authenticated': True,
+                        'user': {
+                            'id': user.id,
+                            'username': user.username,
+                            'isStaff': user.is_staff,
+                            'isSuperuser': user.is_superuser,
+                        }
                     }
-                })
+                )
             except User.DoesNotExist:
                 pass
         
-        return Response({
-            'authenticated': False,
-            'user': None
-        })
+        return success_response(
+            data={
+                '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）
-        from django.contrib.auth import get_user_model
-        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
-            )
+        # 使用全局权限类验证，request.user 已经是认证用户
+        user = request.user
         
         # 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(
-                {'error': '请提供旧密码和新密码'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Old password and new password are required',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         if not user.check_password(old_password):
-            return Response(
-                {'error': '旧密码错误'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                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):
     """
@@ -28,21 +69,14 @@ 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)
@@ -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)
-            return Response({"content": content})
-        except ValueError:
-            return Response({"error": "lines 参数必须是整数"}, status=status.HTTP_400_BAD_REQUEST)
+            content = self.service.get_logs_content(filename=filename, lines=lines)
+            return success_response(data={"content": content})
+        except ValueError as e:
+            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):
-        """连接时加入对应 Worker 的组并自动建立 SSH 连接"""
+    async def on_connect(self):
+        """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}'
         
@@ -242,8 +242,9 @@ class WorkerDeployConsumer(AsyncWebsocketConsumer):
             return
 
         # 远程 Worker 通过 nginx HTTPS 访问（nginx 反代到后端 8888）
-        # 使用 https://{PUBLIC_HOST} 而不是直连 8888 端口
-        heartbeat_api_url = f"https://{public_host}"  # 基础 URL，agent 会加 /api/...
+        # 使用 https://{PUBLIC_HOST}:{PUBLIC_PORT} 而不是直连 8888 端口
+        public_port = getattr(settings, 'PUBLIC_PORT', '8083')
+        heartbeat_api_url = f"https://{public_host}:{public_port}"
 
         session_name = f'xingrin_deploy_{self.worker_id}'
         remote_script_path = '/tmp/xingrin_deploy.sh'

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

@@ -15,9 +15,10 @@
 """
 
 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
 
@@ -44,10 +45,12 @@ 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 {}
-        except yaml.YAMLError as e:
+            config_dict = yaml_parser.load(default_config) or {}
+        except Exception as e:
             self.stdout.write(self.style.ERROR(f'引擎配置 YAML 解析失败: {e}'))
             return
 
@@ -83,15 +86,13 @@ 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(
-                    single_config,
-                    sort_keys=False,
-                    allow_unicode=True,
-                )
-            except yaml.YAMLError as e:
+                stream = StringIO()
+                yaml_parser.dump(single_config, stream)
+                single_yaml = stream.getvalue()
+            except Exception as e:
                 self.stdout.write(self.style.ERROR(f'生成子引擎 {scan_type} 配置失败: {e}'))
                 continue
 

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

@@ -0,0 +1,205 @@
+"""初始化内置指纹库
+
+- 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。
+"""
+
+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,
+    FingersFingerprint,
+    FingerPrintHubFingerprint,
+    ARLFingerprint,
+)
+from apps.engine.services.fingerprints import (
+    EholeFingerprintService,
+    GobyFingerprintService,
+    WappalyzerFingerprintService,
+    FingersFingerprintService,
+    FingerPrintHubFingerprintService,
+    ARLFingerprintService,
+)
+
+
+logger = logging.getLogger(__name__)
+
+
+# 内置指纹配置
+DEFAULT_FINGERPRINTS = [
+    {
+        "type": "ehole",
+        "filename": "ehole.json",
+        "model": EholeFingerprint,
+        "service": EholeFingerprintService,
+        "data_key": "fingerprint",  # JSON 中指纹数组的 key
+        "file_format": "json",
+    },
+    {
+        "type": "goby",
+        "filename": "goby.json",
+        "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",
+        "filename": "wappalyzer.json",
+        "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",
+    },
+]
+
+
+class Command(BaseCommand):
+    help = "初始化内置指纹库"
+
+    def handle(self, *args, **options):
+        project_base = Path(settings.BASE_DIR).parent  # /app/backend -> /app
+        fingerprints_dir = project_base / "backend" / "fingerprints"
+
+        initialized = 0
+        skipped = 0
+        failed = 0
+
+        for item in DEFAULT_FINGERPRINTS:
+            fp_type = item["type"]
+            filename = item["filename"]
+            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()
+            if existing_count > 0:
+                self.stdout.write(self.style.SUCCESS(
+                    f"[{fp_type}] 数据库已有 {existing_count} 条记录，跳过初始化"
+                ))
+                skipped += 1
+                continue
+
+            # 查找源文件
+            src_path = fingerprints_dir / filename
+            if not src_path.exists():
+                self.stdout.write(self.style.WARNING(
+                    f"[{fp_type}] 未找到内置指纹文件: {src_path}，跳过"
+                ))
+                failed += 1
+                continue
+
+            # 读取并解析文件（支持 JSON 和 YAML）
+            try:
+                with open(src_path, "r", encoding="utf-8") as f:
+                    if file_format == "yaml":
+                        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}"
+                ))
+                failed += 1
+                continue
+
+            # 提取指纹数据（根据不同格式处理）
+            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"
+                ))
+                failed += 1
+                continue
+
+            # 使用 Service 批量导入
+            try:
+                service = service_class()
+                result = service.batch_create_fingerprints(fingerprints)
+                created = result.get("created", 0)
+                failed_count = result.get("failed", 0)
+
+                self.stdout.write(self.style.SUCCESS(
+                    f"[{fp_type}] 导入成功: 创建 {created} 条，失败 {failed_count} 条"
+                ))
+                initialized += 1
+            except Exception as exc:
+                self.stdout.write(self.style.ERROR(
+                    f"[{fp_type}] 导入失败: {exc}"
+                ))
+                failed += 1
+                continue
+
+        self.stdout.write(self.style.SUCCESS(
+            f"指纹初始化完成: 成功 {initialized}, 已存在跳过 {skipped}, 失败 {failed}"
+        ))
+
+    def _extract_fingerprints(self, json_data, data_key, fp_type):
+        """
+        根据不同格式提取指纹数据，兼容数组和对象两种格式
+        
+        支持的格式：
+        - 数组格式: [...] 或 {"key": [...]}
+        - 对象格式: {...} 或 {"key": {...}} -> 转换为 [{"name": k, ...v}]
+        """
+        # 获取目标数据
+        if data_key is None:
+            # 直接使用整个 JSON
+            target = json_data
+        else:
+            # 从指定 key 获取，支持多个可能的 key（如 apps/technologies）
+            if data_key == "apps":
+                target = json_data.get("apps") or json_data.get("technologies") or {}
+            else:
+                target = json_data.get(data_key, [])
+        
+        # 根据数据类型处理
+        if isinstance(target, list):
+            # 已经是数组格式，直接返回
+            return target
+        elif isinstance(target, dict):
+            # 对象格式，转换为数组 [{"name": key, ...value}]
+            return [{"name": name, **data} if isinstance(data, dict) else {"name": name}
+                    for name, data in target.items()]
+        
+        return []

