refactor: replace Chinese comments with English in frontend components

- Replace all Chinese inline comments with English equivalents across 24 frontend component files
- Update JSDoc comments to use English for better code documentation
- Improve code readability and maintainability for international development team
- Standardize comment style across directories, endpoints, ip-addresses, subdomains, and websites components
- Ensure consistency with previous frontend refactoring efforts

.github/workflows/docker-build.yml

@@ -106,16 +106,17 @@ jobs:
             ${{ steps.version.outputs.IS_RELEASE == 'true' && format('{0}/{1}:latest', env.IMAGE_PREFIX, matrix.image) || '' }}
           build-args: |
             IMAGE_TAG=${{ steps.version.outputs.VERSION }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
+          cache-from: type=gha,scope=${{ matrix.image }}
+          cache-to: type=gha,mode=max,scope=${{ matrix.image }}
           provenance: false
           sbom: false
 
   # 所有镜像构建成功后，更新 VERSION 文件
+  # 只有正式版本（不含 -dev, -alpha, -beta, -rc 等后缀）才更新
   update-version:
     runs-on: ubuntu-latest
     needs: build
-    if: startsWith(github.ref, 'refs/tags/v')
+    if: startsWith(github.ref, 'refs/tags/v') && !contains(github.ref, '-')
     steps:
       - name: Checkout
         uses: actions/checkout@v4

README.md

@@ -25,23 +25,16 @@
 
 ---
 
+
 <p align="center">
-  <b>🌗 明暗模式切换</b>
+  <b>🎨 现代化 UI </b>
 </p>
 
 <p align="center">
-  <img src="docs/screenshots/light.png" alt="Light Mode" width="49%">
-  <img src="docs/screenshots/dark.png" alt="Dark Mode" width="49%">
-</p>
-
-<p align="center">
-  <b>🎨 多种 UI 主题</b>
-</p>
-
-<p align="center">
-  <img src="docs/screenshots/bubblegum.png" alt="Bubblegum" width="32%">
-  <img src="docs/screenshots/cosmic-night.png" alt="Cosmic Night" width="32%">
-  <img src="docs/screenshots/quantum-rose.png" alt="Quantum Rose" width="32%">
+  <img src="docs/screenshots/light.png" alt="Light Mode" width="24%">
+  <img src="docs/screenshots/bubblegum.png" alt="Bubblegum" width="24%">
+  <img src="docs/screenshots/cosmic-night.png" alt="Cosmic Night" width="24%">
+  <img src="docs/screenshots/quantum-rose.png" alt="Quantum Rose" width="24%">
 </p>
 
 ## 📚 文档
@@ -184,11 +177,19 @@ 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
+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）
+> - 大幅提升安装速度，避免网络超时
+
 ### 访问服务
 
-- **Web 界面**: `https://localhost` 
+- **Web 界面**: `https://ip:8083` 
 
 ### 常用命令
 
@@ -204,9 +205,6 @@ sudo ./restart.sh
 
 # 卸载
 sudo ./uninstall.sh
-
-# 更新
-sudo ./update.sh
 ```
 
 ## 🤝 反馈与贡献

VERSION

@@ -1 +1 @@
-v1.1.1
+v1.1.14

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

@@ -9,7 +9,7 @@ class WebSiteDTO:
     """网站数据传输对象"""
     target_id: int
     url: str
-    host: str
+    host: str = ''
     title: str = ''
     status_code: Optional[int] = None
     content_length: Optional[int] = None

backend/apps/asset/models/asset_models.py

@@ -22,15 +22,15 @@ class Subdomain(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）'
     )
     name = models.CharField(max_length=1000, help_text='子域名名称')
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='首次发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
         db_table = 'subdomain'
         verbose_name = '子域名'
         verbose_name_plural = '子域名'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['-created_at']),
             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
@@ -71,7 +71,7 @@ class Endpoint(models.Model):
         default='',
         help_text='重定向地址（HTTP 3xx 响应头 Location）'
     )
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
     title = models.CharField(
         max_length=1000,
         blank=True,
@@ -128,13 +128,14 @@ class Endpoint(models.Model):
         db_table = 'endpoint'
         verbose_name = '端点'
         verbose_name_plural = '端点'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
-            models.Index(fields=['-discovered_at']),
+            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=['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
         ]
         constraints = [
             # 普通唯一约束：url + target 组合唯一
@@ -172,7 +173,7 @@ class WebSite(models.Model):
         default='',
         help_text='重定向地址（HTTP 3xx 响应头 Location）'
     )
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
     title = models.CharField(
         max_length=1000,
         blank=True,
@@ -223,12 +224,14 @@ class WebSite(models.Model):
         db_table = 'website'
         verbose_name = '站点'
         verbose_name_plural = '站点'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
-            models.Index(fields=['-discovered_at']),
+            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=['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
         ]
         constraints = [
             # 普通唯一约束：url + target 组合唯一
@@ -293,15 +296,15 @@ class Directory(models.Model):
         help_text='请求耗时（单位：纳秒）'
     )
     
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
         db_table = 'directory'
         verbose_name = '目录'
         verbose_name_plural = '目录'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['-created_at']),
             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
@@ -358,23 +361,23 @@ class HostPortMapping(models.Model):
     )
     
     # ==================== 时间字段 ====================
-    discovered_at = models.DateTimeField(
+    created_at = models.DateTimeField(
         auto_now_add=True,
-        help_text='发现时间'
+        help_text='创建时间'
     )
 
     class Meta:
         db_table = 'host_port_mapping'
         verbose_name = '主机端口映射'
         verbose_name_plural = '主机端口映射'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['target']),           # 优化按目标查询
             models.Index(fields=['host']),             # 优化按主机名查询
             models.Index(fields=['ip']),               # 优化按IP查询
             models.Index(fields=['port']),             # 优化按端口查询
             models.Index(fields=['host', 'ip']),       # 优化组合查询
-            models.Index(fields=['-discovered_at']),   # 优化时间排序
+            models.Index(fields=['-created_at']),   # 优化时间排序
         ]
         constraints = [
             # 复合唯一约束：target + host + ip + port 组合唯一
@@ -408,7 +411,7 @@ class Vulnerability(models.Model):
     )
     
     # ==================== 核心字段 ====================
-    url = models.TextField(help_text='漏洞所在的URL')
+    url = models.CharField(max_length=2000, help_text='漏洞所在的URL')
     vuln_type = models.CharField(max_length=100, help_text='漏洞类型（如 xss, sqli）')
     severity = models.CharField(
         max_length=20,
@@ -422,19 +425,20 @@ class Vulnerability(models.Model):
     raw_output = models.JSONField(blank=True, default=dict, help_text='工具原始输出')
     
     # ==================== 时间字段 ====================
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='首次发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
         db_table = 'vulnerability'
         verbose_name = '漏洞'
         verbose_name_plural = '漏洞'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['target']),
             models.Index(fields=['vuln_type']),
             models.Index(fields=['severity']),
             models.Index(fields=['source']),
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['url']),          # url索引，优化智能过滤搜索
+            models.Index(fields=['-created_at']),
         ]
 
     def __str__(self):

backend/apps/asset/models/snapshot_models.py

@@ -15,17 +15,17 @@ class SubdomainSnapshot(models.Model):
     )
     
     name = models.CharField(max_length=1000, help_text='子域名名称')
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
     
     class Meta:
         db_table = 'subdomain_snapshot'
         verbose_name = '子域名快照'
         verbose_name_plural = '子域名快照'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['scan']),
             models.Index(fields=['name']),
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['-created_at']),
         ]
         constraints = [
             # 唯一约束：同一次扫描中，同一个子域名只能记录一次
@@ -70,18 +70,19 @@ class WebsiteSnapshot(models.Model):
     )
     body_preview = models.TextField(blank=True, default='', help_text='响应体预览')
     vhost = models.BooleanField(null=True, blank=True, help_text='虚拟主机标志')
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
         db_table = 'website_snapshot'
         verbose_name = '网站快照'
         verbose_name_plural = '网站快照'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['scan']),
             models.Index(fields=['url']),
             models.Index(fields=['host']),  # host索引，优化根据主机名查询
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['title']),  # title索引，优化标题搜索
+            models.Index(fields=['-created_at']),
         ]
         constraints = [
             # 唯一约束：同一次扫描中，同一个URL只能记录一次
@@ -118,18 +119,19 @@ class DirectorySnapshot(models.Model):
     lines = models.IntegerField(null=True, blank=True, help_text='响应体行数（按换行符分割）')
     content_type = models.CharField(max_length=200, blank=True, default='', help_text='响应头 Content-Type 值')
     duration = models.BigIntegerField(null=True, blank=True, help_text='请求耗时（单位：纳秒）')
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
         db_table = 'directory_snapshot'
         verbose_name = '目录快照'
         verbose_name_plural = '目录快照'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['scan']),
             models.Index(fields=['url']),
             models.Index(fields=['status']),  # 状态码索引，优化筛选
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['content_type']),  # content_type索引，优化内容类型搜索
+            models.Index(fields=['-created_at']),
         ]
         constraints = [
             # 唯一约束：同一次扫描中，同一个目录URL只能记录一次
@@ -183,16 +185,16 @@ class HostPortMappingSnapshot(models.Model):
     )
     
     # ==================== 时间字段 ====================
-    discovered_at = models.DateTimeField(
+    created_at = models.DateTimeField(
         auto_now_add=True,
-        help_text='发现时间'
+        help_text='创建时间'
     )
 
     class Meta:
         db_table = 'host_port_mapping_snapshot'
         verbose_name = '主机端口映射快照'
         verbose_name_plural = '主机端口映射快照'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['scan']),             # 优化按扫描查询
             models.Index(fields=['host']),             # 优化按主机名查询
@@ -200,7 +202,7 @@ class HostPortMappingSnapshot(models.Model):
             models.Index(fields=['port']),             # 优化按端口查询
             models.Index(fields=['host', 'ip']),       # 优化组合查询
             models.Index(fields=['scan', 'host']),     # 优化扫描+主机查询
-            models.Index(fields=['-discovered_at']),   # 优化时间排序
+            models.Index(fields=['-created_at']),   # 优化时间排序
         ]
         constraints = [
             # 复合唯一约束：同一次扫描中，scan + host + ip + port 组合唯一
@@ -257,19 +259,21 @@ class EndpointSnapshot(models.Model):
         default=list,
         help_text='匹配的GF模式列表'
     )
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
         db_table = 'endpoint_snapshot'
         verbose_name = '端点快照'
         verbose_name_plural = '端点快照'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['scan']),
             models.Index(fields=['url']),
             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=['status_code']),  # 状态码索引，优化筛选
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['webserver']),  # webserver索引，优化服务器搜索
+            models.Index(fields=['-created_at']),
         ]
         constraints = [
             # 唯一约束：同一次扫描中，同一个URL只能记录一次
@@ -302,7 +306,7 @@ class VulnerabilitySnapshot(models.Model):
     )
     
     # ==================== 核心字段 ====================
-    url = models.TextField(help_text='漏洞所在的URL')
+    url = models.CharField(max_length=2000, help_text='漏洞所在的URL')
     vuln_type = models.CharField(max_length=100, help_text='漏洞类型（如 xss, sqli）')
     severity = models.CharField(
         max_length=20,
@@ -316,19 +320,20 @@ class VulnerabilitySnapshot(models.Model):
     raw_output = models.JSONField(blank=True, default=dict, help_text='工具原始输出')
     
     # ==================== 时间字段 ====================
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
         db_table = 'vulnerability_snapshot'
         verbose_name = '漏洞快照'
         verbose_name_plural = '漏洞快照'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['scan']),
+            models.Index(fields=['url']),  # url索引，优化URL搜索
             models.Index(fields=['vuln_type']),
             models.Index(fields=['severity']),
             models.Index(fields=['source']),
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['-created_at']),
         ]
 
     def __str__(self):

backend/apps/asset/repositories/asset/directory_repository.py

@@ -74,13 +74,67 @@ class DjangoDirectoryRepository:
             logger.error(f"批量 upsert Directory 失败: {e}")
             raise
 
+    def bulk_create_ignore_conflicts(self, items: List[DirectoryDTO]) -> int:
+        """
+        批量创建 Directory（存在即跳过）
+        
+        与 bulk_upsert 不同，此方法不会更新已存在的记录。
+        适用于批量添加场景，只提供 URL，没有其他字段数据。
+        
+        注意：自动按模型唯一约束去重，保留最后一条记录。
+        
+        Args:
+            items: Directory DTO 列表
+            
+        Returns:
+            int: 处理的记录数
+        """
+        if not items:
+            return 0
+        
+        try:
+            # 自动按模型唯一约束去重
+            unique_items = deduplicate_for_bulk(items, Directory)
+            
+            directories = [
+                Directory(
+                    target_id=item.target_id,
+                    url=item.url,
+                    status=item.status,
+                    content_length=item.content_length,
+                    words=item.words,
+                    lines=item.lines,
+                    content_type=item.content_type or '',
+                    duration=item.duration
+                )
+                for item in unique_items
+            ]
+            
+            with transaction.atomic():
+                Directory.objects.bulk_create(
+                    directories,
+                    ignore_conflicts=True,
+                    batch_size=1000
+                )
+            
+            logger.debug(f"批量创建 Directory 成功（ignore_conflicts）: {len(unique_items)} 条")
+            return len(unique_items)
+                
+        except Exception as e:
+            logger.error(f"批量创建 Directory 失败: {e}")
+            raise
+
+    def count_by_target(self, target_id: int) -> int:
+        """统计目标下的目录总数"""
+        return Directory.objects.filter(target_id=target_id).count()
+
     def get_all(self):
         """获取所有目录"""
-        return Directory.objects.all().order_by('-discovered_at')
+        return Directory.objects.all().order_by('-created_at')
 
     def get_by_target(self, target_id: int):
         """获取目标下的所有目录"""
-        return Directory.objects.filter(target_id=target_id).order_by('-discovered_at')
+        return Directory.objects.filter(target_id=target_id).order_by('-created_at')
 
     def get_urls_for_export(self, target_id: int, batch_size: int = 1000) -> Iterator[str]:
         """流式导出目标下的所有目录 URL"""
@@ -118,7 +172,7 @@ class DjangoDirectoryRepository:
             .filter(target_id=target_id)
             .values(
                 'url', 'status', 'content_length', 'words',
-                'lines', 'content_type', 'duration', 'discovered_at'
+                'lines', 'content_type', 'duration', 'created_at'
             )
             .order_by('url')
         )

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

@@ -80,7 +80,7 @@ class DjangoEndpointRepository:
     
     def get_all(self):
         """获取所有端点（全局查询）"""
-        return Endpoint.objects.all().order_by('-discovered_at')
+        return Endpoint.objects.all().order_by('-created_at')
     
     def get_by_target(self, target_id: int):
         """
@@ -92,7 +92,7 @@ class DjangoEndpointRepository:
         Returns:
             QuerySet: 端点查询集
         """
-        return Endpoint.objects.filter(target_id=target_id).order_by('-discovered_at')
+        return Endpoint.objects.filter(target_id=target_id).order_by('-created_at')
     
     def count_by_target(self, target_id: int) -> int:
         """
@@ -183,7 +183,7 @@ class DjangoEndpointRepository:
             .values(
                 'url', 'host', 'location', 'title', 'status_code',
                 'content_length', 'content_type', 'webserver', 'tech',
-                'body_preview', 'vhost', 'matched_gf_patterns', 'discovered_at'
+                'body_preview', 'vhost', 'matched_gf_patterns', 'created_at'
             )
             .order_by('url')
         )

backend/apps/asset/repositories/asset/host_port_mapping_repository.py

@@ -1,7 +1,9 @@
 """HostPortMapping Repository - Django ORM 实现"""
 
 import logging
-from typing import List, Iterator
+from typing import List, Iterator, Dict, Optional
+
+from django.db.models import QuerySet, Min
 
 from apps.asset.models.asset_models import HostPortMapping
 from apps.asset.dtos.asset import HostPortMappingDTO
@@ -13,7 +15,10 @@ logger = logging.getLogger(__name__)
 
 @auto_ensure_db_connection
 class DjangoHostPortMappingRepository:
-    """HostPortMapping Repository - Django ORM 实现"""
+    """HostPortMapping Repository - Django ORM 实现
+    
+    职责：纯数据访问，不包含业务逻辑
+    """
 
     def bulk_create_ignore_conflicts(self, items: List[HostPortMappingDTO]) -> int:
         """
@@ -90,72 +95,20 @@ class DjangoHostPortMappingRepository:
         for ip in queryset:
             yield ip
 
-    def get_ip_aggregation_by_target(self, target_id: int, search: str = None):
-        from django.db.models import Min
+    def get_queryset_by_target(self, target_id: int) -> QuerySet:
+        """获取目标下的 QuerySet"""
+        return HostPortMapping.objects.filter(target_id=target_id)
 
-        qs = HostPortMapping.objects.filter(target_id=target_id)
-        if search:
-            qs = qs.filter(ip__icontains=search)
+    def get_all_queryset(self) -> QuerySet:
+        """获取所有记录的 QuerySet"""
+        return HostPortMapping.objects.all()
 
-        ip_aggregated = (
-            qs
-            .values('ip')
-            .annotate(discovered_at=Min('discovered_at'))
-            .order_by('-discovered_at')
-        )
-
-        results = []
-        for item in ip_aggregated:
-            ip = item['ip']
-            mappings = (
-                HostPortMapping.objects
-                .filter(target_id=target_id, ip=ip)
-                .values('host', 'port')
-                .distinct()
-            )
-            hosts = sorted({m['host'] for m in mappings})
-            ports = sorted({m['port'] for m in mappings})
-            results.append({
-                'ip': ip,
-                'hosts': hosts,
-                'ports': ports,
-                'discovered_at': item['discovered_at'],
-            })
-        return results
-
-    def get_all_ip_aggregation(self, search: str = None):
-        """获取所有 IP 聚合数据（全局查询）"""
-        from django.db.models import Min
-
-        qs = HostPortMapping.objects.all()
-        if search:
-            qs = qs.filter(ip__icontains=search)
-
-        ip_aggregated = (
-            qs
-            .values('ip')
-            .annotate(discovered_at=Min('discovered_at'))
-            .order_by('-discovered_at')
-        )
-
-        results = []
-        for item in ip_aggregated:
-            ip = item['ip']
-            mappings = (
-                HostPortMapping.objects
-                .filter(ip=ip)
-                .values('host', 'port')
-                .distinct()
-            )
-            hosts = sorted({m['host'] for m in mappings})
-            ports = sorted({m['port'] for m in mappings})
-            results.append({
-                'ip': ip,
-                'hosts': hosts,
-                'ports': ports,
-                'discovered_at': item['discovered_at'],
-            })
-        return results
+    def get_queryset_by_ip(self, ip: str, target_id: Optional[int] = None) -> QuerySet:
+        """获取指定 IP 的 QuerySet"""
+        qs = HostPortMapping.objects.filter(ip=ip)
+        if target_id:
+            qs = qs.filter(target_id=target_id)
+        return qs
 
     def iter_raw_data_for_export(
         self, 
@@ -174,13 +127,13 @@ class DjangoHostPortMappingRepository:
                 'ip': '192.168.1.1',
                 'host': 'example.com',
                 'port': 80,
-                'discovered_at': datetime
+                'created_at': datetime
             }
         """
         qs = (
             HostPortMapping.objects
             .filter(target_id=target_id)
-            .values('ip', 'host', 'port', 'discovered_at')
+            .values('ip', 'host', 'port', 'created_at')
             .order_by('ip', 'host', 'port')
         )
         

backend/apps/asset/repositories/asset/subdomain_repository.py

@@ -55,11 +55,11 @@ class DjangoSubdomainRepository:
     
     def get_all(self):
         """获取所有子域名"""
-        return Subdomain.objects.all().order_by('-discovered_at')
+        return Subdomain.objects.all().order_by('-created_at')
 
     def get_by_target(self, target_id: int):
         """获取目标下的所有子域名"""
-        return Subdomain.objects.filter(target_id=target_id).order_by('-discovered_at')
+        return Subdomain.objects.filter(target_id=target_id).order_by('-created_at')
     
     def count_by_target(self, target_id: int) -> int:
         """统计目标下的域名数量"""
@@ -96,12 +96,12 @@ class DjangoSubdomainRepository:
             batch_size: 每批数据量
         
         Yields:
-            {'name': 'sub.example.com', 'discovered_at': datetime}
+            {'name': 'sub.example.com', 'created_at': datetime}
         """
         qs = (
             Subdomain.objects
             .filter(target_id=target_id)
-            .values('name', 'discovered_at')
+            .values('name', 'created_at')
             .order_by('name')
         )
         

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

@@ -96,11 +96,11 @@ class DjangoWebSiteRepository:
 
     def get_all(self):
         """获取所有网站"""
-        return WebSite.objects.all().order_by('-discovered_at')
+        return WebSite.objects.all().order_by('-created_at')
 
     def get_by_target(self, target_id: int):
         """获取目标下的所有网站"""
-        return WebSite.objects.filter(target_id=target_id).order_by('-discovered_at')
+        return WebSite.objects.filter(target_id=target_id).order_by('-created_at')
 
     def count_by_target(self, target_id: int) -> int:
         """统计目标下的站点总数"""
@@ -177,7 +177,7 @@ class DjangoWebSiteRepository:
             .values(
                 'url', 'host', 'location', 'title', 'status_code',
                 'content_length', 'content_type', 'webserver', 'tech',
-                'body_preview', 'vhost', 'discovered_at'
+                'body_preview', 'vhost', 'created_at'
             )
             .order_by('url')
         )

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

@@ -78,10 +78,10 @@ class DjangoDirectorySnapshotRepository:
             raise
     
     def get_by_scan(self, scan_id: int):
-        return DirectorySnapshot.objects.filter(scan_id=scan_id).order_by('-discovered_at')
+        return DirectorySnapshot.objects.filter(scan_id=scan_id).order_by('-created_at')
 
     def get_all(self):
-        return DirectorySnapshot.objects.all().order_by('-discovered_at')
+        return DirectorySnapshot.objects.all().order_by('-created_at')
 
     def iter_raw_data_for_export(
         self, 
@@ -103,7 +103,7 @@ class DjangoDirectorySnapshotRepository:
             .filter(scan_id=scan_id)
             .values(
                 'url', 'status', 'content_length', 'words',
-                'lines', 'content_type', 'duration', 'discovered_at'
+                'lines', 'content_type', 'duration', 'created_at'
             )
             .order_by('url')
         )

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

@@ -74,10 +74,10 @@ class DjangoEndpointSnapshotRepository:
             raise
     
     def get_by_scan(self, scan_id: int):
-        return EndpointSnapshot.objects.filter(scan_id=scan_id).order_by('-discovered_at')
+        return EndpointSnapshot.objects.filter(scan_id=scan_id).order_by('-created_at')
 
     def get_all(self):
-        return EndpointSnapshot.objects.all().order_by('-discovered_at')
+        return EndpointSnapshot.objects.all().order_by('-created_at')
 
     def iter_raw_data_for_export(
         self, 
@@ -100,7 +100,7 @@ class DjangoEndpointSnapshotRepository:
             .values(
                 'url', 'host', 'location', 'title', 'status_code',
                 'content_length', 'content_type', 'webserver', 'tech',
-                'body_preview', 'vhost', 'matched_gf_patterns', 'discovered_at'
+                'body_preview', 'vhost', 'matched_gf_patterns', 'created_at'
             )
             .order_by('url')
         )

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

@@ -65,20 +65,28 @@ class DjangoHostPortMappingSnapshotRepository:
             )
             raise
     
-    def get_ip_aggregation_by_scan(self, scan_id: int, search: str = None):
+    def get_ip_aggregation_by_scan(self, scan_id: int, filter_query: str = None):
         from django.db.models import Min
+        from apps.common.utils.filter_utils import apply_filters
 
         qs = HostPortMappingSnapshot.objects.filter(scan_id=scan_id)
-        if search:
-            qs = qs.filter(ip__icontains=search)
+        
+        # 应用智能过滤
+        if filter_query:
+            field_mapping = {
+                'ip': 'ip',
+                'port': 'port',
+                'host': 'host',
+            }
+            qs = apply_filters(qs, filter_query, field_mapping)
 
         ip_aggregated = (
             qs
             .values('ip')
             .annotate(
-                discovered_at=Min('discovered_at')
+                created_at=Min('created_at')
             )
-            .order_by('-discovered_at')
+            .order_by('-created_at')
         )
 
         results = []
@@ -98,24 +106,32 @@ class DjangoHostPortMappingSnapshotRepository:
                 'ip': ip,
                 'hosts': hosts,
                 'ports': ports,
-                'discovered_at': item['discovered_at'],
+                'created_at': item['created_at'],
             })
 
         return results
 
-    def get_all_ip_aggregation(self, search: str = None):
+    def get_all_ip_aggregation(self, filter_query: str = None):
         """获取所有 IP 聚合数据"""
         from django.db.models import Min
+        from apps.common.utils.filter_utils import apply_filters
 
         qs = HostPortMappingSnapshot.objects.all()
-        if search:
-            qs = qs.filter(ip__icontains=search)
+        
+        # 应用智能过滤
+        if filter_query:
+            field_mapping = {
+                'ip': 'ip',
+                'port': 'port',
+                'host': 'host',
+            }
+            qs = apply_filters(qs, filter_query, field_mapping)
 
         ip_aggregated = (
             qs
             .values('ip')
-            .annotate(discovered_at=Min('discovered_at'))
-            .order_by('-discovered_at')
+            .annotate(created_at=Min('created_at'))
+            .order_by('-created_at')
         )
 
         results = []
@@ -133,7 +149,7 @@ class DjangoHostPortMappingSnapshotRepository:
                 'ip': ip,
                 'hosts': hosts,
                 'ports': ports,
-                'discovered_at': item['discovered_at'],
+                'created_at': item['created_at'],
             })
         return results
 
@@ -167,13 +183,13 @@ class DjangoHostPortMappingSnapshotRepository:
                 'ip': '192.168.1.1',
                 'host': 'example.com',
                 'port': 80,
-                'discovered_at': datetime
+                'created_at': datetime
             }
         """
         qs = (
             HostPortMappingSnapshot.objects
             .filter(scan_id=scan_id)
-            .values('ip', 'host', 'port', 'discovered_at')
+            .values('ip', 'host', 'port', 'created_at')
             .order_by('ip', 'host', 'port')
         )
         

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

@@ -61,10 +61,10 @@ class DjangoSubdomainSnapshotRepository:
             raise
     
     def get_by_scan(self, scan_id: int):
-        return SubdomainSnapshot.objects.filter(scan_id=scan_id).order_by('-discovered_at')
+        return SubdomainSnapshot.objects.filter(scan_id=scan_id).order_by('-created_at')
 
     def get_all(self):
-        return SubdomainSnapshot.objects.all().order_by('-discovered_at')
+        return SubdomainSnapshot.objects.all().order_by('-created_at')
 
     def iter_raw_data_for_export(
         self, 
@@ -79,12 +79,12 @@ class DjangoSubdomainSnapshotRepository:
             batch_size: 每批数据量
         
         Yields:
-            {'name': 'sub.example.com', 'discovered_at': datetime}
+            {'name': 'sub.example.com', 'created_at': datetime}
         """
         qs = (
             SubdomainSnapshot.objects
             .filter(scan_id=scan_id)
-            .values('name', 'discovered_at')
+            .values('name', 'created_at')
             .order_by('name')
         )
         

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

@@ -66,7 +66,7 @@ class DjangoVulnerabilitySnapshotRepository:
 
     def get_by_scan(self, scan_id: int):
         """按扫描任务获取漏洞快照 QuerySet。"""
-        return VulnerabilitySnapshot.objects.filter(scan_id=scan_id).order_by("-discovered_at")
+        return VulnerabilitySnapshot.objects.filter(scan_id=scan_id).order_by("-created_at")
 
     def get_all(self):
-        return VulnerabilitySnapshot.objects.all().order_by('-discovered_at')
+        return VulnerabilitySnapshot.objects.all().order_by('-created_at')

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

@@ -74,10 +74,10 @@ class DjangoWebsiteSnapshotRepository:
             raise
     
     def get_by_scan(self, scan_id: int):
-        return WebsiteSnapshot.objects.filter(scan_id=scan_id).order_by('-discovered_at')
+        return WebsiteSnapshot.objects.filter(scan_id=scan_id).order_by('-created_at')
 
     def get_all(self):
-        return WebsiteSnapshot.objects.all().order_by('-discovered_at')
+        return WebsiteSnapshot.objects.all().order_by('-created_at')
 
     def iter_raw_data_for_export(
         self, 
@@ -100,7 +100,7 @@ class DjangoWebsiteSnapshotRepository:
             .values(
                 'url', 'host', 'location', 'title', 'status',
                 'content_length', 'content_type', 'web_server', 'tech',
-                'body_preview', 'vhost', 'discovered_at'
+                'body_preview', 'vhost', 'created_at'
             )
             .order_by('url')
         )
@@ -119,5 +119,5 @@ class DjangoWebsiteSnapshotRepository:
                 'tech': row['tech'],
                 'body_preview': row['body_preview'],
                 'vhost': row['vhost'],
-                'discovered_at': row['discovered_at'],
+                'created_at': row['created_at'],
             }

backend/apps/asset/serializers.py

@@ -26,9 +26,9 @@ class SubdomainSerializer(serializers.ModelSerializer):
     class Meta:
         model = Subdomain
         fields = [
-            'id', 'name', 'discovered_at', 'target'
+            'id', 'name', 'created_at', 'target'
         ]
-        read_only_fields = ['id', 'discovered_at']
+        read_only_fields = ['id', 'created_at']
 
 
 class SubdomainListSerializer(serializers.ModelSerializer):
@@ -41,9 +41,9 @@ class SubdomainListSerializer(serializers.ModelSerializer):
     class Meta:
         model = Subdomain
         fields = [
-            'id', 'name', 'discovered_at'
+            'id', 'name', 'created_at'
         ]
-        read_only_fields = ['id', 'discovered_at']
+        read_only_fields = ['id', 'created_at']
 
 
 # class IPAddressListSerializer(serializers.ModelSerializer):
@@ -87,7 +87,7 @@ class WebSiteSerializer(serializers.ModelSerializer):
             'tech',
             'vhost',
             'subdomain',
-            'discovered_at',
+            'created_at',
         ]
         read_only_fields = fields
 
@@ -107,7 +107,7 @@ class VulnerabilitySerializer(serializers.ModelSerializer):
             'cvss_score',
             'description',
             'raw_output',
-            'discovered_at',
+            'created_at',
         ]
         read_only_fields = fields
 
@@ -126,7 +126,7 @@ class VulnerabilitySnapshotSerializer(serializers.ModelSerializer):
             'cvss_score',
             'description',
             'raw_output',
-            'discovered_at',
+            'created_at',
         ]
         read_only_fields = fields
 
@@ -134,8 +134,8 @@ 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,
@@ -155,8 +155,8 @@ class EndpointListSerializer(serializers.ModelSerializer):
             'body_preview',
             'tech',
             'vhost',
-            'tags',
-            'discovered_at',
+            'gfPatterns',
+            'created_at',
         ]
         read_only_fields = fields
 
@@ -164,7 +164,7 @@ class EndpointListSerializer(serializers.ModelSerializer):
 class DirectorySerializer(serializers.ModelSerializer):
     """目录序列化器"""
     
-    discovered_at = serializers.DateTimeField(read_only=True)
+    created_at = serializers.DateTimeField(read_only=True)
     
     class Meta:
         model = Directory
@@ -177,7 +177,7 @@ class DirectorySerializer(serializers.ModelSerializer):
             'lines',
             'content_type',
             'duration',
-            'discovered_at',
+            'created_at',
         ]
         read_only_fields = fields
 
@@ -190,12 +190,12 @@ class IPAddressAggregatedSerializer(serializers.Serializer):
     - ip: IP 地址
     - hosts: 该 IP 关联的所有主机名列表
     - ports: 该 IP 关联的所有端口列表
-    - discovered_at: 首次发现时间
+    - created_at: 创建时间
     """
     ip = serializers.IPAddressField(read_only=True)
     hosts = serializers.ListField(child=serializers.CharField(), read_only=True)
     ports = serializers.ListField(child=serializers.IntegerField(), read_only=True)
-    discovered_at = serializers.DateTimeField(read_only=True)
+    created_at = serializers.DateTimeField(read_only=True)
 
 
 # ==================== 快照序列化器 ====================
@@ -205,7 +205,7 @@ class SubdomainSnapshotSerializer(serializers.ModelSerializer):
     
     class Meta:
         model = SubdomainSnapshot
-        fields = ['id', 'name', 'discovered_at']
+        fields = ['id', 'name', 'created_at']
         read_only_fields = fields
 
 
@@ -231,7 +231,7 @@ class WebsiteSnapshotSerializer(serializers.ModelSerializer):
             'tech',
             'vhost',
             'subdomain_name',
-            'discovered_at',
+            'created_at',
         ]
         read_only_fields = fields
 
@@ -250,7 +250,7 @@ class DirectorySnapshotSerializer(serializers.ModelSerializer):
             'lines',
             'content_type',
             'duration',
-            'discovered_at',
+            'created_at',
         ]
         read_only_fields = fields
 