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

@@ -3,12 +3,17 @@
 项目安装后执行此命令，自动创建官方模板仓库记录。
 
 使用方式：
-    python manage.py init_nuclei_templates           # 只创建记录
+    python manage.py init_nuclei_templates           # 只创建记录（检测本地已有仓库）
     python manage.py init_nuclei_templates --sync    # 创建并同步（git clone）
 """
 
 import logging
+import subprocess
+from pathlib import Path
+
+from django.conf import settings
 from django.core.management.base import BaseCommand
+from django.utils import timezone
 
 from apps.engine.models import NucleiTemplateRepo
 from apps.engine.services import NucleiTemplateRepoService
@@ -26,6 +31,20 @@ DEFAULT_REPOS = [
 ]
 
 
+def get_local_commit_hash(local_path: Path) -> str:
+    """获取本地 Git 仓库的 commit hash"""
+    if not (local_path / ".git").is_dir():
+        return ""
+    result = subprocess.run(
+        ["git", "-C", str(local_path), "rev-parse", "HEAD"],
+        check=False,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        text=True,
+    )
+    return result.stdout.strip() if result.returncode == 0 else ""
+
+
 class Command(BaseCommand):
     help = "初始化 Nuclei 模板仓库（创建官方模板仓库记录）"
 
@@ -46,6 +65,8 @@ class Command(BaseCommand):
         force = options.get("force", False)
 
         service = NucleiTemplateRepoService()
+        base_dir = Path(getattr(settings, "NUCLEI_TEMPLATES_REPOS_BASE_DIR", "/opt/xingrin/nuclei-repos"))
+        
         created = 0
         skipped = 0
         synced = 0
@@ -87,20 +108,30 @@ class Command(BaseCommand):
 
             # 创建新仓库记录
             try:
+                # 检查本地是否已有仓库（由 install.sh 预下载）
+                local_path = base_dir / name
+                local_commit = get_local_commit_hash(local_path)
+                
                 repo = NucleiTemplateRepo.objects.create(
                     name=name,
                     repo_url=repo_url,
+                    local_path=str(local_path) if local_commit else "",
+                    commit_hash=local_commit,
+                    last_synced_at=timezone.now() if local_commit else None,
                 )
-                self.stdout.write(self.style.SUCCESS(
-                    f"[{name}] 创建成功: id={repo.id}"
-                ))
+                
+                if local_commit:
+                    self.stdout.write(self.style.SUCCESS(
+                        f"[{name}] 创建成功（检测到本地仓库）: commit={local_commit[:8]}"
+                    ))
+                else:
+                    self.stdout.write(self.style.SUCCESS(
+                        f"[{name}] 创建成功: id={repo.id}"
+                    ))
                 created += 1
 
-                # 初始化本地路径
-                service.ensure_local_path(repo)
-
-                # 如果需要同步
-                if do_sync:
+                # 如果本地没有仓库且需要同步
+                if not local_commit and do_sync:
                     try:
                         self.stdout.write(self.style.WARNING(
                             f"[{name}] 正在同步（首次可能需要几分钟）..."

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

@@ -1,7 +1,8 @@
 """初始化所有内置字典 Wordlist 记录
 
-- 目录扫描默认字典: dir_default.txt -> /app/backend/wordlist/dir_default.txt
-- 子域名爆破默认字典: subdomains-top1million-110000.txt -> /app/backend/wordlist/subdomains-top1million-110000.txt
+内置字典从镜像内 /app/backend/wordlist/ 复制到运行时目录 /opt/xingrin/wordlists/：
+- 目录扫描默认字典: dir_default.txt
+- 子域名爆破默认字典: subdomains-top1million-110000.txt
 
 可重复执行：如果已存在同名记录且文件有效则跳过，只在缺失或文件丢失时创建/修复。
 """

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

@@ -0,0 +1,29 @@
+"""Engine Models
+
+导出所有 Engine 模块的 Models
+"""
+
+from .engine import WorkerNode, ScanEngine, Wordlist, NucleiTemplateRepo
+from .fingerprints import (
+    EholeFingerprint,
+    GobyFingerprint,
+    WappalyzerFingerprint,
+    FingersFingerprint,
+    FingerPrintHubFingerprint,
+    ARLFingerprint,
+)
+
+__all__ = [
+    # 核心 Models
+    "WorkerNode",
+    "ScanEngine",
+    "Wordlist",
+    "NucleiTemplateRepo",
+    # 指纹 Models
+    "EholeFingerprint",
+    "GobyFingerprint",
+    "WappalyzerFingerprint",
+    "FingersFingerprint",
+    "FingerPrintHubFingerprint",
+    "ARLFingerprint",
+]

backend/apps/engine/models/engine.py

@@ -1,3 +1,8 @@
+"""Engine 模块核心 Models
+
+包含 WorkerNode, ScanEngine, Wordlist, NucleiTemplateRepo
+"""
+
 from django.db import models
 
 
@@ -78,6 +83,7 @@ class ScanEngine(models.Model):
         indexes = [
             models.Index(fields=['-created_at']),
         ]
+
     def __str__(self):
         return str(self.name or f'ScanEngine {self.id}')
 