@@ -258,8 +258,8 @@ 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,
@@ -280,7 +280,7 @@ class EndpointSnapshotSerializer(serializers.ModelSerializer):
             'body_preview',
             'tech',
             'vhost',
-            'tags',
-            'discovered_at',
+            'gfPatterns',
+            'created_at',
         ]
         read_only_fields = fields

backend/apps/asset/services/asset/directory_service.py

@@ -1,10 +1,12 @@
 """Directory Service - 目录业务逻辑层"""
 
 import logging
-from typing import List, Iterator
+from typing import List, Iterator, Optional
 
 from apps.asset.repositories import DjangoDirectoryRepository
 from apps.asset.dtos import DirectoryDTO
+from apps.common.validators import is_valid_url, is_url_match_target
+from apps.common.utils.filter_utils import apply_filters
 
 logger = logging.getLogger(__name__)
 
@@ -12,6 +14,12 @@ logger = logging.getLogger(__name__)
 class DirectoryService:
     """目录业务逻辑层"""
     
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'url': 'url',
+        'status': 'status',
+    }
+    
     def __init__(self, repository=None):
         """初始化目录服务"""
         self.repo = repository or DjangoDirectoryRepository()
@@ -37,13 +45,75 @@ class DirectoryService:
             logger.error(f"批量 upsert 目录失败: {e}")
             raise
     
-    def get_directories_by_target(self, target_id: int):
-        """获取目标下的所有目录"""
-        return self.repo.get_by_target(target_id)
+    def bulk_create_urls(self, target_id: int, target_name: str, target_type: str, urls: List[str]) -> int:
+        """
+        批量创建目录（仅 URL，使用 ignore_conflicts）
+        
+        验证 URL 格式和匹配，过滤无效/不匹配 URL，去重后批量创建。
+        已存在的记录会被跳过。
+        
+        Args:
+            target_id: 目标 ID
+            target_name: 目标名称（用于匹配验证）
+            target_type: 目标类型 ('domain', 'ip', 'cidr')
+            urls: URL 列表
+            
+        Returns:
+            int: 实际创建的记录数
+        """
+        if not urls:
+            return 0
+        
+        # 过滤有效 URL 并去重
+        valid_urls = []
+        seen = set()
+        
+        for url in urls:
+            if not isinstance(url, str):
+                continue
+            url = url.strip()
+            if not url or url in seen:
+                continue
+            if not is_valid_url(url):
+                continue
+            
+            # 匹配验证（前端已阻止不匹配的提交，后端作为双重保障）
+            if not is_url_match_target(url, target_name, target_type):
+                continue
+            
+            seen.add(url)
+            valid_urls.append(url)
+        
+        if not valid_urls:
+            return 0
+        
+        # 获取创建前的数量
+        count_before = self.repo.count_by_target(target_id)
+        
+        # 创建 DTO 列表并批量创建
+        directory_dtos = [
+            DirectoryDTO(url=url, target_id=target_id)
+            for url in valid_urls
+        ]
+        self.repo.bulk_create_ignore_conflicts(directory_dtos)
+        
+        # 获取创建后的数量
+        count_after = self.repo.count_by_target(target_id)
+        return count_after - count_before
     
-    def get_all(self):
+    def get_directories_by_target(self, target_id: int, filter_query: Optional[str] = None):
+        """获取目标下的所有目录"""
+        queryset = self.repo.get_by_target(target_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
+    
+    def get_all(self, filter_query: Optional[str] = None):
         """获取所有目录"""
-        return self.repo.get_all()
+        queryset = self.repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
     def iter_directory_urls_by_target(self, target_id: int, chunk_size: int = 1000) -> Iterator[str]:
         """流式获取目标下的所有目录 URL"""

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

@@ -5,10 +5,12 @@ Endpoint 服务层
 """
 
 import logging
-from typing import List, Iterator
+from typing import List, Iterator, Optional
 
 from apps.asset.dtos.asset import EndpointDTO
 from apps.asset.repositories.asset import DjangoEndpointRepository
+from apps.common.validators import is_valid_url, is_url_match_target
+from apps.common.utils.filter_utils import apply_filters
 
 logger = logging.getLogger(__name__)
 
@@ -20,6 +22,14 @@ class EndpointService:
     提供 Endpoint（URL/端点）相关的业务逻辑
     """
     
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'url': 'url',
+        'host': 'host',
+        'title': 'title',
+        'status': 'status_code',
+    }
+    
     def __init__(self):
         """初始化 Endpoint 服务"""
         self.repo = DjangoEndpointRepository()
@@ -45,9 +55,68 @@ class EndpointService:
             logger.error(f"批量 upsert 端点失败: {e}")
             raise
     
-    def get_endpoints_by_target(self, target_id: int):
+    def bulk_create_urls(self, target_id: int, target_name: str, target_type: str, urls: List[str]) -> int:
+        """
+        批量创建端点（仅 URL，使用 ignore_conflicts）
+        
+        验证 URL 格式和匹配，过滤无效/不匹配 URL，去重后批量创建。
+        已存在的记录会被跳过。
+        
+        Args:
+            target_id: 目标 ID
+            target_name: 目标名称（用于匹配验证）
+            target_type: 目标类型 ('domain', 'ip', 'cidr')
+            urls: URL 列表
+            
+        Returns:
+            int: 实际创建的记录数
+        """
+        if not urls:
+            return 0
+        
+        # 过滤有效 URL 并去重
+        valid_urls = []
+        seen = set()
+        
+        for url in urls:
+            if not isinstance(url, str):
+                continue
+            url = url.strip()
+            if not url or url in seen:
+                continue
+            if not is_valid_url(url):
+                continue
+            
+            # 匹配验证（前端已阻止不匹配的提交，后端作为双重保障）
+            if not is_url_match_target(url, target_name, target_type):
+                continue
+            
+            seen.add(url)
+            valid_urls.append(url)
+        
+        if not valid_urls:
+            return 0
+        
+        # 获取创建前的数量
+        count_before = self.repo.count_by_target(target_id)
+        
+        # 创建 DTO 列表并批量创建
+        endpoint_dtos = [
+            EndpointDTO(url=url, target_id=target_id)
+            for url in valid_urls
+        ]
+        self.repo.bulk_create_ignore_conflicts(endpoint_dtos)
+        
+        # 获取创建后的数量
+        count_after = self.repo.count_by_target(target_id)
+        return count_after - count_before
+    
+    def get_endpoints_by_target(self, target_id: int, filter_query: Optional[str] = None):
         """获取目标下的所有端点"""
-        return self.repo.get_by_target(target_id)
+        queryset = self.repo.get_by_target(target_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
     
     def count_endpoints_by_target(self, target_id: int) -> int:
         """
@@ -61,9 +130,12 @@ class EndpointService:
         """
         return self.repo.count_by_target(target_id)
 
-    def get_all(self):
+    def get_all(self, filter_query: Optional[str] = None):
         """获取所有端点（全局查询）"""
-        return self.repo.get_all()
+        queryset = self.repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
     
     def iter_endpoint_urls_by_target(self, target_id: int, chunk_size: int = 1000) -> Iterator[str]:
         """流式获取目标下的所有端点 URL，用于导出。"""

backend/apps/asset/services/asset/host_port_mapping_service.py

@@ -1,16 +1,31 @@
 """HostPortMapping Service - 业务逻辑层"""
 
 import logging
-from typing import List, Iterator
+from typing import List, Iterator, Optional, Dict
+
+from django.db.models import Min
 
 from apps.asset.repositories.asset import DjangoHostPortMappingRepository
 from apps.asset.dtos.asset import HostPortMappingDTO
+from apps.common.utils.filter_utils import apply_filters
 
 logger = logging.getLogger(__name__)
 
 
 class HostPortMappingService:
-    """主机端口映射服务 - 负责主机端口映射数据的业务逻辑"""
+    """主机端口映射服务 - 负责主机端口映射数据的业务逻辑
+    
+    职责：
+    - 业务逻辑处理（过滤、聚合）
+    - 调用 Repository 进行数据访问
+    """
+    
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'ip': 'ip',
+        'port': 'port',
+        'host': 'host',
+    }
     
     def __init__(self):
         self.repo = DjangoHostPortMappingRepository()
@@ -49,12 +64,93 @@ class HostPortMappingService:
     def iter_host_port_by_target(self, target_id: int, batch_size: int = 1000):
         return self.repo.get_for_export(target_id=target_id, batch_size=batch_size)
 
-    def get_ip_aggregation_by_target(self, target_id: int, search: str = None):
-        return self.repo.get_ip_aggregation_by_target(target_id, search=search)
+    def get_ip_aggregation_by_target(
+        self, 
+        target_id: int, 
+        filter_query: Optional[str] = None
+    ) -> List[Dict]:
+        """获取目标下的 IP 聚合数据
+        
+        Args:
+            target_id: 目标 ID
+            filter_query: 智能过滤语法字符串
+        
+        Returns:
+            聚合后的 IP 数据列表
+        """
+        # 从 Repository 获取基础 QuerySet
+        qs = self.repo.get_queryset_by_target(target_id)
+        
+        # Service 层应用过滤逻辑
+        if filter_query:
+            qs = apply_filters(qs, filter_query, self.FILTER_FIELD_MAPPING)
+        
+        # Service 层处理聚合逻辑
+        return self._aggregate_by_ip(qs, filter_query, target_id=target_id)
 
-    def get_all_ip_aggregation(self, search: str = None):
-        """获取所有 IP 聚合数据（全局查询）"""
-        return self.repo.get_all_ip_aggregation(search=search)
+    def get_all_ip_aggregation(self, filter_query: Optional[str] = None) -> List[Dict]:
+        """获取所有 IP 聚合数据（全局查询）
+        
+        Args:
+            filter_query: 智能过滤语法字符串
+        
+        Returns:
+            聚合后的 IP 数据列表
+        """
+        # 从 Repository 获取基础 QuerySet
+        qs = self.repo.get_all_queryset()
+        
+        # Service 层应用过滤逻辑
+        if filter_query:
+            qs = apply_filters(qs, filter_query, self.FILTER_FIELD_MAPPING)
+        
+        # Service 层处理聚合逻辑
+        return self._aggregate_by_ip(qs, filter_query)
+
+    def _aggregate_by_ip(
+        self, 
+        qs, 
+        filter_query: Optional[str] = None,
+        target_id: Optional[int] = None
+    ) -> List[Dict]:
+        """按 IP 聚合数据
+        
+        Args:
+            qs: 已过滤的 QuerySet
+            filter_query: 过滤条件（用于子查询）
+            target_id: 目标 ID（用于子查询限定范围）
+        
+        Returns:
+            聚合后的数据列表
+        """
+        ip_aggregated = (
+            qs
+            .values('ip')
+            .annotate(created_at=Min('created_at'))
+            .order_by('-created_at')
+        )
+
+        results = []
+        for item in ip_aggregated:
+            ip = item['ip']
+            
+            # 获取该 IP 的所有 host 和 port（也需要应用过滤条件）
+            mappings_qs = self.repo.get_queryset_by_ip(ip, target_id=target_id)
+            if filter_query:
+                mappings_qs = apply_filters(mappings_qs, filter_query, self.FILTER_FIELD_MAPPING)
+            
+            mappings = mappings_qs.values('host', 'port').distinct()
+            hosts = sorted({m['host'] for m in mappings})
+            ports = sorted({m['port'] for m in mappings})
+            
+            results.append({
+                'ip': ip,
+                'hosts': hosts,
+                'ports': ports,
+                'created_at': item['created_at'],
+            })
+        
+        return results
 
     def iter_ips_by_target(self, target_id: int, batch_size: int = 1000) -> Iterator[str]:
         """流式获取目标下的所有唯一 IP 地址。"""
@@ -68,6 +164,6 @@ class HostPortMappingService:
             target_id: 目标 ID
         
         Yields:
-            原始数据字典 {ip, host, port, discovered_at}
+            原始数据字典 {ip, host, port, created_at}
         """
         return self.repo.iter_raw_data_for_export(target_id=target_id)

backend/apps/asset/services/asset/subdomain_service.py

@@ -1,15 +1,33 @@
 import logging
-from typing import Tuple, List, Dict
+from typing import List, Dict, Optional
+from dataclasses import dataclass
 
 from apps.asset.repositories import DjangoSubdomainRepository
 from apps.asset.dtos import SubdomainDTO
+from apps.common.validators import is_valid_domain
+from apps.common.utils.filter_utils import apply_filters
 
 logger = logging.getLogger(__name__)
 
 
+@dataclass
+class BulkCreateResult:
+    """批量创建结果"""
+    created_count: int
+    skipped_count: int
+    invalid_count: int
+    mismatched_count: int
+    total_received: int
+
+
 class SubdomainService:
     """子域名业务逻辑层"""
     
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'name': 'name',
+    }
+    
     def __init__(self, repository=None):
         """
         初始化子域名服务
@@ -21,30 +39,50 @@ class SubdomainService:
     
     # ==================== 查询操作 ====================
     
-    def get_all(self):
+    def get_all(self, filter_query: Optional[str] = None):
         """
         获取所有子域名
         
+        Args:
+            filter_query: 智能过滤语法字符串
+        
         Returns:
             QuerySet: 子域名查询集
         """
         logger.debug("获取所有子域名")
-        return self.repo.get_all()
+        queryset = self.repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
     
-    # ==================== 创建操作 ====================
-
-    def bulk_create_ignore_conflicts(self, items: List[SubdomainDTO]) -> None:
+    def get_subdomains_by_target(self, target_id: int, filter_query: Optional[str] = None):
         """
-        批量创建子域名，忽略冲突
+        获取目标下的子域名
         
         Args:
-            items: 子域名 DTO 列表
+            target_id: 目标 ID
+            filter_query: 智能过滤语法字符串
         
-        Note:
-            使用 ignore_conflicts 策略，重复记录会被跳过
+        Returns:
+            QuerySet: 子域名查询集
         """
-        logger.debug("批量创建子域名 - 数量: %d", len(items))
-        return self.repo.bulk_create_ignore_conflicts(items)
+        queryset = self.repo.get_by_target(target_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
+
+    def count_subdomains_by_target(self, target_id: int) -> int:
+        """
+        统计目标下的子域名数量
+        
+        Args:
+            target_id: 目标 ID
+        
+        Returns:
+            int: 子域名数量
+        """
+        logger.debug("统计目标下子域名数量 - Target ID: %d", target_id)
+        return self.repo.count_by_target(target_id)
     
     def get_by_names_and_target_id(self, names: set, target_id: int) -> dict:
         """
@@ -71,25 +109,8 @@ class SubdomainService:
             List[str]: 子域名名称列表
         """
         logger.debug("获取目标下所有子域名 - Target ID: %d", target_id)
-        # 通过仓储层统一访问数据库，内部已使用 iterator() 做流式查询
         return list(self.repo.get_domains_for_export(target_id=target_id))
     
-    def get_subdomains_by_target(self, target_id: int):
-        return self.repo.get_by_target(target_id)
-    
-    def count_subdomains_by_target(self, target_id: int) -> int:
-        """
-        统计目标下的子域名数量
-        
-        Args:
-            target_id: 目标 ID
-        
-        Returns:
-            int: 子域名数量
-        """
-        logger.debug("统计目标下子域名数量 - Target ID: %d", target_id)
-        return self.repo.count_by_target(target_id)
-    
     def iter_subdomain_names_by_target(self, target_id: int, chunk_size: int = 1000):
         """
         流式获取目标下的所有子域名名称（内存优化）
@@ -102,7 +123,6 @@ class SubdomainService:
             str: 子域名名称
         """
         logger.debug("流式获取目标下所有子域名 - Target ID: %d, 批次大小: %d", target_id, chunk_size)
-        # 通过仓储层统一访问数据库，内部已使用 iterator() 做流式查询
         return self.repo.get_domains_for_export(target_id=target_id, batch_size=chunk_size)
 
     def iter_raw_data_for_csv_export(self, target_id: int):
@@ -113,9 +133,113 @@ class SubdomainService:
             target_id: 目标 ID
         
         Yields:
-            原始数据字典 {name, discovered_at}
+            原始数据字典 {name, created_at}
         """
         return self.repo.iter_raw_data_for_export(target_id=target_id)
 
+    # ==================== 创建操作 ====================
 
-__all__ = ['SubdomainService']
+    def bulk_create_ignore_conflicts(self, items: List[SubdomainDTO]) -> None:
+        """
+        批量创建子域名，忽略冲突
+        
+        Args:
+            items: 子域名 DTO 列表
+        
+        Note:
+            使用 ignore_conflicts 策略，重复记录会被跳过
+        """
+        logger.debug("批量创建子域名 - 数量: %d", len(items))
+        return self.repo.bulk_create_ignore_conflicts(items)
+
+    def bulk_create_subdomains(
+        self,
+        target_id: int,
+        target_name: str,
+        subdomains: List[str]
+    ) -> BulkCreateResult:
+        """
+        批量创建子域名（带验证）
+        
+        Args:
+            target_id: 目标 ID
+            target_name: 目标域名（用于匹配验证）
+            subdomains: 子域名列表
+        
+        Returns:
+            BulkCreateResult: 创建结果统计
+        """
+        total_received = len(subdomains)
+        target_name = target_name.lower().strip()
+        
+        def is_subdomain_match(subdomain: str) -> bool:
+            """验证子域名是否匹配目标域名"""
+            if subdomain == target_name:
+                return True
+            if subdomain.endswith('.' + target_name):
+                return True
+            return False
+        
+        # 过滤有效的子域名
+        valid_subdomains = []
+        invalid_count = 0
+        mismatched_count = 0
+        
+        for subdomain in subdomains:
+            if not isinstance(subdomain, str) or not subdomain.strip():
+                continue
+            
+            subdomain = subdomain.lower().strip()
+            
+            # 验证格式
+            if not is_valid_domain(subdomain):
+                invalid_count += 1
+                continue
+            
+            # 验证匹配
+            if not is_subdomain_match(subdomain):
+                mismatched_count += 1
+                continue
+            
+            valid_subdomains.append(subdomain)
+        
+        # 去重