backend/apps/engine/models/fingerprints.py

@@ -0,0 +1,195 @@
+"""指纹相关 Models
+
+包含 EHole、Goby、Wappalyzer 等指纹格式的数据模型
+"""
+
+from django.db import models
+
+
+class GobyFingerprint(models.Model):
+    """Goby 格式指纹规则
+    
+    Goby 使用逻辑表达式和规则数组进行匹配：
+    - logic: 逻辑表达式，如 "a||b", "(a&&b)||c"
+    - rule: 规则数组，每条规则包含 label, feature, is_equal
+    """
+    
+    name = models.CharField(max_length=300, unique=True, help_text='产品名称')
+    logic = models.CharField(max_length=500, help_text='逻辑表达式')
+    rule = models.JSONField(default=list, help_text='规则数组')
+    created_at = models.DateTimeField(auto_now_add=True)
+    
+    class Meta:
+        db_table = 'goby_fingerprint'
+        verbose_name = 'Goby 指纹'
+        verbose_name_plural = 'Goby 指纹'
+        ordering = ['-created_at']
+        indexes = [
+            models.Index(fields=['name']),
+            models.Index(fields=['logic']),
+            models.Index(fields=['-created_at']),
+        ]
+    
+    def __str__(self) -> str:
+        return f"{self.name} ({self.logic})"
+
+
+class EholeFingerprint(models.Model):
+    """EHole 格式指纹规则（字段与 ehole.json 一致）"""
+    
+    cms = models.CharField(max_length=200, help_text='产品/CMS名称')
+    method = models.CharField(max_length=200, default='keyword', help_text='匹配方式')
+    location = models.CharField(max_length=200, default='body', help_text='匹配位置')
+    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(max_length=100, blank=True, default='-', help_text='分类')
+    created_at = models.DateTimeField(auto_now_add=True)
+    
+    class Meta:
+        db_table = 'ehole_fingerprint'
+        verbose_name = 'EHole 指纹'
+        verbose_name_plural = 'EHole 指纹'
+        ordering = ['-created_at']
+        indexes = [
+            # 搜索过滤字段索引
+            models.Index(fields=['cms']),
+            models.Index(fields=['method']),
+            models.Index(fields=['location']),
+            models.Index(fields=['type']),
+            models.Index(fields=['is_important']),
+            # 排序字段索引
+            models.Index(fields=['-created_at']),
+        ]
+        constraints = [
+            # 唯一约束：cms + method + location 组合不能重复
+            models.UniqueConstraint(
+                fields=['cms', 'method', 'location'],
+                name='unique_ehole_fingerprint'
+            ),
+        ]
+    
+    def __str__(self) -> str:
+        return f"{self.cms} ({self.method}@{self.location})"
+
+
+class WappalyzerFingerprint(models.Model):
+    """Wappalyzer 格式指纹规则
+    
+    Wappalyzer 支持多种检测方式：cookies, headers, scriptSrc, js, meta, html 等
+    """
+    
+    name = models.CharField(max_length=300, unique=True, help_text='应用名称')
+    cats = models.JSONField(default=list, help_text='分类 ID 数组')
+    cookies = models.JSONField(default=dict, blank=True, help_text='Cookie 检测规则')
+    headers = models.JSONField(default=dict, blank=True, help_text='HTTP Header 检测规则')
+    script_src = models.JSONField(default=list, blank=True, help_text='脚本 URL 正则数组')
+    js = models.JSONField(default=list, blank=True, help_text='JavaScript 变量检测规则')
+    implies = models.JSONField(default=list, blank=True, help_text='依赖关系数组')
+    meta = models.JSONField(default=dict, blank=True, help_text='HTML meta 标签检测规则')
+    html = models.JSONField(default=list, blank=True, help_text='HTML 内容正则数组')
+    description = models.TextField(blank=True, default='', help_text='应用描述')
+    website = models.URLField(max_length=500, blank=True, default='', help_text='官网链接')
+    cpe = models.CharField(max_length=300, blank=True, default='', help_text='CPE 标识符')
+    created_at = models.DateTimeField(auto_now_add=True)
+    
+    class Meta:
+        db_table = 'wappalyzer_fingerprint'
+        verbose_name = 'Wappalyzer 指纹'
+        verbose_name_plural = 'Wappalyzer 指纹'
+        ordering = ['-created_at']
+        indexes = [
+            models.Index(fields=['name']),
+            models.Index(fields=['website']),
+            models.Index(fields=['cpe']),
+            models.Index(fields=['-created_at']),
+        ]
+    
+    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

@@ -88,6 +88,8 @@ def _register_scheduled_jobs(scheduler: BackgroundScheduler):
         replace_existing=True,
     )
     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():

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

@@ -0,0 +1,20 @@
+"""指纹管理 Serializers
+
+导出所有指纹相关的 Serializer 类
+"""
+
+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/ehole.py

@@ -0,0 +1,27 @@
+"""EHole 指纹 Serializer"""
+
+from rest_framework import serializers
+
+from apps.engine.models import EholeFingerprint
+
+
+class EholeFingerprintSerializer(serializers.ModelSerializer):
+    """EHole 指纹序列化器"""
+    
+    class Meta:
+        model = EholeFingerprint
+        fields = ['id', 'cms', 'method', 'location', 'keyword', 
+                  'is_important', 'type', 'created_at']
+        read_only_fields = ['id', 'created_at']
+    
+    def validate_cms(self, value):
+        """校验 cms 字段"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("cms 字段不能为空")
+        return value.strip()
+    
+    def validate_keyword(self, value):
+        """校验 keyword 字段"""
+        if not isinstance(value, list):
+            raise serializers.ValidationError("keyword 必须是数组")
+        return value

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/serializers/fingerprints/goby.py

@@ -0,0 +1,26 @@
+"""Goby 指纹 Serializer"""
+
+from rest_framework import serializers
+
+from apps.engine.models import GobyFingerprint
+
+
+class GobyFingerprintSerializer(serializers.ModelSerializer):
+    """Goby 指纹序列化器"""
+    
+    class Meta:
+        model = GobyFingerprint
+        fields = ['id', 'name', 'logic', '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 isinstance(value, list):
+            raise serializers.ValidationError("rule 必须是数组")
+        return value

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

@@ -0,0 +1,24 @@
+"""Wappalyzer 指纹 Serializer"""
+
+from rest_framework import serializers
+
+from apps.engine.models import WappalyzerFingerprint
+
+
+class WappalyzerFingerprintSerializer(serializers.ModelSerializer):
+    """Wappalyzer 指纹序列化器"""
+    
+    class Meta:
+        model = WappalyzerFingerprint
+        fields = [
+            'id', 'name', 'cats', 'cookies', 'headers', 'script_src',
+            'js', 'implies', 'meta', 'html', 'description', 'website',
+            'cpe', '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()

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

@@ -0,0 +1,22 @@
+"""指纹管理 Services
+
+导出所有指纹相关的 Service 类
+"""
+
+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/base.py

@@ -0,0 +1,144 @@
+"""指纹管理基类 Service
+
+提供通用的批量操作和缓存逻辑，供 EHole/Goby/Wappalyzer 等子类继承
+"""
+
+import json
+import logging
+from typing import Any
+
+logger = logging.getLogger(__name__)
+
+
+class BaseFingerprintService:
+    """指纹管理基类 Service，提供通用的批量操作和缓存逻辑"""
+    
+    model = None  # 子类必须指定
+    BATCH_SIZE = 1000  # 每批处理数量
+    
+    def validate_fingerprint(self, item: dict) -> bool:
+        """
+        校验单条指纹，子类必须实现
+        
+        Args:
+            item: 单条指纹数据
+            
+        Returns:
+            bool: 是否有效
+        """
+        raise NotImplementedError("子类必须实现 validate_fingerprint 方法")
+    
+    def validate_fingerprints(self, raw_data: list) -> tuple[list, list]:
+        """
+        批量校验指纹数据
+        
+        Args:
+            raw_data: 原始指纹数据列表
+            
+        Returns:
+            tuple: (valid_items, invalid_items)
+        """
+        valid, invalid = [], []
+        for item in raw_data:
+            if self.validate_fingerprint(item):
+                valid.append(item)
+            else:
+                invalid.append(item)
+        return valid, invalid
+    
+    def to_model_data(self, item: dict) -> dict:
+        """
+        转换为 Model 字段，子类必须实现
+        
+        Args:
+            item: 原始指纹数据
+            
+        Returns:
+            dict: Model 字段数据
+        """
+        raise NotImplementedError("子类必须实现 to_model_data 方法")
+
+    def bulk_create(self, fingerprints: list) -> int:
+        """
+        批量创建指纹记录（已校验的数据）
+        
+        Args:
+            fingerprints: 已校验的指纹数据列表
+            
+        Returns:
+            int: 成功创建数量
+        """
+        if not fingerprints:
+            return 0
+        
+        objects = [self.model(**self.to_model_data(item)) for item in fingerprints]
+        created = self.model.objects.bulk_create(objects, ignore_conflicts=True)
+        return len(created)
+    
+    def batch_create_fingerprints(self, raw_data: list) -> dict:
+        """
+        完整流程：分批校验 + 批量创建
+        
+        Args:
+            raw_data: 原始指纹数据列表
+            
+        Returns:
+            dict: {'created': int, 'failed': int}
+        """
+        total_created = 0
+        total_failed = 0
+        
+        for i in range(0, len(raw_data), self.BATCH_SIZE):
+            batch = raw_data[i:i + self.BATCH_SIZE]
+            valid, invalid = self.validate_fingerprints(batch)
+            total_created += self.bulk_create(valid)
+            total_failed += len(invalid)
+        
+        logger.info(
+            "批量创建指纹完成: created=%d, failed=%d, total=%d",
+            total_created, total_failed, len(raw_data)
+        )
+        return {'created': total_created, 'failed': total_failed}
+    
+    def get_export_data(self) -> dict:
+        """
+        获取导出数据，子类必须实现
+        
+        Returns:
+            dict: 导出的 JSON 数据
+        """
+        raise NotImplementedError("子类必须实现 get_export_data 方法")
+    
+    def export_to_file(self, output_path: str) -> int:
+        """
+        导出所有指纹到 JSON 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:
+            json.dump(data, f, ensure_ascii=False)
+        count = len(data.get('fingerprint', []))
+        logger.info("导出指纹文件: %s, 数量: %d", output_path, count)
+        return count
+    
+    def get_fingerprint_version(self) -> str:
+        """
+        获取指纹库版本标识（用于缓存校验）
+        
+        Returns:
+            str: 版本标识，格式 "{count}_{latest_timestamp}"
+        
+        版本变化场景：
+        - 新增记录 → count 变化
+        - 删除记录 → count 变化
+        - 清空全部 → count 变为 0
+        """
+        count = self.model.objects.count()
+        latest = self.model.objects.order_by('-created_at').first()
+        latest_ts = int(latest.created_at.timestamp()) if latest else 0
+        return f"{count}_{latest_ts}"

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

@@ -0,0 +1,84 @@
+"""EHole 指纹管理 Service
+
+实现 EHole 格式指纹的校验、转换和导出逻辑
+"""
+
+from apps.engine.models import EholeFingerprint
+from .base import BaseFingerprintService
+
+
+class EholeFingerprintService(BaseFingerprintService):
+    """EHole 指纹管理服务（继承基类，实现 EHole 特定逻辑）"""
+    
+    model = EholeFingerprint
+    
+    def validate_fingerprint(self, item: dict) -> bool:
+        """
+        校验单条 EHole 指纹
+        
+        校验规则：
+        - cms 字段必须存在且非空
+        - keyword 字段必须是数组
+        
+        Args:
+            item: 单条指纹数据
+            
+        Returns:
+            bool: 是否有效
+        """
+        cms = item.get('cms', '')
+        keyword = item.get('keyword')
+        return bool(cms and str(cms).strip()) and isinstance(keyword, list)
+    
+    def to_model_data(self, item: dict) -> dict:
+        """
+        转换 EHole JSON 格式为 Model 字段
+        
+        字段映射：
+        - isImportant (JSON) → is_important (Model)
+        
+        Args:
+            item: 原始 EHole JSON 数据
+            
+        Returns:
+            dict: Model 字段数据
+        """
+        return {
+            'cms': str(item.get('cms', '')).strip(),
+            'method': item.get('method', 'keyword'),
+            'location': item.get('location', 'body'),
+            'keyword': item.get('keyword', []),
+            'is_important': item.get('isImportant', False),
+            'type': item.get('type', '-'),
+        }
+    
+    def get_export_data(self) -> dict:
+        """
+        获取导出数据（EHole JSON 格式）
+        
+        Returns:
+            dict: EHole 格式的 JSON 数据
+            {
+                "fingerprint": [
+                    {"cms": "...", "method": "...", "location": "...", 
+                     "keyword": [...], "isImportant": false, "type": "..."},
+                    ...
+                ],
+                "version": "1000_1703836800"
+            }
+        """
+        fingerprints = self.model.objects.all()
+        data = []
+        for fp in fingerprints:
+            data.append({
+                'cms': fp.cms,
+                'method': fp.method,
+                'location': fp.location,
+                'keyword': fp.keyword,
+                'isImportant': fp.is_important,  # 转回 JSON 格式
+                'type': fp.type,
+            })
+        return {
+            'fingerprint': data,
+            'version': self.get_fingerprint_version(),
+        }

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

@@ -0,0 +1,87 @@
+"""Goby 指纹管理 Service
+
+实现 Goby 格式指纹的校验、转换和导出逻辑
+"""
+
+from apps.engine.models import GobyFingerprint
+from .base import BaseFingerprintService
+
+
+class GobyFingerprintService(BaseFingerprintService):
+    """Goby 指纹管理服务（继承基类，实现 Goby 特定逻辑）"""
+    
+    model = GobyFingerprint
+    
+    def validate_fingerprint(self, item: dict) -> bool:
+        """
+        校验单条 Goby 指纹
+        
+        支持两种格式：
+        1. 标准格式: {"name": "...", "logic": "...", "rule": [...]}
+        2. JSONL 格式: {"product": "...", "rule": "..."}
+        
+        Args:
+            item: 单条指纹数据
+            
+        Returns:
+            bool: 是否有效
+        """
+        # 标准格式：name + logic + rule(数组)
+        name = item.get('name', '')
+        if name and item.get('logic') is not None and isinstance(item.get('rule'), list):
+            return bool(str(name).strip())
+        
+        # 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('product', '')).strip(),
+            'logic': 'or',  # JSONL 格式默认 or 逻辑
+            'rule': [item.get('rule', '')] if item.get('rule') else [],
+        }
+    
+    def get_export_data(self) -> list:
+        """
+        获取导出数据（Goby JSON 格式 - 数组）
+        
+        Returns:
+            list: Goby 格式的 JSON 数据（数组格式）
+            [
+                {"name": "...", "logic": "...", "rule": [...]},
+                ...
+            ]
+        """
+        fingerprints = self.model.objects.all()
+        return [
+            {
+                'name': fp.name,
+                'logic': fp.logic,
+                'rule': fp.rule,
+            }
+            for fp in fingerprints
+        ]