+        unique_subdomains = list(set(valid_subdomains))
+        duplicate_count = len(valid_subdomains) - len(unique_subdomains)
+        
+        if not unique_subdomains:
+            return BulkCreateResult(
+                created_count=0,
+                skipped_count=duplicate_count,
+                invalid_count=invalid_count,
+                mismatched_count=mismatched_count,
+                total_received=total_received,
+            )
+        
+        # 获取创建前的数量
+        count_before = self.repo.count_by_target(target_id)
+        
+        # 创建 DTO 列表并批量创建
+        subdomain_dtos = [
+            SubdomainDTO(name=name, target_id=target_id)
+            for name in unique_subdomains
+        ]
+        self.repo.bulk_create_ignore_conflicts(subdomain_dtos)
+        
+        # 获取创建后的数量
+        count_after = self.repo.count_by_target(target_id)
+        created_count = count_after - count_before
+        
+        # 计算因数据库冲突跳过的数量
+        db_skipped = len(unique_subdomains) - created_count
+        
+        return BulkCreateResult(
+            created_count=created_count,
+            skipped_count=duplicate_count + db_skipped,
+            invalid_count=invalid_count,
+            mismatched_count=mismatched_count,
+            total_received=total_received,
+        )
+
+
+__all__ = ['SubdomainService', 'BulkCreateResult']

backend/apps/asset/services/asset/vulnerability_service.py

@@ -1,12 +1,13 @@
 """Vulnerability Service - 漏洞资产业务逻辑层"""
 
 import logging
-from typing import List
+from typing import List, Optional
 
 from apps.asset.models import Vulnerability
 from apps.asset.dtos.asset import VulnerabilityDTO
 from apps.common.decorators import auto_ensure_db_connection
 from apps.common.utils import deduplicate_for_bulk
+from apps.common.utils.filter_utils import apply_filters
 
 logger = logging.getLogger(__name__)
 
@@ -17,6 +18,14 @@ class VulnerabilityService:
 
     当前提供基础的批量创建能力，使用 ignore_conflicts 依赖数据库唯一约束去重。
     """
+    
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'type': 'vuln_type',
+        'severity': 'severity',
+        'source': 'source',
+        'url': 'url',
+    }
 
     def bulk_create_ignore_conflicts(self, items: List[VulnerabilityDTO]) -> None:
         """批量创建漏洞资产记录，忽略冲突。
@@ -63,24 +72,34 @@ class VulnerabilityService:
 
     # ==================== 查询方法 ====================
 
-    def get_all(self):
+    def get_all(self, filter_query: Optional[str] = None):
         """获取所有漏洞 QuerySet（用于全局漏洞列表）。
 
-        Returns:
-            QuerySet[Vulnerability]: 所有漏洞，按发现时间倒序
-        """
-        return Vulnerability.objects.all().order_by("-discovered_at")
+        Args:
+            filter_query: 智能过滤语法字符串
 
-    def get_vulnerabilities_by_target(self, target_id: int):
+        Returns:
+            QuerySet[Vulnerability]: 所有漏洞，按创建时间倒序
+        """
+        queryset = Vulnerability.objects.all().order_by("-created_at")
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
+
+    def get_vulnerabilities_by_target(self, target_id: int, filter_query: Optional[str] = None):
         """按目标获取漏洞 QuerySet（用于分页）。
 
         Args:
             target_id: 目标 ID
+            filter_query: 智能过滤语法字符串
 
         Returns:
-            QuerySet[Vulnerability]: 目标下的所有漏洞，按发现时间倒序
+            QuerySet[Vulnerability]: 目标下的所有漏洞，按创建时间倒序
         """
-        return Vulnerability.objects.filter(target_id=target_id).order_by("-discovered_at")
+        queryset = Vulnerability.objects.filter(target_id=target_id).order_by("-created_at")
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
     def count_by_target(self, target_id: int) -> int:
         """统计目标下的漏洞数量。"""

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

@@ -1,10 +1,12 @@
 """WebSite Service - 网站业务逻辑层"""
 
 import logging
-from typing import List, Iterator
+from typing import List, Iterator, Optional
 
 from apps.asset.repositories import DjangoWebSiteRepository
 from apps.asset.dtos import WebSiteDTO
+from apps.common.validators import is_valid_url, is_url_match_target
+from apps.common.utils.filter_utils import apply_filters
 
 logger = logging.getLogger(__name__)
 
@@ -12,6 +14,14 @@ logger = logging.getLogger(__name__)
 class WebSiteService:
     """网站业务逻辑层"""
     
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'url': 'url',
+        'host': 'host',
+        'title': 'title',
+        'status': 'status_code',
+    }
+    
     def __init__(self, repository=None):
         """初始化网站服务"""
         self.repo = repository or DjangoWebSiteRepository()
@@ -37,13 +47,75 @@ class WebSiteService:
             logger.error(f"批量 upsert 网站失败: {e}")
             raise
     
-    def get_websites_by_target(self, target_id: int):
-        """获取目标下的所有网站"""
-        return self.repo.get_by_target(target_id)
+    def bulk_create_urls(self, target_id: int, target_name: str, target_type: str, urls: List[str]) -> int:
+        """
+        批量创建网站（仅 URL，使用 ignore_conflicts）
+        
+        验证 URL 格式和匹配，过滤无效/不匹配 URL，去重后批量创建。
+        已存在的记录会被跳过。
+        
+        Args:
+            target_id: 目标 ID
+            target_name: 目标名称（用于匹配验证）
+            target_type: 目标类型 ('domain', 'ip', 'cidr')
+            urls: URL 列表
+            
+        Returns:
+            int: 实际创建的记录数
+        """
+        if not urls:
+            return 0
+        
+        # 过滤有效 URL 并去重
+        valid_urls = []
+        seen = set()
+        
+        for url in urls:
+            if not isinstance(url, str):
+                continue
+            url = url.strip()
+            if not url or url in seen:
+                continue
+            if not is_valid_url(url):
+                continue
+            
+            # 匹配验证（前端已阻止不匹配的提交，后端作为双重保障）
+            if not is_url_match_target(url, target_name, target_type):
+                continue
+            
+            seen.add(url)
+            valid_urls.append(url)
+        
+        if not valid_urls:
+            return 0
+        
+        # 获取创建前的数量
+        count_before = self.repo.count_by_target(target_id)
+        
+        # 创建 DTO 列表并批量创建
+        website_dtos = [
+            WebSiteDTO(url=url, target_id=target_id)
+            for url in valid_urls
+        ]
+        self.repo.bulk_create_ignore_conflicts(website_dtos)
+        
+        # 获取创建后的数量
+        count_after = self.repo.count_by_target(target_id)
+        return count_after - count_before
     
-    def get_all(self):
+    def get_websites_by_target(self, target_id: int, filter_query: Optional[str] = None):
+        """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)
+        return queryset
+    
+    def get_all(self, filter_query: Optional[str] = None):
         """获取所有网站"""
-        return self.repo.get_all()
+        queryset = self.repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
     
     def get_by_url(self, url: str, target_id: int) -> int:
         """根据 URL 和 target_id 查找网站 ID"""

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

@@ -50,7 +50,7 @@ class DirectorySnapshotsService:
             
             # 步骤 2: 转换为资产 DTO 并保存到资产表（upsert）
             # - 新记录：插入资产表
-            # - 已存在的记录：更新字段（discovered_at 不更新，保留首次发现时间）
+            # - 已存在的记录：更新字段（created_at 不更新，保留创建时间）
             logger.debug("步骤 2: 同步到资产表（通过 Service 层，upsert）")
             asset_items = [item.to_asset_dto() for item in items]
             
@@ -67,12 +67,29 @@ class DirectorySnapshotsService:
             )
             raise
     
-    def get_by_scan(self, scan_id: int):
-        return self.snapshot_repo.get_by_scan(scan_id)
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'url': 'url',
+        'status': 'status',
+        'content_type': 'content_type',
+    }
+    
+    def get_by_scan(self, scan_id: int, filter_query: str = None):
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_by_scan(scan_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
-    def get_all(self):
+    def get_all(self, filter_query: str = None):
         """获取所有目录快照"""
-        return self.snapshot_repo.get_all()
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
     def iter_directory_urls_by_scan(self, scan_id: int, chunk_size: int = 1000) -> Iterator[str]:
         """流式获取某次扫描下的所有目录 URL。"""

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

@@ -67,12 +67,32 @@ class EndpointSnapshotsService:
             )
             raise
     
-    def get_by_scan(self, scan_id: int):
-        return self.snapshot_repo.get_by_scan(scan_id)
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'url': 'url',
+        'host': 'host',
+        'title': 'title',
+        'status': 'status_code',
+        'webserver': 'webserver',
+        'tech': 'tech',
+    }
+    
+    def get_by_scan(self, scan_id: int, filter_query: str = None):
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_by_scan(scan_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
-    def get_all(self):
+    def get_all(self, filter_query: str = None):
         """获取所有端点快照"""
-        return self.snapshot_repo.get_all()
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
     def iter_endpoint_urls_by_scan(self, scan_id: int, chunk_size: int = 1000) -> Iterator[str]:
         """流式获取某次扫描下的所有端点 URL。"""

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

@@ -69,12 +69,12 @@ class HostPortMappingSnapshotsService:
             )
             raise
     
-    def get_ip_aggregation_by_scan(self, scan_id: int, search: str = None):
-        return self.snapshot_repo.get_ip_aggregation_by_scan(scan_id, search=search)
+    def get_ip_aggregation_by_scan(self, scan_id: int, filter_query: str = None):
+        return self.snapshot_repo.get_ip_aggregation_by_scan(scan_id, filter_query=filter_query)
 
-    def get_all_ip_aggregation(self, search: str = None):
+    def get_all_ip_aggregation(self, filter_query: str = None):
         """获取所有 IP 聚合数据"""
-        return self.snapshot_repo.get_all_ip_aggregation(search=search)
+        return self.snapshot_repo.get_all_ip_aggregation(filter_query=filter_query)
 
     def iter_ips_by_scan(self, scan_id: int, batch_size: int = 1000) -> Iterator[str]:
         """流式获取某次扫描下的所有唯一 IP 地址。"""
@@ -88,6 +88,6 @@ class HostPortMappingSnapshotsService:
             scan_id: 扫描 ID
         
         Yields:
-            原始数据字典 {ip, host, port, discovered_at}
+            原始数据字典 {ip, host, port, created_at}
         """
         return self.snapshot_repo.iter_raw_data_for_export(scan_id=scan_id)

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

@@ -66,12 +66,27 @@ class SubdomainSnapshotsService:
             )
             raise
     
-    def get_by_scan(self, scan_id: int):
-        return self.subdomain_snapshot_repo.get_by_scan(scan_id)
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'name': 'name',
+    }
+    
+    def get_by_scan(self, scan_id: int, filter_query: str = None):
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.subdomain_snapshot_repo.get_by_scan(scan_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
-    def get_all(self):
+    def get_all(self, filter_query: str = None):
         """获取所有子域名快照"""
-        return self.subdomain_snapshot_repo.get_all()
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.subdomain_snapshot_repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
     def iter_subdomain_names_by_scan(self, scan_id: int, chunk_size: int = 1000) -> Iterator[str]:
         queryset = self.subdomain_snapshot_repo.get_by_scan(scan_id)
@@ -86,6 +101,6 @@ class SubdomainSnapshotsService:
             scan_id: 扫描 ID
         
         Yields:
-            原始数据字典 {name, discovered_at}
+            原始数据字典 {name, created_at}
         """
         return self.subdomain_snapshot_repo.iter_raw_data_for_export(scan_id=scan_id)

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

@@ -66,13 +66,31 @@ class VulnerabilitySnapshotsService:
             )
             raise
 
-    def get_by_scan(self, scan_id: int):
-        """按扫描任务获取所有漏洞快照。"""
-        return self.snapshot_repo.get_by_scan(scan_id)
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'type': 'vuln_type',
+        'url': 'url',
+        'severity': 'severity',
+        'source': 'source',
+    }
 
-    def get_all(self):
+    def get_by_scan(self, scan_id: int, filter_query: str = None):
+        """按扫描任务获取所有漏洞快照。"""
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_by_scan(scan_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
+
+    def get_all(self, filter_query: str = None):
         """获取所有漏洞快照"""
-        return self.snapshot_repo.get_all()
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
     def iter_vuln_urls_by_scan(self, scan_id: int, chunk_size: int = 1000) -> Iterator[str]:
         """流式获取某次扫描下的所有漏洞 URL。"""

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

@@ -51,7 +51,7 @@ class WebsiteSnapshotsService:
             
             # 步骤 2: 转换为资产 DTO 并保存到资产表（upsert）
             # - 新记录：插入资产表
-            # - 已存在的记录：更新字段（discovered_at 不更新，保留首次发现时间）
+            # - 已存在的记录：更新字段（created_at 不更新，保留创建时间）
             logger.debug("步骤 2: 同步到资产表（通过 Service 层，upsert）")
             asset_items = [item.to_asset_dto() for item in items]
             
@@ -68,15 +68,35 @@ class WebsiteSnapshotsService:
             )
             raise
     
-    def get_by_scan(self, scan_id: int):
-        return self.snapshot_repo.get_by_scan(scan_id)
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'url': 'url',
+        'host': 'host',
+        'title': 'title',
+        'status': 'status',
+        'webserver': 'web_server',
+        'tech': 'tech',
+    }
+    
+    def get_by_scan(self, scan_id: int, filter_query: str = None):
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_by_scan(scan_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
-    def get_all(self):
+    def get_all(self, filter_query: str = None):
         """获取所有网站快照"""
-        return self.snapshot_repo.get_all()
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
     def iter_website_urls_by_scan(self, scan_id: int, chunk_size: int = 1000) -> Iterator[str]:
-        """流式获取某次扫描下的所有站点 URL（按发现时间倒序）。"""
+        """流式获取某次扫描下的所有站点 URL（按创建时间倒序）。"""
         queryset = self.snapshot_repo.get_by_scan(scan_id)
         for snapshot in queryset.iterator(chunk_size=chunk_size):
             yield snapshot.url

backend/apps/asset/views.py

@@ -126,30 +126,113 @@ class SubdomainViewSet(viewsets.ModelViewSet):
     支持两种访问方式：
     1. 嵌套路由：GET /api/targets/{target_pk}/subdomains/
     2. 独立路由：GET /api/subdomains/（全局查询）
+    
+    支持智能过滤语法（filter 参数）：
+    - name="api"         子域名模糊匹配
+    - name=="api.example.com"  精确匹配
+    - 多条件空格分隔     AND 关系
     """
     
     serializer_class = SubdomainListSerializer
     pagination_class = BasePagination
-    filter_backends = [filters.SearchFilter, filters.OrderingFilter]
-    search_fields = ['name']
-    ordering = ['-discovered_at']
+    filter_backends = [filters.OrderingFilter]
+    ordering = ['-created_at']
     
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
         self.service = SubdomainService()
     
     def get_queryset(self):
-        """根据是否有 target_pk 参数决定查询范围"""
+        """根据是否有 target_pk 参数决定查询范围，支持智能过滤"""
         target_pk = self.kwargs.get('target_pk')
+        filter_query = self.request.query_params.get('filter', None)
+        
         if target_pk:
-            return self.service.get_subdomains_by_target(target_pk)
-        return self.service.get_all()
+            return self.service.get_subdomains_by_target(target_pk, filter_query=filter_query)
+        return self.service.get_all(filter_query=filter_query)
+
+    @action(detail=False, methods=['post'], url_path='bulk-create')
+    def bulk_create(self, request, **kwargs):
+        """批量创建子域名
+        
+        POST /api/targets/{target_pk}/subdomains/bulk-create/
+        
+        请求体:
+        {
+            "subdomains": ["sub1.example.com", "sub2.example.com"]
+        }
+        
+        响应:
+        {
+            "message": "批量创建完成",
+            "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
+            )
+        
+        # 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
+            )
+        
+        # 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
+            )
+        
+        # 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
+            )
+        
+        # 调用 service 层处理
+        try:
+            result = self.service.bulk_create_subdomains(
+                target_id=int(target_pk),
+                target_name=target.name,
+                subdomains=subdomains
+            )
+        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 Response({
+            'message': '批量创建完成',
+            'createdCount': result.created_count,
+            'skippedCount': result.skipped_count,
+            'invalidCount': result.invalid_count,
+            'mismatchedCount': result.mismatched_count,
+            'totalReceived': result.total_received,
+        }, status=status.HTTP_200_OK)
 
     @action(detail=False, methods=['get'], url_path='export')
     def export(self, request, **kwargs):
         """导出子域名为 CSV 格式
         
-        CSV 列：name, discovered_at
+        CSV 列：name, created_at
         """
         from apps.common.utils import generate_csv_rows, format_datetime
         
@@ -159,8 +242,8 @@ class SubdomainViewSet(viewsets.ModelViewSet):
         
         data_iterator = self.service.iter_raw_data_for_csv_export(target_id=target_pk)
         
-        headers = ['name', 'discovered_at']
-        formatters = {'discovered_at': format_datetime}
+        headers = ['name', 'created_at']
+        formatters = {'created_at': format_datetime}
         
         response = StreamingHttpResponse(
             generate_csv_rows(data_iterator, headers, formatters),
@@ -176,30 +259,102 @@ class WebSiteViewSet(viewsets.ModelViewSet):
     支持两种访问方式：
     1. 嵌套路由：GET /api/targets/{target_pk}/websites/
     2. 独立路由：GET /api/websites/（全局查询）
+    
+    支持智能过滤语法（filter 参数）：
+    - url="api"          URL 模糊匹配
+    - 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
+    - 多条件空格分隔     AND 关系
     """
     
     serializer_class = WebSiteSerializer
     pagination_class = BasePagination
-    filter_backends = [filters.SearchFilter, filters.OrderingFilter]
-    search_fields = ['host']
-    ordering = ['-discovered_at']
+    filter_backends = [filters.OrderingFilter]
+    ordering = ['-created_at']
     
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
         self.service = WebSiteService()
     
     def get_queryset(self):
-        """根据是否有 target_pk 参数决定查询范围"""
+        """根据是否有 target_pk 参数决定查询范围，支持智能过滤"""
         target_pk = self.kwargs.get('target_pk')
+        filter_query = self.request.query_params.get('filter', None)
+        
         if target_pk:
-            return self.service.get_websites_by_target(target_pk)
-        return self.service.get_all()
+            return self.service.get_websites_by_target(target_pk, filter_query=filter_query)
+        return self.service.get_all(filter_query=filter_query)
+
+    @action(detail=False, methods=['post'], url_path='bulk-create')
+    def bulk_create(self, request, **kwargs):
+        """批量创建网站
+        
+        POST /api/targets/{target_pk}/websites/bulk-create/
+        
+        请求体:
+        {
+            "urls": ["https://example.com", "https://test.com"]
+        }
+        
+        响应:
+        {
+            "message": "批量创建完成",
+            "createdCount": 10,
+            "mismatchedCount": 2
+        }
+        """
+        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
+            )
+        
+        # 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
+            )
+        
+        # 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
+            )
+        
+        # 调用 service 层处理
+        try:
+            created_count = self.service.bulk_create_urls(
+                target_id=int(target_pk),
+                target_name=target.name,
+                target_type=target.type,
+                urls=urls
+            )
+        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 Response({
+            'message': '批量创建完成',
+            'createdCount': created_count,
+        }, status=status.HTTP_200_OK)
 
     @action(detail=False, methods=['get'], url_path='export')
     def export(self, request, **kwargs):
         """导出网站为 CSV 格式
         
-        CSV 列：url, host, location, title, status_code, content_length, content_type, webserver, tech, body_preview, vhost, discovered_at
+        CSV 列：url, host, location, title, status_code, content_length, content_type, webserver, tech, body_preview, vhost, created_at
         """
         from apps.common.utils import generate_csv_rows, format_datetime, format_list_field
         
@@ -212,10 +367,10 @@ class WebSiteViewSet(viewsets.ModelViewSet):
         headers = [
             'url', 'host', 'location', 'title', 'status_code',
             'content_length', 'content_type', 'webserver', 'tech',
-            'body_preview', 'vhost', 'discovered_at'
+            'body_preview', 'vhost', 'created_at'
         ]
         formatters = {
-            'discovered_at': format_datetime,
+            'created_at': format_datetime,
             'tech': lambda x: format_list_field(x, separator=','),
         }
         
@@ -233,30 +388,100 @@ class DirectoryViewSet(viewsets.ModelViewSet):
     支持两种访问方式：
     1. 嵌套路由：GET /api/targets/{target_pk}/directories/
     2. 独立路由：GET /api/directories/（全局查询）
+    
+    支持智能过滤语法（filter 参数）：
+    - url="admin"        URL 模糊匹配
+    - status="200,301"   状态码多值匹配
+    - 多条件空格分隔     AND 关系
     """
     
     serializer_class = DirectorySerializer
     pagination_class = BasePagination
-    filter_backends = [filters.SearchFilter, filters.OrderingFilter]
-    search_fields = ['url']
-    ordering = ['-discovered_at']
+    filter_backends = [filters.OrderingFilter]
+    ordering = ['-created_at']
     
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
         self.service = DirectoryService()
     
     def get_queryset(self):
-        """根据是否有 target_pk 参数决定查询范围"""
+        """根据是否有 target_pk 参数决定查询范围，支持智能过滤"""
         target_pk = self.kwargs.get('target_pk')
+        filter_query = self.request.query_params.get('filter', None)
+        
         if target_pk:
-            return self.service.get_directories_by_target(target_pk)
-        return self.service.get_all()
+            return self.service.get_directories_by_target(target_pk, filter_query=filter_query)
+        return self.service.get_all(filter_query=filter_query)
+
+    @action(detail=False, methods=['post'], url_path='bulk-create')
+    def bulk_create(self, request, **kwargs):
+        """批量创建目录
+        
+        POST /api/targets/{target_pk}/directories/bulk-create/
+        
+        请求体:
+        {
+            "urls": ["https://example.com/admin", "https://example.com/api"]
+        }
+        
+        响应:
+        {
+            "message": "批量创建完成",
+            "createdCount": 10,
+            "mismatchedCount": 2
+        }
+        """
+        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
+            )
+        
+        # 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
+            )
+        
+        # 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
+            )
+        
+        # 调用 service 层处理
+        try:
+            created_count = self.service.bulk_create_urls(
+                target_id=int(target_pk),
+                target_name=target.name,
+                target_type=target.type,
+                urls=urls
+            )
+        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 Response({
+            'message': '批量创建完成',
+            'createdCount': created_count,
+        }, status=status.HTTP_200_OK)
 
     @action(detail=False, methods=['get'], url_path='export')
     def export(self, request, **kwargs):
         """导出目录为 CSV 格式
         
-        CSV 列：url, status, content_length, words, lines, content_type, duration, discovered_at
+        CSV 列：url, status, content_length, words, lines, content_type, duration, created_at
         """
         from apps.common.utils import generate_csv_rows, format_datetime
         
@@ -268,10 +493,10 @@ class DirectoryViewSet(viewsets.ModelViewSet):
         
         headers = [
             'url', 'status', 'content_length', 'words',
-            'lines', 'content_type', 'duration', 'discovered_at'
+            'lines', 'content_type', 'duration', 'created_at'
         ]
         formatters = {
-            'discovered_at': format_datetime,
+            'created_at': format_datetime,
         }
         
         response = StreamingHttpResponse(
@@ -288,30 +513,102 @@ class EndpointViewSet(viewsets.ModelViewSet):
     支持两种访问方式：
     1. 嵌套路由：GET /api/targets/{target_pk}/endpoints/
     2. 独立路由：GET /api/endpoints/（全局查询）
+    
+    支持智能过滤语法（filter 参数）：
+    - url="api"          URL 模糊匹配
+    - 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
+    - 多条件空格分隔     AND 关系
     """
     
     serializer_class = EndpointListSerializer
     pagination_class = BasePagination
-    filter_backends = [filters.SearchFilter, filters.OrderingFilter]
-    search_fields = ['host']
-    ordering = ['-discovered_at']
+    filter_backends = [filters.OrderingFilter]
+    ordering = ['-created_at']
     
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
         self.service = EndpointService()
     
     def get_queryset(self):
-        """根据是否有 target_pk 参数决定查询范围"""
+        """根据是否有 target_pk 参数决定查询范围，支持智能过滤"""
         target_pk = self.kwargs.get('target_pk')
+        filter_query = self.request.query_params.get('filter', None)
+        
         if target_pk:
-            return self.service.get_endpoints_by_target(target_pk)
-        return self.service.get_all()
+            return self.service.get_endpoints_by_target(target_pk, filter_query=filter_query)
+        return self.service.get_all(filter_query=filter_query)
+
+    @action(detail=False, methods=['post'], url_path='bulk-create')
+    def bulk_create(self, request, **kwargs):
+        """批量创建端点
+        
+        POST /api/targets/{target_pk}/endpoints/bulk-create/
+        
+        请求体:
+        {
+            "urls": ["https://example.com/api/v1", "https://example.com/api/v2"]
+        }
+        
+        响应:
+        {
+            "message": "批量创建完成",
+            "createdCount": 10,
+            "mismatchedCount": 2
+        }
+        """
+        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
+            )
+        
+        # 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
+            )
+        
+        # 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
+            )
+        
+        # 调用 service 层处理
+        try:
+            created_count = self.service.bulk_create_urls(
+                target_id=int(target_pk),
+                target_name=target.name,
+                target_type=target.type,
+                urls=urls
+            )
+        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 Response({
+            'message': '批量创建完成',
+            'createdCount': created_count,
+        }, status=status.HTTP_200_OK)
 
     @action(detail=False, methods=['get'], url_path='export')
     def export(self, request, **kwargs):
         """导出端点为 CSV 格式
         
-        CSV 列：url, host, location, title, status_code, content_length, content_type, webserver, tech, body_preview, vhost, matched_gf_patterns, discovered_at
+        CSV 列：url, host, location, title, status_code, content_length, content_type, webserver, tech, body_preview, vhost, matched_gf_patterns, created_at
         """
         from apps.common.utils import generate_csv_rows, format_datetime, format_list_field
         
@@ -324,10 +621,10 @@ class EndpointViewSet(viewsets.ModelViewSet):
         headers = [
             'url', 'host', 'location', 'title', 'status_code',
             'content_length', 'content_type', 'webserver', 'tech',
-            'body_preview', 'vhost', 'matched_gf_patterns', 'discovered_at'
+            'body_preview', 'vhost', 'matched_gf_patterns', 'created_at'
         ]
         formatters = {
-            'discovered_at': format_datetime,
+            'created_at': format_datetime,
             'tech': lambda x: format_list_field(x, separator=','),
             'matched_gf_patterns': lambda x: format_list_field(x, separator=','),
         }
@@ -349,29 +646,46 @@ class HostPortMappingViewSet(viewsets.ModelViewSet):
     
     返回按 IP 聚合的数据，每个 IP 显示其关联的所有 hosts 和 ports
     
+    支持智能过滤语法（filter 参数）：
+    - ip="192.168"       IP 模糊匹配
+    - port="80,443"      端口多值匹配
+    - host="api"         主机名模糊匹配
+    - 多条件空格分隔     AND 关系
+    
     注意：由于返回的是聚合数据（字典列表），不支持 DRF SearchFilter
     """
     
     serializer_class = IPAddressAggregatedSerializer
     pagination_class = BasePagination
     
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'ip': 'ip',
+        'port': 'port',
+        'host': 'host',
+    }
+    
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
         self.service = HostPortMappingService()
     
     def get_queryset(self):
-        """根据是否有 target_pk 参数决定查询范围，返回按 IP 聚合的数据"""
+        """根据是否有 target_pk 参数决定查询范围，返回按 IP 聚合的数据
+        
+        支持智能过滤语法（filter 参数）
+        """
         target_pk = self.kwargs.get('target_pk')
-        search = self.request.query_params.get('search', None)
+        filter_query = self.request.query_params.get('filter', None)
+        
         if target_pk:
-            return self.service.get_ip_aggregation_by_target(target_pk, search=search)
-        return self.service.get_all_ip_aggregation(search=search)
+            return self.service.get_ip_aggregation_by_target(target_pk, filter_query=filter_query)
+        return self.service.get_all_ip_aggregation(filter_query=filter_query)
 
     @action(detail=False, methods=['get'], url_path='export')
     def export(self, request, **kwargs):
         """导出 IP 地址为 CSV 格式
         
-        CSV 列：ip, host, port, discovered_at
+        CSV 列：ip, host, port, created_at
         """
         from apps.common.utils import generate_csv_rows, format_datetime
         
@@ -383,9 +697,9 @@ class HostPortMappingViewSet(viewsets.ModelViewSet):
         data_iterator = self.service.iter_raw_data_for_csv_export(target_id=target_pk)
         
         # CSV 表头和格式化器
-        headers = ['ip', 'host', 'port', 'discovered_at']
+        headers = ['ip', 'host', 'port', 'created_at']
         formatters = {
-            'discovered_at': format_datetime
+            'created_at': format_datetime
         }
         
         # 生成流式响应
@@ -404,37 +718,50 @@ class VulnerabilityViewSet(viewsets.ModelViewSet):
     支持两种访问方式：
     1. 嵌套路由：GET /api/targets/{target_pk}/vulnerabilities/
     2. 独立路由：GET /api/vulnerabilities/（全局查询）
+    
+    支持智能过滤语法（filter 参数）：
+    - type="xss"         漏洞类型模糊匹配
+    - severity="high"    严重程度匹配
+    - source="nuclei"    来源工具匹配
+    - url="api"          URL 模糊匹配
+    - 多条件空格分隔     AND 关系
     """
     
     serializer_class = VulnerabilitySerializer
     pagination_class = BasePagination
-    filter_backends = [filters.SearchFilter, filters.OrderingFilter]
-    search_fields = ['vuln_type']
-    ordering = ['-discovered_at']
+    filter_backends = [filters.OrderingFilter]
+    ordering = ['-created_at']
     
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
         self.service = VulnerabilityService()
     
     def get_queryset(self):
-        """根据是否有 target_pk 参数决定查询范围"""
+        """根据是否有 target_pk 参数决定查询范围，支持智能过滤"""
         target_pk = self.kwargs.get('target_pk')
+        filter_query = self.request.query_params.get('filter', None)
+        
         if target_pk:
-            return self.service.get_vulnerabilities_by_target(target_pk)
-        return self.service.get_all()
+            return self.service.get_vulnerabilities_by_target(target_pk, filter_query=filter_query)
+        return self.service.get_all(filter_query=filter_query)
 
 
 # ==================== 快照 ViewSet（Scan 嵌套路由） ====================
 
 class SubdomainSnapshotViewSet(viewsets.ModelViewSet):
-    """子域名快照 ViewSet - 嵌套路由：GET /api/scans/{scan_pk}/subdomains/"""
+    """子域名快照 ViewSet - 嵌套路由：GET /api/scans/{scan_pk}/subdomains/
+    
+    支持智能过滤语法（filter 参数）：
+    - name="api"         子域名模糊匹配
+    - name=="api.example.com"  精确匹配
+    - name!="test"       排除匹配
+    """
     
     serializer_class = SubdomainSnapshotSerializer
     pagination_class = BasePagination
-    filter_backends = [filters.SearchFilter, filters.OrderingFilter]
-    search_fields = ['name']
-    ordering_fields = ['name', 'discovered_at']
-    ordering = ['-discovered_at']
+    filter_backends = [filters.OrderingFilter]
+    ordering_fields = ['name', 'created_at']
+    ordering = ['-created_at']
     
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
@@ -442,15 +769,17 @@ class SubdomainSnapshotViewSet(viewsets.ModelViewSet):
     
     def get_queryset(self):
         scan_pk = self.kwargs.get('scan_pk')
+        filter_query = self.request.query_params.get('filter', None)
+        
         if scan_pk:
-            return self.service.get_by_scan(scan_pk)
-        return self.service.get_all()
+            return self.service.get_by_scan(scan_pk, filter_query=filter_query)
+        return self.service.get_all(filter_query=filter_query)
 
     @action(detail=False, methods=['get'], url_path='export')
     def export(self, request, **kwargs):
         """导出子域名快照为 CSV 格式
         
-        CSV 列：name, discovered_at
+        CSV 列：name, created_at
         """
         from apps.common.utils import generate_csv_rows, format_datetime
         
@@ -460,8 +789,8 @@ class SubdomainSnapshotViewSet(viewsets.ModelViewSet):
         
         data_iterator = self.service.iter_raw_data_for_csv_export(scan_id=scan_pk)
         
-        headers = ['name', 'discovered_at']
-        formatters = {'discovered_at': format_datetime}
+        headers = ['name', 'created_at']
+        formatters = {'created_at': format_datetime}
         
         response = StreamingHttpResponse(
             generate_csv_rows(data_iterator, headers, formatters),
@@ -472,13 +801,21 @@ class SubdomainSnapshotViewSet(viewsets.ModelViewSet):
 
 
 class WebsiteSnapshotViewSet(viewsets.ModelViewSet):
-    """网站快照 ViewSet - 嵌套路由：GET /api/scans/{scan_pk}/websites/"""
+    """网站快照 ViewSet - 嵌套路由：GET /api/scans/{scan_pk}/websites/
+    
+    支持智能过滤语法（filter 参数）：
+    - url="api"          URL 模糊匹配
+    - host="example"     主机名模糊匹配
+    - title="login"      标题模糊匹配
+    - status="200"       状态码匹配
+    - webserver="nginx"  服务器类型匹配
+    - tech="php"         技术栈匹配
+    """
     
     serializer_class = WebsiteSnapshotSerializer
     pagination_class = BasePagination
-    filter_backends = [filters.SearchFilter, filters.OrderingFilter]
-    search_fields = ['host']
-    ordering = ['-discovered_at']
+    filter_backends = [filters.OrderingFilter]
+    ordering = ['-created_at']
     
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
@@ -486,15 +823,17 @@ class WebsiteSnapshotViewSet(viewsets.ModelViewSet):
     