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

@@ -0,0 +1,99 @@
+"""Wappalyzer 指纹管理 Service
+
+实现 Wappalyzer 格式指纹的校验、转换和导出逻辑
+"""
+
+from apps.engine.models import WappalyzerFingerprint
+from .base import BaseFingerprintService
+
+
+class WappalyzerFingerprintService(BaseFingerprintService):
+    """Wappalyzer 指纹管理服务（继承基类，实现 Wappalyzer 特定逻辑）"""
+    
+    model = WappalyzerFingerprint
+    
+    def validate_fingerprint(self, item: dict) -> bool:
+        """
+        校验单条 Wappalyzer 指纹
+        
+        校验规则：
+        - name 字段必须存在且非空（从 apps 对象的 key 传入）
+        
+        Args:
+            item: 单条指纹数据
+            
+        Returns:
+            bool: 是否有效
+        """
+        name = item.get('name', '')
+        return bool(name and str(name).strip())
+    
+    def to_model_data(self, item: dict) -> dict:
+        """
+        转换 Wappalyzer JSON 格式为 Model 字段
+        
+        字段映射：
+        - scriptSrc (JSON) → script_src (Model)
+        
+        Args:
+            item: 原始 Wappalyzer JSON 数据
+            
+        Returns:
+            dict: Model 字段数据
+        """
+        return {
+            'name': str(item.get('name', '')).strip(),
+            'cats': item.get('cats', []),
+            'cookies': item.get('cookies', {}),
+            'headers': item.get('headers', {}),
+            'script_src': item.get('scriptSrc', []),  # JSON: scriptSrc -> Model: script_src
+            'js': item.get('js', []),
+            'implies': item.get('implies', []),
+            'meta': item.get('meta', {}),
+            'html': item.get('html', []),
+            'description': item.get('description', ''),
+            'website': item.get('website', ''),
+            'cpe': item.get('cpe', ''),
+        }
+    
+    def get_export_data(self) -> dict:
+        """
+        获取导出数据（Wappalyzer JSON 格式）
+        
+        Returns:
+            dict: Wappalyzer 格式的 JSON 数据
+            {
+                "apps": {
+                    "AppName": {"cats": [...], "cookies": {...}, ...},
+                    ...
+                }
+            }
+        """
+        fingerprints = self.model.objects.all()
+        apps = {}
+        for fp in fingerprints:
+            app_data = {}
+            if fp.cats:
+                app_data['cats'] = fp.cats
+            if fp.cookies:
+                app_data['cookies'] = fp.cookies
+            if fp.headers:
+                app_data['headers'] = fp.headers
+            if fp.script_src:
+                app_data['scriptSrc'] = fp.script_src  # Model: script_src -> JSON: scriptSrc
+            if fp.js:
+                app_data['js'] = fp.js
+            if fp.implies:
+                app_data['implies'] = fp.implies
+            if fp.meta:
+                app_data['meta'] = fp.meta
+            if fp.html:
+                app_data['html'] = fp.html
+            if fp.description:
+                app_data['description'] = fp.description
+            if fp.website:
+                app_data['website'] = fp.website
+            if fp.cpe:
+                app_data['cpe'] = fp.cpe
+            apps[fp.name] = app_data
+        return {'apps': apps}

backend/apps/engine/services/nuclei_template_repo_service.py

@@ -196,6 +196,9 @@ class NucleiTemplateRepoService:
         cmd: List[str]
         action: str
 
+        # 直接使用原始 URL（不再使用 Git 加速）
+        repo_url = obj.repo_url
+
         # 判断是 clone 还是 pull
         if git_dir.is_dir():
             # 检查远程地址是否变化
@@ -208,12 +211,13 @@ class NucleiTemplateRepoService:
             )
             current_url = current_remote.stdout.strip() if current_remote.returncode == 0 else ""
             
-            if current_url != obj.repo_url:
+            # 检查是否需要重新 clone
+            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", obj.repo_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
@@ -224,7 +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", obj.repo_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

@@ -76,8 +76,8 @@ class TaskDistributor:
         self.docker_image = settings.TASK_EXECUTOR_IMAGE
         if not self.docker_image:
             raise ValueError("TASK_EXECUTOR_IMAGE 未配置，请确保 IMAGE_TAG 环境变量已设置")
-        self.results_mount = getattr(settings, 'CONTAINER_RESULTS_MOUNT', '/app/backend/results')
-        self.logs_mount = getattr(settings, 'CONTAINER_LOGS_MOUNT', '/app/backend/logs')
+        # 统一使用 /opt/xingrin 下的路径
+        self.logs_mount = "/opt/xingrin/logs"
         self.submit_interval = getattr(settings, 'TASK_SUBMIT_INTERVAL', 5)
     
     def get_online_workers(self) -> list[WorkerNode]:
@@ -153,30 +153,68 @@ class TaskDistributor:
             else:
                 scored_workers.append((worker, score, cpu, mem))
         
-        # 降级策略：如果没有正常负载的，等待后重新选择
+        # 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:
-                # 高负载时先等待，给系统喘息时间（默认 60 秒）
+                # 高负载等待参数（默认每 60 秒检测一次，最多 10 次）
                 high_load_wait = getattr(settings, 'HIGH_LOAD_WAIT_SECONDS', 60)
-                logger.warning("所有 Worker 高负载，等待 %d 秒后重试...", high_load_wait)
-                time.sleep(high_load_wait)
+                high_load_max_retries = getattr(settings, 'HIGH_LOAD_MAX_RETRIES', 10)
                 
-                # 重新选择（递归调用，可能负载已降下来）
-                # 为避免无限递归，这里直接使用高负载中最低的
+                # 开始等待前发送高负载通知
                 high_load_workers.sort(key=lambda x: x[1])
-                best_worker, _, cpu, mem = high_load_workers[0]
-                
-                # 发送高负载通知
+                _, _, first_cpu, first_mem = high_load_workers[0]
                 from apps.common.signals import all_workers_high_load
                 all_workers_high_load.send(
                     sender=self.__class__,
-                    worker_name=best_worker.name,
-                    cpu=cpu,
-                    mem=mem
+                    worker_name="所有节点",
+                    cpu=first_cpu,
+                    mem=first_mem
                 )
                 