     def get_queryset(self):
         scan_pk = self.kwargs.get('scan_pk')
+        filter_query = self.request.query_params.get('filter', None)
+        
         if scan_pk:
-            return self.service.get_by_scan(scan_pk)
-        return self.service.get_all()
+            return self.service.get_by_scan(scan_pk, filter_query=filter_query)
+        return self.service.get_all(filter_query=filter_query)
 
     @action(detail=False, methods=['get'], url_path='export')
     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, discovered_at
+        CSV 列：url, host, location, title, status_code, content_length, content_type, webserver, tech, body_preview, vhost, created_at
         """
         from apps.common.utils import generate_csv_rows, format_datetime, format_list_field
         
@@ -507,10 +846,10 @@ class WebsiteSnapshotViewSet(viewsets.ModelViewSet):
         headers = [
             'url', 'host', 'location', 'title', 'status_code',
             'content_length', 'content_type', 'webserver', 'tech',
-            'body_preview', 'vhost', 'discovered_at'
+            'body_preview', 'vhost', 'created_at'
         ]
         formatters = {
-            'discovered_at': format_datetime,
+            'created_at': format_datetime,
             'tech': lambda x: format_list_field(x, separator=','),
         }
         
@@ -523,13 +862,18 @@ class WebsiteSnapshotViewSet(viewsets.ModelViewSet):
 
 
 class DirectorySnapshotViewSet(viewsets.ModelViewSet):
-    """目录快照 ViewSet - 嵌套路由：GET /api/scans/{scan_pk}/directories/"""
+    """目录快照 ViewSet - 嵌套路由：GET /api/scans/{scan_pk}/directories/
+    
+    支持智能过滤语法（filter 参数）：
+    - url="admin"        URL 模糊匹配
+    - status="200"       状态码匹配
+    - content_type="html" 内容类型匹配
+    """
     
     serializer_class = DirectorySnapshotSerializer
     pagination_class = BasePagination
-    filter_backends = [filters.SearchFilter, filters.OrderingFilter]
-    search_fields = ['url']
-    ordering = ['-discovered_at']
+    filter_backends = [filters.OrderingFilter]
+    ordering = ['-created_at']
     
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
@@ -537,15 +881,17 @@ class DirectorySnapshotViewSet(viewsets.ModelViewSet):
     
     def get_queryset(self):
         scan_pk = self.kwargs.get('scan_pk')
+        filter_query = self.request.query_params.get('filter', None)
+        
         if scan_pk:
-            return self.service.get_by_scan(scan_pk)
-        return self.service.get_all()
+            return self.service.get_by_scan(scan_pk, filter_query=filter_query)
+        return self.service.get_all(filter_query=filter_query)
 
     @action(detail=False, methods=['get'], url_path='export')
     def export(self, request, **kwargs):
         """导出目录快照为 CSV 格式
         
-        CSV 列：url, status, content_length, words, lines, content_type, duration, discovered_at
+        CSV 列：url, status, content_length, words, lines, content_type, duration, created_at
         """
         from apps.common.utils import generate_csv_rows, format_datetime
         
@@ -557,10 +903,10 @@ class DirectorySnapshotViewSet(viewsets.ModelViewSet):
         
         headers = [
             'url', 'status', 'content_length', 'words',
-            'lines', 'content_type', 'duration', 'discovered_at'
+            'lines', 'content_type', 'duration', 'created_at'
         ]
         formatters = {
-            'discovered_at': format_datetime,
+            'created_at': format_datetime,
         }
         
         response = StreamingHttpResponse(
@@ -572,13 +918,21 @@ class DirectorySnapshotViewSet(viewsets.ModelViewSet):
 
 
 class EndpointSnapshotViewSet(viewsets.ModelViewSet):
-    """端点快照 ViewSet - 嵌套路由：GET /api/scans/{scan_pk}/endpoints/"""
+    """端点快照 ViewSet - 嵌套路由：GET /api/scans/{scan_pk}/endpoints/
+    
+    支持智能过滤语法（filter 参数）：
+    - url="api"          URL 模糊匹配
+    - host="example"     主机名模糊匹配
+    - title="login"      标题模糊匹配
+    - status="200"       状态码匹配
+    - webserver="nginx"  服务器类型匹配
+    - tech="php"         技术栈匹配
+    """
     
     serializer_class = EndpointSnapshotSerializer
     pagination_class = BasePagination
-    filter_backends = [filters.SearchFilter, filters.OrderingFilter]
-    search_fields = ['host']
-    ordering = ['-discovered_at']
+    filter_backends = [filters.OrderingFilter]
+    ordering = ['-created_at']
     
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
@@ -586,15 +940,17 @@ class EndpointSnapshotViewSet(viewsets.ModelViewSet):
     
     def get_queryset(self):
         scan_pk = self.kwargs.get('scan_pk')
+        filter_query = self.request.query_params.get('filter', None)
+        
         if scan_pk:
-            return self.service.get_by_scan(scan_pk)
-        return self.service.get_all()
+            return self.service.get_by_scan(scan_pk, filter_query=filter_query)
+        return self.service.get_all(filter_query=filter_query)
 
     @action(detail=False, methods=['get'], url_path='export')
     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, discovered_at
+        CSV 列：url, host, location, title, status_code, content_length, content_type, webserver, tech, body_preview, vhost, matched_gf_patterns, created_at
         """
         from apps.common.utils import generate_csv_rows, format_datetime, format_list_field
         
@@ -607,10 +963,10 @@ class EndpointSnapshotViewSet(viewsets.ModelViewSet):
         headers = [
             'url', 'host', 'location', 'title', 'status_code',
             'content_length', 'content_type', 'webserver', 'tech',
-            'body_preview', 'vhost', 'matched_gf_patterns', 'discovered_at'
+            'body_preview', 'vhost', 'matched_gf_patterns', 'created_at'
         ]
         formatters = {
-            'discovered_at': format_datetime,
+            'created_at': format_datetime,
             'tech': lambda x: format_list_field(x, separator=','),
             'matched_gf_patterns': lambda x: format_list_field(x, separator=','),
         }
@@ -626,7 +982,12 @@ class EndpointSnapshotViewSet(viewsets.ModelViewSet):
 class HostPortMappingSnapshotViewSet(viewsets.ModelViewSet):
     """主机端口映射快照 ViewSet - 嵌套路由：GET /api/scans/{scan_pk}/ip-addresses/
     
-    注意：由于返回的是聚合数据（字典列表），不支持 DRF SearchFilter
+    支持智能过滤语法（filter 参数）：
+    - ip="192.168"       IP 模糊匹配
+    - port="80"          端口匹配
+    - host="api"         主机名模糊匹配
+    
+    注意：由于返回的是聚合数据（字典列表），过滤在 Service 层处理
     """
     
     serializer_class = IPAddressAggregatedSerializer
@@ -638,16 +999,17 @@ class HostPortMappingSnapshotViewSet(viewsets.ModelViewSet):
     
     def get_queryset(self):
         scan_pk = self.kwargs.get('scan_pk')
-        search = self.request.query_params.get('search', None)
+        filter_query = self.request.query_params.get('filter', None)
+        
         if scan_pk:
-            return self.service.get_ip_aggregation_by_scan(scan_pk, search=search)
-        return self.service.get_all_ip_aggregation(search=search)
+            return self.service.get_ip_aggregation_by_scan(scan_pk, filter_query=filter_query)
+        return self.service.get_all_ip_aggregation(filter_query=filter_query)
 
     @action(detail=False, methods=['get'], url_path='export')
     def export(self, request, **kwargs):
         """导出 IP 地址为 CSV 格式
         
-        CSV 列：ip, host, port, discovered_at
+        CSV 列：ip, host, port, created_at
         """
         from apps.common.utils import generate_csv_rows, format_datetime
         
@@ -659,9 +1021,9 @@ class HostPortMappingSnapshotViewSet(viewsets.ModelViewSet):
         data_iterator = self.service.iter_raw_data_for_csv_export(scan_id=scan_pk)
         
         # CSV 表头和格式化器
-        headers = ['ip', 'host', 'port', 'discovered_at']
+        headers = ['ip', 'host', 'port', 'created_at']
         formatters = {
-            'discovered_at': format_datetime
+            'created_at': format_datetime
         }
         
         # 生成流式响应
@@ -675,13 +1037,19 @@ class HostPortMappingSnapshotViewSet(viewsets.ModelViewSet):
 
 
 class VulnerabilitySnapshotViewSet(viewsets.ModelViewSet):
-    """漏洞快照 ViewSet - 嵌套路由：GET /api/scans/{scan_pk}/vulnerabilities/"""
+    """漏洞快照 ViewSet - 嵌套路由：GET /api/scans/{scan_pk}/vulnerabilities/
+    
+    支持智能过滤语法（filter 参数）：
+    - type="xss"         漏洞类型模糊匹配
+    - url="api"          URL 模糊匹配
+    - severity="high"    严重程度匹配
+    - source="nuclei"    来源工具匹配
+    """
     
     serializer_class = VulnerabilitySnapshotSerializer
     pagination_class = BasePagination
-    filter_backends = [filters.SearchFilter, filters.OrderingFilter]
-    search_fields = ['vuln_type']
-    ordering = ['-discovered_at']
+    filter_backends = [filters.OrderingFilter]
+    ordering = ['-created_at']
     
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
@@ -689,6 +1057,8 @@ class VulnerabilitySnapshotViewSet(viewsets.ModelViewSet):
     
     def get_queryset(self):
         scan_pk = self.kwargs.get('scan_pk')
+        filter_query = self.request.query_params.get('filter', None)
+        
         if scan_pk:
-            return self.service.get_by_scan(scan_pk)
-        return self.service.get_all()
+            return self.service.get_by_scan(scan_pk, filter_query=filter_query)
+        return self.service.get_all(filter_query=filter_query)

backend/apps/common/container_bootstrap.py

@@ -66,12 +66,19 @@ def fetch_config_and_setup_django():
         os.environ.setdefault("ENABLE_COMMAND_LOGGING", str(config['logging']['enableCommandLogging']).lower())
         os.environ.setdefault("DEBUG", str(config['debug']))
         
+        # Git 加速配置（用于 Git clone 加速）
+        git_mirror = config.get('gitMirror', '')
+        if git_mirror:
+            os.environ.setdefault("GIT_MIRROR", git_mirror)
+        
         print(f"[CONFIG] ✓ 配置获取成功")
         print(f"[CONFIG]   DB_HOST: {db_host}")
         print(f"[CONFIG]   DB_PORT: {db_port}")
         print(f"[CONFIG]   DB_NAME: {db_name}")
         print(f"[CONFIG]   DB_USER: {db_user}")
         print(f"[CONFIG]   REDIS_URL: {config['redisUrl']}")
+        if git_mirror:
+            print(f"[CONFIG]   GIT_MIRROR: {git_mirror}")
         
     except Exception as e:
         print(f"[ERROR] 获取配置失败: {config_url} - {e}", file=sys.stderr)

backend/apps/common/services/__init__.py

@@ -3,8 +3,13 @@
 
 提供系统级别的公共服务，包括：
 - SystemLogService: 系统日志读取服务
+
+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
 
-__all__ = ['SystemLogService']
+__all__ = [
+    'SystemLogService',
+]

backend/apps/common/services/system_log_service.py

@@ -21,8 +21,8 @@ class SystemLogService:
     """
     
     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"
+        # 日志文件路径（统一使用 /opt/xingrin/logs）
+        self.log_file = "/opt/xingrin/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

backend/apps/common/utils/__init__.py

@@ -13,6 +13,7 @@ from .csv_utils import (
     format_datetime,
     UTF8_BOM,
 )
+from .git_proxy import get_git_proxy_url
 
 __all__ = [
     'deduplicate_for_bulk',
@@ -25,4 +26,5 @@ __all__ = [
     'format_list_field',
     'format_datetime',
     'UTF8_BOM',
+    'get_git_proxy_url',
 ]

backend/apps/common/utils/filter_utils.py

@@ -0,0 +1,281 @@
+"""智能过滤工具 - 通用查询语法解析和 Django ORM 查询构建
+
+支持的语法：
+- field="value"     模糊匹配（包含）
+- field=="value"    精确匹配
+- field!="value"    不等于
+
+逻辑运算符：
+- AND: && 或 and 或 空格（默认）
+- OR:  || 或 or
+
+示例：
+    type="xss" || type="sqli"           # OR
+    type="xss" or type="sqli"           # OR（等价）
+    severity="high" && source="nuclei"  # AND
+    severity="high" source="nuclei"     # AND（空格默认为 AND）
+    severity="high" and source="nuclei" # AND（等价）
+
+使用示例：
+    from apps.common.utils.filter_utils import apply_filters
+    
+    field_mapping = {'ip': 'ip', 'port': 'port', 'host': 'host'}
+    queryset = apply_filters(queryset, 'ip="192" || port="80"', field_mapping)
+"""
+
+import re
+import logging
+from dataclasses import dataclass
+from typing import List, Dict, Optional, Union
+from enum import Enum
+
+from django.db.models import QuerySet, Q
+
+logger = logging.getLogger(__name__)
+
+
+class LogicalOp(Enum):
+    """逻辑运算符"""
+    AND = 'AND'
+    OR = 'OR'
+
+
+@dataclass
+class ParsedFilter:
+    """解析后的过滤条件"""
+    field: str      # 字段名
+    operator: str   # 操作符: '=', '==', '!='
+    value: str      # 原始值
+
+
+@dataclass
+class FilterGroup:
+    """过滤条件组（带逻辑运算符）"""
+    filter: ParsedFilter
+    logical_op: LogicalOp  # 与前一个条件的逻辑关系
+
+
+class QueryParser:
+    """查询语法解析器
+    
+    支持 ||/or (OR) 和 &&/and/空格 (AND) 逻辑运算符
+    """
+    
+    # 正则匹配: field="value", field=="value", field!="value"
+    FILTER_PATTERN = re.compile(r'(\w+)(==|!=|=)"([^"]*)"')
+    
+    # 逻辑运算符模式（带空格）
+    OR_PATTERN = re.compile(r'\s*(\|\||(?<![a-zA-Z])or(?![a-zA-Z]))\s*', re.IGNORECASE)
+    AND_PATTERN = re.compile(r'\s*(&&|(?<![a-zA-Z])and(?![a-zA-Z]))\s*', re.IGNORECASE)
+    
+    @classmethod
+    def parse(cls, query_string: str) -> List[FilterGroup]:
+        """解析查询语法字符串
+        
+        Args:
+            query_string: 查询语法字符串
+        
+        Returns:
+            解析后的过滤条件组列表
+        
+        Examples:
+            >>> QueryParser.parse('type="xss" || type="sqli"')
+            [FilterGroup(filter=..., logical_op=AND),  # 第一个默认 AND
+             FilterGroup(filter=..., logical_op=OR)]
+        """
+        if not query_string or not query_string.strip():
+            return []
+        
+        # 标准化逻辑运算符
+        # 先处理 || 和 or -> __OR__
+        normalized = cls.OR_PATTERN.sub(' __OR__ ', query_string)
+        # 再处理 && 和 and -> __AND__
+        normalized = cls.AND_PATTERN.sub(' __AND__ ', normalized)
+        
+        # 分词：按空格分割，保留逻辑运算符标记
+        tokens = normalized.split()
+        
+        groups = []
+        pending_op = LogicalOp.AND  # 默认 AND
+        
+        for token in tokens:
+            if token == '__OR__':
+                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
+        
+        return groups
+
+
+class QueryBuilder:
+    """Django ORM 查询构建器
+    
+    将解析后的过滤条件转换为 Django ORM 查询，支持 AND/OR 逻辑
+    """
+    
+    @classmethod
+    def build_query(
+        cls,
+        queryset: QuerySet,
+        filter_groups: List[FilterGroup],
+        field_mapping: Dict[str, str],
+        json_array_fields: List[str] = None
+    ) -> QuerySet:
+        """构建 Django ORM 查询
+        
+        Args:
+            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
+        """
+        if not filter_groups:
+            return queryset
+        
+        json_array_fields = json_array_fields or []
+        
+        # 构建 Q 对象
+        combined_q = None
+        
+        for group in filter_groups:
+            f = group.filter
+            
+            # 字段映射
+            db_field = field_mapping.get(f.field)
+            if not db_field:
+                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, is_json_array)
+            if q is None:
+                continue
+            
+            # 组合 Q 对象
+            if combined_q is None:
+                combined_q = q
+            elif group.logical_op == LogicalOp.OR:
+                combined_q = combined_q | q
+            else:  # AND
+                combined_q = combined_q & q
+        
+        if combined_q is not None:
+            return queryset.filter(combined_q)
+        return queryset
+    
+    @classmethod
+    def _build_single_q(cls, field: str, operator: str, value: str, is_json_array: bool = False) -> Optional[Q]:
+        """构建单个条件的 Q 对象"""
+        if is_json_array:
+            # JSON 数组字段使用 __contains 查询
+            return Q(**{f'{field}__contains': [value]})
+        
+        if operator == '!=':
+            return cls._build_not_equal_q(field, value)
+        elif operator == '==':
+            return cls._build_exact_q(field, value)
+        else:  # '='
+            return cls._build_fuzzy_q(field, value)
+    
+    @classmethod
+    def _try_convert_to_int(cls, value: str) -> Optional[int]:
+        """尝试将值转换为整数"""
+        try:
+            return int(value.strip())
+        except (ValueError, TypeError):
+            return None
+    
+    @classmethod
+    def _build_fuzzy_q(cls, field: str, value: str) -> Q:
+        """模糊匹配: 包含"""
+        return Q(**{f'{field}__icontains': value})
+    
+    @classmethod
+    def _build_exact_q(cls, field: str, value: str) -> Q:
+        """精确匹配"""
+        int_val = cls._try_convert_to_int(value)
+        if int_val is not None:
+            return Q(**{f'{field}__exact': int_val})
+        return Q(**{f'{field}__exact': value})
+    
+    @classmethod
+    def _build_not_equal_q(cls, field: str, value: str) -> Q:
+        """不等于"""
+        int_val = cls._try_convert_to_int(value)
+        if int_val is not None:
+            return ~Q(**{f'{field}__exact': int_val})
+        return ~Q(**{f'{field}__exact': value})
+
+
+def apply_filters(
+    queryset: QuerySet,
+    query_string: str,
+    field_mapping: Dict[str, str],
+    json_array_fields: List[str] = None
+) -> QuerySet:
+    """应用过滤条件到 QuerySet
+    
+    Args:
+        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
+    
+    Examples:
+        # OR 查询
+        apply_filters(qs, 'type="xss" || type="sqli"', mapping)
+        apply_filters(qs, 'type="xss" or type="sqli"', mapping)
+        
+        # AND 查询
+        apply_filters(qs, 'severity="high" && source="nuclei"', mapping)
+        apply_filters(qs, 'severity="high" source="nuclei"', mapping)
+        
+        # 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
+    
+    try:
+        filter_groups = QueryParser.parse(query_string)
+        if not filter_groups:
+            logger.debug(f"未解析到有效过滤条件: {query_string}")
+            return queryset
+        
+        logger.debug(f"解析过滤条件: {filter_groups}")
+        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}")
+        return queryset  # 静默降级

backend/apps/common/utils/git_proxy.py

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

backend/apps/common/validators.py

@@ -27,6 +27,21 @@ def validate_domain(domain: str) -> None:
         raise ValueError(f"域名格式无效: {domain}")
 
 
+def is_valid_domain(domain: str) -> bool:
+    """
+    判断是否为有效域名（不抛异常）
+    
+    Args:
+        domain: 域名字符串
+        
+    Returns:
+        bool: 是否为有效域名
+    """
+    if not domain or len(domain) > 253:
+        return False
+    return bool(validators.domain(domain))
+
+
 def validate_ip(ip: str) -> None:
     """
     验证 IP 地址格式（支持 IPv4 和 IPv6）
@@ -190,6 +205,70 @@ def validate_url(url: str) -> None:
         raise ValueError(f"URL 格式无效: {url}")
 
 
+def is_valid_url(url: str, max_length: int = 2000) -> bool:
+    """
+    判断是否为有效 URL（不抛异常）
+    
+    Args:
+        url: URL 字符串
+        max_length: URL 最大长度，默认 2000
+        
+    Returns:
+        bool: 是否为有效 URL
+    """
+    if not url or len(url) > max_length:
+        return False
+    try:
+        validate_url(url)
+        return True
+    except ValueError:
+        return False
+
+
+def is_url_match_target(url: str, target_name: str, target_type: str) -> bool:
+    """
+    判断 URL 是否匹配目标
+    
+    Args:
+        url: URL 字符串
+        target_name: 目标名称（域名、IP 或 CIDR）
+        target_type: 目标类型 ('domain', 'ip', 'cidr')
+        
+    Returns:
+        bool: 是否匹配
+    """
+    try:
+        parsed = urlparse(url)
+        hostname = parsed.hostname
+        if not hostname:
+            return False
+        
+        hostname = hostname.lower()
+        target_name = target_name.lower()
+        
+        if target_type == 'domain':
+            # 域名类型：hostname 等于 target_name 或以 .target_name 结尾
+            return hostname == target_name or hostname.endswith('.' + target_name)
+        
+        elif target_type == 'ip':
+            # IP 类型：hostname 必须完全等于 target_name
+            return hostname == target_name
+        
+        elif target_type == 'cidr':
+            # CIDR 类型：hostname 必须是 IP 且在 CIDR 范围内
+            try:
+                ip = ipaddress.ip_address(hostname)
+                network = ipaddress.ip_network(target_name, strict=False)
+                return ip in network
+            except ValueError:
+                # hostname 不是有效 IP
+                return False
+        
+        return False
+    except Exception:
+        return False
+
+
 def detect_input_type(input_str: str) -> str:
     """
     检测输入类型（用于快速扫描输入解析）

backend/apps/engine/consumers/worker_deploy_consumer.py

@@ -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_fingerprints.py

@@ -0,0 +1,160 @@
+"""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
+
+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
+
+from django.conf import settings
+from django.core.management.base import BaseCommand
+
+from apps.engine.models import EholeFingerprint, GobyFingerprint, WappalyzerFingerprint
+from apps.engine.services.fingerprints import (
+    EholeFingerprintService,
+    GobyFingerprintService,
+    WappalyzerFingerprintService,
+)
+
+
+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
+    },
+    {
+        "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
+    },
+    {
+        "type": "wappalyzer",
+        "filename": "wappalyzer.json",
+        "model": WappalyzerFingerprint,
+        "service": WappalyzerFingerprintService,
+        "data_key": "apps",  # Wappalyzer 使用 apps 对象
+    },
+]
+
+
+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"]
+
+            # 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 JSON
+            try:
+                with open(src_path, "r", encoding="utf-8") as f:
+                    json_data = json.load(f)
+            except (json.JSONDecodeError, 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(json_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/models/__init__.py

@@ -0,0 +1,19 @@
+"""Engine Models
+
+导出所有 Engine 模块的 Models
+"""
+
+from .engine import WorkerNode, ScanEngine, Wordlist, NucleiTemplateRepo
+from .fingerprints import EholeFingerprint, GobyFingerprint, WappalyzerFingerprint
+
+__all__ = [
+    # 核心 Models
+    "WorkerNode",
+    "ScanEngine",
+    "Wordlist",
+    "NucleiTemplateRepo",
+    # 指纹 Models
+    "EholeFingerprint",
+    "GobyFingerprint",
+    "WappalyzerFingerprint",
+]

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 +1,108 @@
+"""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}"

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

@@ -0,0 +1,14 @@
+"""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
+
+__all__ = [
+    "EholeFingerprintSerializer",
+    "GobyFingerprintSerializer",
+    "WappalyzerFingerprintSerializer",
+]

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/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/fingerprints/__init__.py

@@ -0,0 +1,16 @@
+"""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
+
+__all__ = [
+    "BaseFingerprintService",
+    "EholeFingerprintService",
+    "GobyFingerprintService",
+    "WappalyzerFingerprintService",
+]

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/goby.py

@@ -0,0 +1,70 @@
+"""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
+        
+        校验规则：
+        - name 字段必须存在且非空
+        - logic 字段必须存在
+        - 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', '')
+        logic = item.get('logic', '')
+        rule = item.get('rule')
+        return bool(name and str(name).strip()) and bool(logic) and isinstance(rule, list)
+    
+    def to_model_data(self, item: dict) -> dict:
+        """
+        转换 Goby JSON 格式为 Model 字段
+        
+        Args:
+            item: 原始 Goby JSON 数据
+            
+        Returns:
+            dict: Model 字段数据
+        """
+        return {
+            'name': str(item.get('name', '')).strip(),
+            'logic': item.get('logic', ''),
+            'rule': item.get('rule', []),
+        }
+    
+    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

@@ -186,6 +186,7 @@ class NucleiTemplateRepoService:
             RuntimeError: Git 命令执行失败
         """
         import subprocess
+        from apps.common.utils.git_proxy import get_git_proxy_url
 
         obj = self._get_repo_obj(repo_id)
 
@@ -196,9 +197,14 @@ class NucleiTemplateRepoService:
         cmd: List[str]
         action: str
 
+        # 获取代理后的 URL（如果启用了 Git 加速）
+        proxied_url = get_git_proxy_url(obj.repo_url)
+        if proxied_url != obj.repo_url:
+            logger.info("使用 Git 加速: %s -> %s", obj.repo_url, proxied_url)
+
         # 判断是 clone 还是 pull
         if git_dir.is_dir():
-            # 检查远程地址是否变化
+            # 检查远程地址是否变化（比较原始 URL，不是代理 URL）
             current_remote = subprocess.run(
                 ["git", "-C", str(local_path), "remote", "get-url", "origin"],
                 check=False,
@@ -208,12 +214,13 @@ 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（原始 URL 或代理 URL 变化都需要）
+            if current_url not in [obj.repo_url, proxied_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)
                 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", proxied_url, str(local_path)]
                 action = "clone"
             else:
                 # 已有仓库且地址未变，执行 pull
@@ -224,7 +231,7 @@ 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", proxied_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）
+        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
@@ -251,15 +288,12 @@ class TaskDistributor:
             "-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
@@ -520,7 +554,7 @@ 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 +7,11 @@ from .views import (
     WordlistViewSet,
     NucleiTemplateRepoViewSet,
 )
+from .views.fingerprints import (
+    EholeFingerprintViewSet,
+    GobyFingerprintViewSet,
+    WappalyzerFingerprintViewSet,
+)
 
 
 # 创建路由器
@@ -15,6 +20,10 @@ 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")
 
 urlpatterns = [
     path("", include(router.urls)),

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

@@ -0,0 +1,16 @@
+"""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
+
+__all__ = [
+    "BaseFingerprintViewSet",
+    "EholeFingerprintViewSet",
+    "GobyFingerprintViewSet",
+    "WappalyzerFingerprintViewSet",
+]

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

@@ -0,0 +1,202 @@
+"""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.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 Response(result, status=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
+        
+        返回：同 batch_create
+        """
+        file = request.FILES.get('file')
+        if not file:
+            raise ValidationError('缺少文件')
+        
+        try:
+            json_data = json.load(file)
+        except json.JSONDecodeError as e:
+            raise ValidationError(f'无效的 JSON 格式: {e}')
+        
+        fingerprints = self.parse_import_data(json_data)
+        if not fingerprints:
+            raise ValidationError('文件中没有有效的指纹数据')
+        
+        result = self.get_service().batch_create_fingerprints(fingerprints)
+        return Response(result, status=status.HTTP_201_CREATED)
+    
+    @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 Response({'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 Response({'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/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/worker_views.py

@@ -238,7 +238,7 @@ 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 \
@@ -390,12 +390,14 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
             },
             'redisUrl': worker_redis_url,
             'paths': {
-                'results': getattr(settings, 'CONTAINER_RESULTS_MOUNT', '/app/backend/results'),
-                'logs': getattr(settings, 'CONTAINER_LOGS_MOUNT', '/app/backend/logs'),
+                '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
+            'debug': settings.DEBUG,
+            # Git 加速配置（用于 Git clone 加速，如 Nuclei 模板仓库）
+            'gitMirror': os.getenv('GIT_MIRROR', ''),
         })

backend/apps/scan/configs/command_templates.py

@@ -225,12 +225,32 @@ VULN_SCAN_COMMANDS = {
 }
 
 
+# ==================== 指纹识别 ====================
+
+FINGERPRINT_DETECT_COMMANDS = {
+    'xingfinger': {
+        # 流式输出模式（不使用 -o，输出到 stdout）
+        # -l: URL 列表文件输入
+        # -s: 静默模式，只输出命中结果
+        # --json: JSON 格式输出（每行一条）
+        'base': "xingfinger -l '{urls_file}' -s --json",
+        'optional': {
+            # 自定义指纹库路径
+            'ehole': '--ehole {ehole}',
+            'goby': '--goby {goby}',
+            'wappalyzer': '--wappalyzer {wappalyzer}',
+        }
+    },
+}
+
+
 # ==================== 工具映射 ====================
 
 COMMAND_TEMPLATES = {
     'subdomain_discovery': SUBDOMAIN_DISCOVERY_COMMANDS,
     'port_scan': PORT_SCAN_COMMANDS,
     'site_scan': SITE_SCAN_COMMANDS,
+    'fingerprint_detect': FINGERPRINT_DETECT_COMMANDS,
     'directory_scan': DIRECTORY_SCAN_COMMANDS,
     'url_fetch': URL_FETCH_COMMANDS,
     'vuln_scan': VULN_SCAN_COMMANDS,
@@ -242,7 +262,7 @@ COMMAND_TEMPLATES = {
 EXECUTION_STAGES = [
     {
         'mode': 'sequential',
-        'flows': ['subdomain_discovery', 'port_scan', 'site_scan']
+        'flows': ['subdomain_discovery', 'port_scan', 'site_scan', 'fingerprint_detect']
     },
     {
         'mode': 'parallel',

backend/apps/scan/configs/engine_config_example.yaml

@@ -1,7 +1,8 @@
 # 引擎配置
 #
 # 参数命名：统一用中划线（如 rate-limit），系统自动转换为下划线
-# 必需参数：enabled（是否启用）、timeout（超时秒数，auto 表示自动计算）
+# 必需参数：enabled（是否启用）
+# 可选参数：timeout（超时秒数，默认 auto 自动计算）
 
 # ==================== 子域名发现 ====================
 # 
@@ -39,7 +40,7 @@ subdomain_discovery:
   bruteforce:
     enabled: false
     subdomain_bruteforce:
-      timeout: auto                      # 自动根据字典行数计算
+      # timeout: auto                    # 自动根据字典行数计算
       wordlist-name: subdomains-top1million-110000.txt    # 对应「字典管理」中的 Wordlist.name
 
   # === Stage 3: 变异生成 + 存活验证（可选）===
@@ -52,14 +53,14 @@ subdomain_discovery:
   resolve:
     enabled: true
     subdomain_resolve:
-      timeout: auto      # 自动根据候选子域数量计算
+      # timeout: auto    # 自动根据候选子域数量计算
 
 # ==================== 端口扫描 ====================
 port_scan:
   tools:
     naabu_active:
       enabled: true
-      timeout: auto      # 自动计算（目标数 × 端口数 × 0.5秒），范围 60秒 ~ 2天
+      # timeout: auto    # 自动计算（目标数 × 端口数 × 0.5秒），范围 60秒 ~ 2天
       threads: 200       # 并发连接数（默认 5）
       # ports: 1-65535   # 扫描端口范围（默认 1-65535）
       top-ports: 100     # 扫描 nmap top 100 端口
@@ -67,25 +68,33 @@ port_scan:
       
     naabu_passive:
       enabled: true
-      timeout: auto      # 被动扫描通常较快
+      # timeout: auto    # 被动扫描通常较快
 
 # ==================== 站点扫描 ====================
 site_scan:
   tools:
     httpx:
       enabled: true
-      timeout: auto          # 自动计算（每个 URL 约 1 秒）
+      # timeout: auto        # 自动计算（每个 URL 约 1 秒）
       # threads: 50          # 并发线程数（默认 50）
       # rate-limit: 150      # 每秒请求数（默认 150）
       # request-timeout: 10  # 单个请求超时秒数（默认 10）
       # retries: 2           # 请求失败重试次数
 
+# ==================== 指纹识别 ====================
+# 在 site_scan 后串行执行，识别 WebSite 的技术栈
+fingerprint_detect:
+  tools:
+    xingfinger:
+      enabled: true
+      fingerprint-libs: [ehole, goby, wappalyzer]  # 启用的指纹库：ehole, goby, wappalyzer, fingers, fingerprinthub
+
 # ==================== 目录扫描 ====================
 directory_scan:
   tools:
     ffuf:
       enabled: true
-      timeout: auto                       # 自动计算（字典行数 × 0.02秒），范围 60秒 ~ 2小时
+      # timeout: auto                     # 自动计算（字典行数 × 0.02秒），范围 60秒 ~ 2小时
       max-workers: 5                      # 并发扫描站点数（默认 5）
       wordlist-name: dir_default.txt      # 对应「字典管理」中的 Wordlist.name
       delay: 0.1-2.0                      # 请求间隔，支持范围随机（如 "0.1-2.0"）
@@ -103,7 +112,7 @@ url_fetch:
     
     katana:
       enabled: true
-      timeout: auto      # 自动计算（根据站点数量）
+      # timeout: auto    # 自动计算（根据站点数量）
       depth: 5           # 爬取最大深度（默认 3）
       threads: 10        # 全局并发数
       rate-limit: 30     # 每秒最多请求数
@@ -113,7 +122,7 @@ url_fetch:
     
     uro:
       enabled: true
-      timeout: auto      # 自动计算（每 100 个 URL 约 1 秒），范围 30 ~ 300 秒
+      # timeout: auto    # 自动计算（每 100 个 URL 约 1 秒），范围 30 ~ 300 秒
       # whitelist:       # 只保留指定扩展名
       #   - php
       #   - asp
@@ -127,7 +136,7 @@ url_fetch:
     
     httpx:
       enabled: true
-      timeout: auto          # 自动计算（每个 URL 约 1 秒）
+      # timeout: auto        # 自动计算（每个 URL 约 1 秒）
       # threads: 50          # 并发线程数（默认 50）
       # rate-limit: 150      # 每秒请求数（默认 150）
       # request-timeout: 10  # 单个请求超时秒数（默认 10）
@@ -138,7 +147,7 @@ vuln_scan:
   tools:
     dalfox_xss:
       enabled: true
-      timeout: auto          # 自动计算（endpoints 行数 × 100 秒）
+      # timeout: auto        # 自动计算（endpoints 行数 × 100 秒）
       request-timeout: 10  # 单个请求超时秒数
       only-poc: r            # 只输出 POC 结果（r: 反射型）
       ignore-return: "302,404,403"  # 忽略的返回码
@@ -149,7 +158,7 @@ vuln_scan:
 
     nuclei:
       enabled: true
-      timeout: auto          # 自动计算（根据 endpoints 行数）
+      # timeout: auto        # 自动计算（根据 endpoints 行数）
       template-repo-names:   # 模板仓库列表，对应「Nuclei 模板」中的仓库名
         - nuclei-templates
         # - nuclei-custom    # 可追加自定义仓库

backend/apps/scan/flows/__init__.py

@@ -5,8 +5,10 @@
 
 from .initiate_scan_flow import initiate_scan_flow
 from .subdomain_discovery_flow import subdomain_discovery_flow
+from .fingerprint_detect_flow import fingerprint_detect_flow
 
 __all__ = [
     'initiate_scan_flow',
     'subdomain_discovery_flow',
+    'fingerprint_detect_flow',
 ]

backend/apps/scan/flows/directory_scan_flow.py

@@ -140,28 +140,7 @@ def _get_max_workers(tool_config: dict, default: int = DEFAULT_MAX_WORKERS) -> i
     return default
 
 
-def _setup_directory_scan_directory(scan_workspace_dir: str) -> Path:
-    """
-    创建并验证目录扫描工作目录
-    
-    Args:
-        scan_workspace_dir: 扫描工作空间目录
-        
-    Returns:
-        Path: 目录扫描目录路径
-        
-    Raises:
-        RuntimeError: 目录创建或验证失败
-    """
-    directory_scan_dir = Path(scan_workspace_dir) / 'directory_scan'
-    directory_scan_dir.mkdir(parents=True, exist_ok=True)
-    
-    if not directory_scan_dir.is_dir():
-        raise RuntimeError(f"目录扫描目录创建失败: {directory_scan_dir}")
-    if not os.access(directory_scan_dir, os.W_OK):
-        raise RuntimeError(f"目录扫描目录不可写: {directory_scan_dir}")
-    
-    return directory_scan_dir
+
 
 
 def _export_site_urls(target_id: int, target_name: str, directory_scan_dir: Path) -> tuple[str, int]:
@@ -185,8 +164,7 @@ def _export_site_urls(target_id: int, target_name: str, directory_scan_dir: Path
     export_result = export_sites_task(
         target_id=target_id,
         output_file=sites_file,
-        batch_size=1000,  # 每次读取 1000 条，优化内存占用
-        target_name=target_name  # 传入 target_name 用于懒加载
+        batch_size=1000  # 每次读取 1000 条，优化内存占用
     )
     
     site_count = export_result['total_count']
@@ -483,13 +461,23 @@ def _run_scans_concurrently(
             logger.warning("没有有效的扫描任务")
             continue
         
-        # 使用 ThreadPoolTaskRunner 并发执行
-        logger.info("开始并发提交 %d 个扫描任务...", len(scan_params_list))