-                logger.info("选择 Worker: %s (CPU: %.1f%%, MEM: %.1f%%)", best_worker.name, cpu, mem)
-                return best_worker
+                for retry in range(high_load_max_retries):
+                    logger.warning(
+                        "所有 Worker 高负载，等待 %d 秒后重试... (%d/%d)",
+                        high_load_wait, retry + 1, high_load_max_retries
+                    )
+                    time.sleep(high_load_wait)
+                    
+                    # 重新获取负载数据
+                    loads = worker_load_service.get_all_loads(worker_ids)
+                    
+                    # 重新评估
+                    scored_workers = []
+                    high_load_workers = []
+                    
+                    for worker in workers:
+                        load = loads.get(worker.id)
+                        if not load:
+                            continue
+                        
+                        cpu = load.get('cpu', 0)
+                        mem = load.get('mem', 0)
+                        score = cpu * 0.7 + mem * 0.3
+                        
+                        if cpu > 85 or mem > 85:
+                            high_load_workers.append((worker, score, cpu, mem))
+                        else:
+                            scored_workers.append((worker, score, cpu, mem))
+                    
+                    # 如果有正常负载的 Worker，跳出循环
+                    if scored_workers:
+                        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
+                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%%)",
+                        best_worker.name, cpu, mem
+                    )
+                    return best_worker
+                    return best_worker
             else:
                 logger.warning("没有可用的 Worker")
                 return None
@@ -234,11 +272,10 @@ class TaskDistributor:
         else:
             # 远程：通过 Nginx 反向代理访问（HTTPS，不直连 8888 端口）
             network_arg = ""
-            server_url = f"https://{settings.PUBLIC_HOST}"
+            server_url = f"https://{settings.PUBLIC_HOST}:{settings.PUBLIC_PORT}"
         
-        # 挂载路径（所有节点统一使用固定路径）
-        host_results_dir = settings.HOST_RESULTS_DIR  # /opt/xingrin/results
-        host_logs_dir = settings.HOST_LOGS_DIR  # /opt/xingrin/logs
+        # 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
@@ -247,19 +284,17 @@ class TaskDistributor:
         env_vars = [
             f"-e SERVER_URL={shlex.quote(server_url)}",
             f"-e IS_LOCAL={is_local_str}",
+            f"-e WORKER_API_KEY={shlex.quote(settings.WORKER_API_KEY)}",  # Worker API 认证密钥
             "-e PREFECT_HOME=/tmp/.prefect",  # 设置 Prefect 数据目录到可写位置
             "-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=DEBUG",  # 启用 DEBUG 级别日志
-            "-e PREFECT_LOGGING_SERVER_LEVEL=DEBUG",  # Server 日志级别
-            "-e PREFECT_DEBUG_MODE=true",  # 启用调试模式
+            "-e PREFECT_LOGGING_LEVEL=WARNING",  # 日志级别（减少 DEBUG 噪音）
         ]
         
-        # 挂载卷
+        # 挂载卷（统一挂载整个 /opt/xingrin 目录）
         volumes = [
-            f"-v {host_results_dir}:{self.results_mount}",
-            f"-v {host_logs_dir}:{self.logs_mount}",
+            f"-v {host_xingrin_dir}:{host_xingrin_dir}",
         ]
         
         # 构建命令行参数
@@ -277,11 +312,14 @@ 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
-        cmd = f'''docker run --rm -d --pull=missing {network_arg} \
-            {' '.join(env_vars)} \
-            {' '.join(volumes)} \
-            {self.docker_image} \
+        # OOM 优先级：--oom-score-adj=1000 让 Worker 在内存不足时优先被杀
+        # - 范围 -1000 到 1000，值越大越容易被 OOM Killer 选中
+        # - 保护 server/nginx/frontend 等核心服务，确保 Web 界面可用
+        cmd = f'''docker run --rm -d --pull=missing {network_arg} \\
+            --oom-score-adj=1000 \\
+            {' '.join(env_vars)} \\
+            {' '.join(volumes)} \\
+            {self.docker_image} \\
             sh -c "{inner_cmd}"'''
         
         return cmd
@@ -520,7 +558,7 @@ class TaskDistributor:
             try:
                 # 构建 docker run 命令（清理过期扫描结果目录）
                 script_args = {
-                    'results_dir': '/app/backend/results',
+                    'results_dir': '/opt/xingrin/results',
                     'retention_days': retention_days,
                 }
                 

backend/apps/engine/urls.py

@@ -7,6 +7,14 @@ from .views import (
     WordlistViewSet,
     NucleiTemplateRepoViewSet,
 )
+from .views.fingerprints import (
+    EholeFingerprintViewSet,
+    GobyFingerprintViewSet,
+    WappalyzerFingerprintViewSet,
+    FingersFingerprintViewSet,
+    FingerPrintHubFingerprintViewSet,
+    ARLFingerprintViewSet,
+)
 
 
 # 创建路由器
@@ -15,6 +23,13 @@ router.register(r"engines", ScanEngineViewSet, basename="engine")
 router.register(r"workers", WorkerNodeViewSet, basename="worker")
 router.register(r"wordlists", WordlistViewSet, basename="wordlist")
 router.register(r"nuclei/repos", NucleiTemplateRepoViewSet, basename="nuclei-repos")
+# 指纹管理
+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

@@ -0,0 +1,22 @@
+"""指纹管理 ViewSets
+
+导出所有指纹相关的 ViewSet 类
+"""
+
+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

@@ -0,0 +1,241 @@
+"""指纹管理基类 ViewSet
+
+提供通用的 CRUD 和批量操作，供 EHole/Goby/Wappalyzer 等子类继承
+"""
+
+import json
+import logging
+
+from django.http import HttpResponse
+from rest_framework import viewsets, status, filters
+from rest_framework.decorators import action
+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__)
+
+
+class BaseFingerprintViewSet(viewsets.ModelViewSet):
+    """指纹管理基类 ViewSet，供 EHole/Goby/Wappalyzer 等子类继承
+    
+    提供的 API：
+    
+    标准 CRUD（继承自 ModelViewSet）：
+    - GET    /                  列表查询（分页 + 智能过滤）
+    - POST   /                  创建单条
+    - GET    /{id}/             获取详情
+    - PUT    /{id}/             更新
+    - DELETE /{id}/             删除
+    
+    批量操作（本类实现）：
+    - POST   /batch_create/     批量创建（JSON body）
+    - POST   /import_file/      文件导入（multipart/form-data，适合 10MB+ 大文件）
+    - 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）：
+    - field="value"      模糊匹配（包含）
+    - field=="value"     精确匹配
+    - 多条件空格分隔     AND 关系
+    - || 或 or           OR 关系
+    
+    子类必须实现：
+    - service_class      Service 类
+    - parse_import_data  解析导入数据格式
+    - get_export_filename 导出文件名
+    """
+    
+    pagination_class = BasePagination
+    filter_backends = [filters.OrderingFilter]
+    ordering = ['-created_at']
+    
+    # 子类必须指定
+    service_class = None  # Service 类
+    
+    # 智能过滤字段映射，子类必须覆盖
+    FILTER_FIELD_MAPPING = {}
+    
+    # JSON 数组字段列表（使用 __contains 查询），子类可覆盖
+    JSON_ARRAY_FIELDS = []
+    
+    def get_queryset(self):
+        """支持智能过滤语法"""
+        queryset = super().get_queryset()
+        filter_query = self.request.query_params.get('filter', None)
+        if filter_query:
+            queryset = apply_filters(
+                queryset, 
+                filter_query, 
+                self.FILTER_FIELD_MAPPING,
+                json_array_fields=getattr(self, 'JSON_ARRAY_FIELDS', [])
+            )
+        return queryset
+    
+    def get_service(self):
+        """获取 Service 实例"""
+        if self.service_class is None:
+            raise NotImplementedError("子类必须指定 service_class")
+        return self.service_class()
+    
+    def parse_import_data(self, json_data: dict) -> list:
+        """
+        解析导入数据，子类必须实现
+        
+        Args:
+            json_data: 解析后的 JSON 数据
+            
+        Returns:
+            list: 指纹数据列表
+        """
+        raise NotImplementedError("子类必须实现 parse_import_data 方法")
+    
+    def get_export_filename(self) -> str:
+        """
+        导出文件名，子类必须实现
+        
+        Returns:
+            str: 文件名
+        """
+        raise NotImplementedError("子类必须实现 get_export_filename 方法")
+
+    @action(detail=False, methods=['post'])
+    def batch_create(self, request):
+        """
+        批量创建指纹规则
+        POST /api/engine/fingerprints/{type}/batch_create/
+        
+        请求格式：
+        {
+            "fingerprints": [
+                {"cms": "WordPress", "method": "keyword", ...},
+                ...
+            ]
+        }
+        
+        返回：
+        {
+            "created": 2,
+            "failed": 0
+        }
+        """
+        fingerprints = request.data.get('fingerprints', [])
+        if not fingerprints:
+            raise ValidationError('fingerprints 不能为空')
+        if not isinstance(fingerprints, list):
+            raise ValidationError('fingerprints 必须是数组')
+        
+        result = self.get_service().batch_create_fingerprints(fingerprints)
+        return success_response(data=result, status_code=status.HTTP_201_CREATED)
+    
+    @action(detail=False, methods=['post'])
+    def import_file(self, request):
+        """
+        文件导入（适合大文件，10MB+）
+        POST /api/engine/fingerprints/{type}/import_file/
+        
+        请求格式：multipart/form-data
+        - file: JSON 文件（支持标准 JSON 和 JSONL 格式）
+        
+        返回：同 batch_create
+        """
+        file = request.FILES.get('file')
+        if not file:
+            raise ValidationError('缺少文件')
+        
+        try:
+            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 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):
+        """
+        批量删除
+        POST /api/engine/fingerprints/{type}/bulk-delete/
+        
+        请求格式：{"ids": [1, 2, 3]}
+        返回：{"deleted": 3}
+        """
+        ids = request.data.get('ids', [])
+        if not ids:
+            raise ValidationError('ids 不能为空')
+        if not isinstance(ids, list):
+            raise ValidationError('ids 必须是数组')
+        
+        deleted_count = self.queryset.model.objects.filter(id__in=ids).delete()[0]
+        return success_response(data={'deleted': deleted_count})
+    
+    @action(detail=False, methods=['post'], url_path='delete-all')
+    def delete_all(self, request):
+        """
+        删除所有指纹
+        POST /api/engine/fingerprints/{type}/delete-all/
+        
+        返回：{"deleted": 1000}
+        """
+        deleted_count = self.queryset.model.objects.all().delete()[0]
+        return success_response(data={'deleted': deleted_count})
+    
+    @action(detail=False, methods=['get'])
+    def export(self, request):
+        """
+        导出指纹（前端下载）
+        GET /api/engine/fingerprints/{type}/export/
+        
+        返回：JSON 文件下载
+        """
+        data = self.get_service().get_export_data()
+        content = json.dumps(data, ensure_ascii=False, indent=2)
+        response = HttpResponse(content, content_type='application/json')
+        response['Content-Disposition'] = f'attachment; filename="{self.get_export_filename()}"'
+        return response

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

@@ -0,0 +1,67 @@
+"""EHole 指纹管理 ViewSet"""
+
+from apps.common.pagination import BasePagination
+from apps.engine.models import EholeFingerprint
+from apps.engine.serializers.fingerprints import EholeFingerprintSerializer
+from apps.engine.services.fingerprints import EholeFingerprintService
+
+from .base import BaseFingerprintViewSet
+
+
+class EholeFingerprintViewSet(BaseFingerprintViewSet):
+    """EHole 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）：
+    - cms="word"         模糊匹配 cms 字段
+    - cms=="WordPress"   精确匹配
+    - type="CMS"         按类型筛选
+    - method="keyword"   按匹配方式筛选
+    - location="body"    按匹配位置筛选
+    """
+    
+    queryset = EholeFingerprint.objects.all()
+    serializer_class = EholeFingerprintSerializer
+    pagination_class = BasePagination
+    service_class = EholeFingerprintService
+    
+    # 排序配置
+    ordering_fields = ['created_at', 'cms']
+    ordering = ['-created_at']
+    
+    # EHole 过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'cms': 'cms',
+        'method': 'method',
+        'location': 'location',
+        'type': 'type',
+        'isImportant': 'is_important',
+    }
+    
+    def parse_import_data(self, json_data: dict) -> list:
+        """
+        解析 EHole JSON 格式的导入数据
+        
+        输入格式：{"fingerprint": [...]}
+        返回：指纹列表
+        """
+        return json_data.get('fingerprint', [])
+    
+    def get_export_filename(self) -> str:
+        """导出文件名"""
+        return 'ehole.json'

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/fingerprints/goby.py

@@ -0,0 +1,65 @@
+"""Goby 指纹管理 ViewSet"""
+
+from apps.common.pagination import BasePagination
+from apps.engine.models import GobyFingerprint
+from apps.engine.serializers.fingerprints import GobyFingerprintSerializer
+from apps.engine.services.fingerprints import GobyFingerprintService
+
+from .base import BaseFingerprintViewSet
+
+
+class GobyFingerprintViewSet(BaseFingerprintViewSet):
+    """Goby 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=="ProductName" 精确匹配
+    """
+    
+    queryset = GobyFingerprint.objects.all()
+    serializer_class = GobyFingerprintSerializer
+    pagination_class = BasePagination
+    service_class = GobyFingerprintService
+    
+    # 排序配置
+    ordering_fields = ['created_at', 'name']
+    ordering = ['-created_at']
+    
+    # Goby 过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'name': 'name',
+        'logic': 'logic',
+    }
+    
+    def parse_import_data(self, json_data) -> list:
+        """
+        解析 Goby JSON 格式的导入数据
+        
+        Goby 格式是数组格式：[{...}, {...}, ...]
+        
+        输入格式：[{"name": "...", "logic": "...", "rule": [...]}, ...]
+        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 'goby.json'

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

@@ -0,0 +1,75 @@
+"""Wappalyzer 指纹管理 ViewSet"""
+
+from apps.common.pagination import BasePagination
+from apps.engine.models import WappalyzerFingerprint
+from apps.engine.serializers.fingerprints import WappalyzerFingerprintSerializer
+from apps.engine.services.fingerprints import WappalyzerFingerprintService
+
+from .base import BaseFingerprintViewSet
+
+
+class WappalyzerFingerprintViewSet(BaseFingerprintViewSet):
+    """Wappalyzer 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=="AppName"    精确匹配
+    """
+    
+    queryset = WappalyzerFingerprint.objects.all()
+    serializer_class = WappalyzerFingerprintSerializer
+    pagination_class = BasePagination
+    service_class = WappalyzerFingerprintService
+    
+    # 排序配置
+    ordering_fields = ['created_at', 'name']
+    ordering = ['-created_at']
+    
+    # Wappalyzer 过滤字段映射
+    # 注意：implies 是 JSON 数组字段，使用 __contains 查询
+    FILTER_FIELD_MAPPING = {
+        'name': 'name',
+        'description': 'description',
+        'website': 'website',
+        'cpe': 'cpe',
+        'implies': 'implies',  # JSON 数组字段
+    }
+    
+    # JSON 数组字段列表（使用 __contains 查询）
+    JSON_ARRAY_FIELDS = ['implies']
+    
+    def parse_import_data(self, json_data: dict) -> list:
+        """
+        解析 Wappalyzer JSON 格式的导入数据
+        
+        Wappalyzer 格式是 apps 对象格式：{"apps": {"AppName": {...}, ...}}
+        
+        输入格式：{"apps": {"1C-Bitrix": {"cats": [...], ...}, ...}}
+        返回：指纹列表（每个 app 转换为带 name 字段的 dict）
+        """
+        apps = json_data.get('apps', {})
+        fingerprints = []
+        for name, data in apps.items():
+            item = {'name': name, **data}
+            fingerprints.append(item)
+        return fingerprints
+    
+    def get_export_filename(self) -> str:
+        """导出文件名"""
+        return 'wappalyzer.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 Response(result)
+            return error_response(
+                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 Response({"content": content})
+                return error_response(
+                    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(
-            {"message": f"节点 {worker_name} 已删除"},
-            status=status.HTTP_200_OK
+        return success_response(
+            data={'name': worker_name}
         )
     
     @action(detail=True, methods=['post'])
@@ -190,11 +191,13 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
                     worker.status = 'online'
                     worker.save(update_fields=['status'])
         
-        return Response({
-            'status': 'ok',
-            'need_update': need_update,
-            'server_version': server_version
-        })
+        return success_response(
+            data={
+                'status': 'ok',
+                'needUpdate': need_update,
+                'serverVersion': server_version
+            }
+        )
     
     def _trigger_remote_agent_update(self, worker, target_version: str):
         """
@@ -238,7 +241,7 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
                     docker run -d --pull=always \
                         --name xingrin-agent \
                         --restart always \
-                        -e HEARTBEAT_API_URL="https://{django_settings.PUBLIC_HOST}" \
+                        -e HEARTBEAT_API_URL="https://{django_settings.PUBLIC_HOST}:{getattr(django_settings, 'PUBLIC_PORT', '8083')}" \
                         -e WORKER_ID="{worker_id}" \
                         -e IMAGE_TAG="{target_version}" \
                         -v /proc:/host/proc:ro \
@@ -304,9 +307,10 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
         is_local = request.data.get('is_local', True)
         
         if not name:
-            return Response(
-                {'error': '缺少 name 参数'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                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({
-            'worker_id': worker.id,
-            'name': worker.name,
-            'created': created
-        })
+        return success_response(
+            data={
+                'workerId': worker.id,
+                '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
-            - 远程 Worker (is_local=false): db_host=PUBLIC_HOST, redis=PUBLIC_HOST:6379
+            - 本地 Worker (is_local=true): db_host=postgres
+            - 远程 Worker (is_local=false): db_host=PUBLIC_HOST
         """
         from django.conf import settings
         import logging
@@ -365,37 +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({
-            'db': {
-                'host': worker_db_host,
-                'port': str(settings.DATABASES['default']['PORT']),
-                'name': settings.DATABASES['default']['NAME'],
-                'user': settings.DATABASES['default']['USER'],
-                'password': settings.DATABASES['default']['PASSWORD'],
-            },
-            'redisUrl': worker_redis_url,
-            'paths': {
-                'results': getattr(settings, 'CONTAINER_RESULTS_MOUNT', '/app/backend/results'),
-                'logs': getattr(settings, 'CONTAINER_LOGS_MOUNT', '/app/backend/logs'),
-            },
-            'logging': {
-                'level': os.getenv('LOG_LEVEL', 'INFO'),
-                'enableCommandLogging': os.getenv('ENABLE_COMMAND_LOGGING', 'true').lower() == 'true',
-            },
-            'debug': settings.DEBUG
-        })
+        return success_response(
+            data={
+                'db': {
+                    'host': worker_db_host,
+                    'port': str(settings.DATABASES['default']['PORT']),
+                    'name': settings.DATABASES['default']['NAME'],
+                    'user': settings.DATABASES['default']['USER'],
+                    'password': settings.DATABASES['default']['PASSWORD'],
+                },
+                'paths': {
+                    'results': getattr(settings, 'CONTAINER_RESULTS_MOUNT', '/opt/xingrin/results'),
+                    'logs': getattr(settings, 'CONTAINER_LOGS_MOUNT', '/opt/xingrin/logs'),
+                },
+                'logging': {
+                    'level': os.getenv('LOG_LEVEL', 'INFO'),
+                    'enableCommandLogging': os.getenv('ENABLE_COMMAND_LOGGING', 'true').lower() == 'true',
+                },
+                'debug': settings.DEBUG,
+            }
+        )