+        # ============================================================
+        # 分批执行策略：控制实际并发的 ffuf 进程数
+        # ============================================================
+        total_tasks = len(scan_params_list)
+        logger.info("开始分批执行 %d 个扫描任务（每批 %d 个）...", total_tasks, max_workers)
         
-        with ThreadPoolTaskRunner(max_workers=max_workers) as task_runner:
-            # 提交所有任务
+        batch_num = 0
+        for batch_start in range(0, total_tasks, max_workers):
+            batch_end = min(batch_start + max_workers, total_tasks)
+            batch_params = scan_params_list[batch_start:batch_end]
+            batch_num += 1
+            
+            logger.info("执行第 %d 批任务（%d-%d/%d）...", batch_num, batch_start + 1, batch_end, total_tasks)
+            
+            # 提交当前批次的任务（非阻塞，立即返回 future）
             futures = []
-            for params in scan_params_list:
+            for params in batch_params:
                 future = run_and_stream_save_directories_task.submit(
                     cmd=params['command'],
                     tool_name=tool_name,
@@ -504,12 +492,10 @@ def _run_scans_concurrently(
                 )
                 futures.append((params['idx'], params['site_url'], future))
             
-            logger.info("✓ 已提交 %d 个扫描任务，等待完成...", len(futures))
-            
-            # 等待所有任务完成并聚合结果
+            # 等待当前批次所有任务完成（阻塞，确保本批完成后再启动下一批）
             for idx, site_url, future in futures:
                 try:
-                    result = future.result()
+                    result = future.result()  # 阻塞等待单个任务完成
                     directories_found = result.get('created_directories', 0)
                     total_directories += directories_found
                     processed_sites_count += 1
@@ -521,7 +507,6 @@ def _run_scans_concurrently(
                     
                 except Exception as exc:
                     failed_sites.append(site_url)
-                    # 判断是否为超时异常
                     if 'timeout' in str(exc).lower() or isinstance(exc, subprocess.TimeoutExpired):
                         logger.warning(
                             "⚠️ [%d/%d] 站点扫描超时: %s - 错误: %s",
@@ -633,7 +618,8 @@ def directory_scan_flow(
             raise ValueError("enabled_tools 不能为空")
         
         # Step 0: 创建工作目录
-        directory_scan_dir = _setup_directory_scan_directory(scan_workspace_dir)
+        from apps.scan.utils import setup_scan_directory
+        directory_scan_dir = setup_scan_directory(scan_workspace_dir, 'directory_scan')
         
         # Step 1: 导出站点 URL（支持懒加载）
         sites_file, site_count = _export_site_urls(target_id, target_name, directory_scan_dir)

backend/apps/scan/flows/fingerprint_detect_flow.py

@@ -0,0 +1,380 @@
+"""
+指纹识别 Flow
+
+负责编排指纹识别的完整流程
+
+架构：
+- Flow 负责编排多个原子 Task
+- 在 site_scan 后串行执行
+- 使用 xingfinger 工具识别技术栈
+- 流式处理输出，批量更新数据库
+"""
+
+# Django 环境初始化（导入即生效）
+from apps.common.prefect_django_setup import setup_django_for_prefect
+
+import logging
+import os
+from datetime import datetime
+from pathlib import Path
+
+from prefect import flow
+
+from apps.scan.handlers.scan_flow_handlers import (
+    on_scan_flow_running,
+    on_scan_flow_completed,
+    on_scan_flow_failed,
+)
+from apps.scan.tasks.fingerprint_detect import (
+    export_urls_for_fingerprint_task,
+    run_xingfinger_and_stream_update_tech_task,
+)
+from apps.scan.utils import build_scan_command
+from apps.scan.utils.fingerprint_helpers import get_fingerprint_paths
+
+logger = logging.getLogger(__name__)
+
+
+def calculate_fingerprint_detect_timeout(
+    url_count: int,
+    base_per_url: float = 3.0,
+    min_timeout: int = 60
+) -> int:
+    """
+    根据 URL 数量计算超时时间
+    
+    公式：超时时间 = URL 数量 × 每 URL 基础时间
+    最小值：60秒
+    无上限
+    
+    Args:
+        url_count: URL 数量
+        base_per_url: 每 URL 基础时间（秒），默认 3秒
+        min_timeout: 最小超时时间（秒），默认 60秒
+        
+    Returns:
+        int: 计算出的超时时间（秒）
+        
+    示例：
+        100 URL × 3秒 = 300秒
+        1000 URL × 3秒 = 3000秒（50分钟）
+        10000 URL × 3秒 = 30000秒（8.3小时）
+    """
+    timeout = int(url_count * base_per_url)
+    return max(min_timeout, timeout)
+
+
+
+
+
+def _export_urls(
+    target_id: int,
+    fingerprint_dir: Path,
+    source: str = 'website'
+) -> tuple[str, int]:
+    """
+    导出 URL 到文件
+    
+    Args:
+        target_id: 目标 ID
+        fingerprint_dir: 指纹识别目录
+        source: 数据源类型
+        
+    Returns:
+        tuple: (urls_file, total_count)
+    """
+    logger.info("Step 1: 导出 URL 列表 (source=%s)", source)
+    
+    urls_file = str(fingerprint_dir / 'urls.txt')
+    export_result = export_urls_for_fingerprint_task(
+        target_id=target_id,
+        output_file=urls_file,
+        source=source,
+        batch_size=1000
+    )
+    
+    total_count = export_result['total_count']
+    
+    logger.info(
+        "✓ URL 导出完成 - 文件: %s, 数量: %d",
+        export_result['output_file'],
+        total_count
+    )
+    
+    return export_result['output_file'], total_count
+
+
+def _run_fingerprint_detect(
+    enabled_tools: dict,
+    urls_file: str,
+    url_count: int,
+    fingerprint_dir: Path,
+    scan_id: int,
+    target_id: int,
+    source: str
+) -> tuple[dict, list]:
+    """
+    执行指纹识别任务
+    
+    Args:
+        enabled_tools: 已启用的工具配置字典
+        urls_file: URL 文件路径
+        url_count: URL 总数
+        fingerprint_dir: 指纹识别目录
+        scan_id: 扫描任务 ID
+        target_id: 目标 ID
+        source: 数据源类型
+        
+    Returns:
+        tuple: (tool_stats, failed_tools)
+    """
+    tool_stats = {}
+    failed_tools = []
+    
+    for tool_name, tool_config in enabled_tools.items():
+        # 1. 获取指纹库路径
+        lib_names = tool_config.get('fingerprint_libs', ['ehole'])
+        fingerprint_paths = get_fingerprint_paths(lib_names)
+        
+        if not fingerprint_paths:
+            reason = f"没有可用的指纹库: {lib_names}"
+            logger.warning(reason)
+            failed_tools.append({'tool': tool_name, 'reason': reason})
+            continue
+        
+        # 2. 将指纹库路径合并到 tool_config（用于命令构建）
+        tool_config_with_paths = {**tool_config, **fingerprint_paths}
+        
+        # 3. 构建命令
+        try:
+            command = build_scan_command(
+                tool_name=tool_name,
+                scan_type='fingerprint_detect',
+                command_params={
+                    'urls_file': urls_file
+                },
+                tool_config=tool_config_with_paths
+            )
+        except Exception as e:
+            reason = f"命令构建失败: {str(e)}"
+            logger.error("构建 %s 命令失败: %s", tool_name, e)
+            failed_tools.append({'tool': tool_name, 'reason': reason})
+            continue
+        
+        # 4. 计算超时时间
+        timeout = calculate_fingerprint_detect_timeout(url_count)
+        
+        # 5. 生成日志文件路径
+        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
+        log_file = fingerprint_dir / f"{tool_name}_{timestamp}.log"
+        
+        logger.info(
+            "开始执行 %s 指纹识别 - URL数: %d, 超时: %ds, 指纹库: %s",
+            tool_name, url_count, timeout, list(fingerprint_paths.keys())
+        )
+        
+        # 6. 执行扫描任务
+        try:
+            result = run_xingfinger_and_stream_update_tech_task(
+                cmd=command,
+                tool_name=tool_name,
+                scan_id=scan_id,
+                target_id=target_id,
+                source=source,
+                cwd=str(fingerprint_dir),
+                timeout=timeout,
+                log_file=str(log_file),
+                batch_size=100
+            )
+            
+            tool_stats[tool_name] = {
+                'command': command,
+                'result': result,
+                'timeout': timeout,
+                'fingerprint_libs': list(fingerprint_paths.keys())
+            }
+            
+            logger.info(
+                "✓ 工具 %s 执行完成 - 处理记录: %d, 更新: %d, 未找到: %d",
+                tool_name,
+                result.get('processed_records', 0),
+                result.get('updated_count', 0),
+                result.get('not_found_count', 0)
+            )
+            
+        except Exception as exc:
+            failed_tools.append({'tool': tool_name, 'reason': str(exc)})
+            logger.error("工具 %s 执行失败: %s", tool_name, exc, exc_info=True)
+    
+    if failed_tools:
+        logger.warning(
+            "以下指纹识别工具执行失败: %s",
+            ', '.join([f['tool'] for f in failed_tools])
+        )
+    
+    return tool_stats, failed_tools
+
+
+@flow(
+    name="fingerprint_detect",
+    log_prints=True,
+    on_running=[on_scan_flow_running],
+    on_completion=[on_scan_flow_completed],
+    on_failure=[on_scan_flow_failed],
+)
+def fingerprint_detect_flow(
+    scan_id: int,
+    target_name: str,
+    target_id: int,
+    scan_workspace_dir: str,
+    enabled_tools: dict
+) -> dict:
+    """
+    指纹识别 Flow
+    
+    主要功能：
+        1. 从数据库导出目标下所有 WebSite URL 到文件
+        2. 使用 xingfinger 进行技术栈识别
+        3. 解析结果并更新 WebSite.tech 字段（合并去重）
+    
+    工作流程：
+        Step 0: 创建工作目录
+        Step 1: 导出 URL 列表
+        Step 2: 解析配置，获取启用的工具
+        Step 3: 执行 xingfinger 并解析结果
+    
+    Args:
+        scan_id: 扫描任务 ID
+        target_name: 目标名称
+        target_id: 目标 ID
+        scan_workspace_dir: 扫描工作空间目录
+        enabled_tools: 启用的工具配置（xingfinger）
+        
+    Returns:
+        dict: {
+            'success': bool,
+            'scan_id': int,
+            'target': str,
+            'scan_workspace_dir': str,
+            'urls_file': str,
+            'url_count': int,
+            'processed_records': int,
+            'updated_count': int,
+            'not_found_count': int,
+            'executed_tasks': list,
+            'tool_stats': dict
+        }
+    """
+    try:
+        logger.info(
+            "="*60 + "\n" +
+            "开始指纹识别\n" +
+            f"  Scan ID: {scan_id}\n" +
+            f"  Target: {target_name}\n" +
+            f"  Workspace: {scan_workspace_dir}\n" +
+            "="*60
+        )
+        
+        # 参数验证
+        if scan_id is None:
+            raise ValueError("scan_id 不能为空")
+        if not target_name:
+            raise ValueError("target_name 不能为空")
+        if target_id is None:
+            raise ValueError("target_id 不能为空")
+        if not scan_workspace_dir:
+            raise ValueError("scan_workspace_dir 不能为空")
+        
+        # 数据源类型（当前只支持 website）
+        source = 'website'
+        
+        # Step 0: 创建工作目录
+        from apps.scan.utils import setup_scan_directory
+        fingerprint_dir = setup_scan_directory(scan_workspace_dir, 'fingerprint_detect')
+        
+        # Step 1: 导出 URL（支持懒加载）
+        urls_file, url_count = _export_urls(target_id, fingerprint_dir, source)
+        
+        if url_count == 0:
+            logger.warning("目标下没有可用的 URL，跳过指纹识别")
+            return {
+                'success': True,
+                'scan_id': scan_id,
+                'target': target_name,
+                'scan_workspace_dir': scan_workspace_dir,
+                'urls_file': urls_file,
+                'url_count': 0,
+                'processed_records': 0,
+                'updated_count': 0,
+                'created_count': 0,
+                'executed_tasks': ['export_urls_for_fingerprint'],
+                'tool_stats': {
+                    'total': 0,
+                    'successful': 0,
+                    'failed': 0,
+                    'successful_tools': [],
+                    'failed_tools': [],
+                    'details': {}
+                }
+            }
+        
+        # Step 2: 工具配置信息
+        logger.info("Step 2: 工具配置信息")
+        logger.info("✓ 启用工具: %s", ', '.join(enabled_tools.keys()))
+        
+        # Step 3: 执行指纹识别
+        logger.info("Step 3: 执行指纹识别")
+        tool_stats, failed_tools = _run_fingerprint_detect(
+            enabled_tools=enabled_tools,
+            urls_file=urls_file,
+            url_count=url_count,
+            fingerprint_dir=fingerprint_dir,
+            scan_id=scan_id,
+            target_id=target_id,
+            source=source
+        )
+        
+        logger.info("="*60 + "\n✓ 指纹识别完成\n" + "="*60)
+        
+        # 动态生成已执行的任务列表
+        executed_tasks = ['export_urls_for_fingerprint']
+        executed_tasks.extend([f'run_xingfinger ({tool})' for tool in tool_stats.keys()])
+        
+        # 汇总所有工具的结果
+        total_processed = sum(stats['result'].get('processed_records', 0) for stats in tool_stats.values())
+        total_updated = sum(stats['result'].get('updated_count', 0) for stats in tool_stats.values())
+        total_created = sum(stats['result'].get('created_count', 0) for stats in tool_stats.values())
+        
+        successful_tools = [name for name in enabled_tools.keys() 
+                           if name not in [f['tool'] for f in failed_tools]]
+        
+        return {
+            'success': True,
+            'scan_id': scan_id,
+            'target': target_name,
+            'scan_workspace_dir': scan_workspace_dir,
+            'urls_file': urls_file,
+            'url_count': url_count,
+            'processed_records': total_processed,
+            'updated_count': total_updated,
+            'created_count': total_created,
+            'executed_tasks': executed_tasks,
+            'tool_stats': {
+                'total': len(enabled_tools),
+                'successful': len(successful_tools),
+                'failed': len(failed_tools),
+                'successful_tools': successful_tools,
+                'failed_tools': failed_tools,
+                'details': tool_stats
+            }
+        }
+        
+    except ValueError as e:
+        logger.error("配置错误: %s", e)
+        raise
+    except RuntimeError as e:
+        logger.error("运行时错误: %s", e)
+        raise
+    except Exception as e:
+        logger.exception("指纹识别失败: %s", e)
+        raise

backend/apps/scan/flows/initiate_scan_flow.py

@@ -30,7 +30,7 @@ from apps.scan.handlers import (
     on_initiate_scan_flow_failed,
 )
 from prefect.futures import wait
-from apps.scan.tasks.workspace_tasks import create_scan_workspace_task
+from apps.scan.utils import setup_scan_workspace
 from apps.scan.orchestrators import FlowOrchestrator
 
 logger = logging.getLogger(__name__)
@@ -110,7 +110,7 @@ def initiate_scan_flow(
         )
         
         # ==================== Task 1: 创建 Scan 工作空间 ====================
-        scan_workspace_path = create_scan_workspace_task(scan_workspace_dir)
+        scan_workspace_path = setup_scan_workspace(scan_workspace_dir)
         
         # ==================== Task 2: 获取引擎配置 ====================
         from apps.scan.models import Scan

backend/apps/scan/flows/port_scan_flow.py

@@ -154,28 +154,7 @@ def _parse_port_count(tool_config: dict) -> int:
     return 100
 
 
-def _setup_port_scan_directory(scan_workspace_dir: str) -> Path:
-    """
-    创建并验证端口扫描工作目录
-    
-    Args:
-        scan_workspace_dir: 扫描工作空间目录
-        
-    Returns:
-        Path: 端口扫描目录路径
-        
-    Raises:
-        RuntimeError: 目录创建或验证失败
-    """
-    port_scan_dir = Path(scan_workspace_dir) / 'port_scan'
-    port_scan_dir.mkdir(parents=True, exist_ok=True)
-    
-    if not port_scan_dir.is_dir():
-        raise RuntimeError(f"端口扫描目录创建失败: {port_scan_dir}")
-    if not os.access(port_scan_dir, os.W_OK):
-        raise RuntimeError(f"端口扫描目录不可写: {port_scan_dir}")
-    
-    return port_scan_dir
+
 
 
 def _export_scan_targets(target_id: int, port_scan_dir: Path) -> tuple[str, int, str]:
@@ -442,7 +421,8 @@ def port_scan_flow(
         )
         
         # Step 0: 创建工作目录
-        port_scan_dir = _setup_port_scan_directory(scan_workspace_dir)
+        from apps.scan.utils import setup_scan_directory
+        port_scan_dir = setup_scan_directory(scan_workspace_dir, 'port_scan')
         
         # Step 1: 导出扫描目标列表到文件（根据 Target 类型自动决定内容）
         targets_file, target_count, target_type = _export_scan_targets(target_id, port_scan_dir)

backend/apps/scan/flows/site_scan_flow.py

@@ -85,28 +85,7 @@ def calculate_timeout_by_line_count(
         return min_timeout
 
 
-def _setup_site_scan_directory(scan_workspace_dir: str) -> Path:
-    """
-    创建并验证站点扫描工作目录
-    
-    Args:
-        scan_workspace_dir: 扫描工作空间目录
-        
-    Returns:
-        Path: 站点扫描目录路径
-        
-    Raises:
-        RuntimeError: 目录创建或验证失败
-    """
-    site_scan_dir = Path(scan_workspace_dir) / 'site_scan'
-    site_scan_dir.mkdir(parents=True, exist_ok=True)
-    
-    if not site_scan_dir.is_dir():
-        raise RuntimeError(f"站点扫描目录创建失败: {site_scan_dir}")
-    if not os.access(site_scan_dir, os.W_OK):
-        raise RuntimeError(f"站点扫描目录不可写: {site_scan_dir}")
-    
-    return site_scan_dir
+
 
 
 def _export_site_urls(target_id: int, site_scan_dir: Path, target_name: str = None) -> tuple[str, int, int]:
@@ -130,7 +109,6 @@ def _export_site_urls(target_id: int, site_scan_dir: Path, target_name: str = No
     export_result = export_site_urls_task(
         target_id=target_id,
         output_file=urls_file,
-        target_name=target_name,
         batch_size=1000  # 每次处理1000个子域名
     )
     
@@ -403,7 +381,8 @@ def site_scan_flow(
             raise ValueError("scan_workspace_dir 不能为空")
         
         # Step 0: 创建工作目录
-        site_scan_dir = _setup_site_scan_directory(scan_workspace_dir)
+        from apps.scan.utils import setup_scan_directory
+        site_scan_dir = setup_scan_directory(scan_workspace_dir, 'site_scan')
         
         # Step 1: 导出站点 URL
         urls_file, total_urls, association_count = _export_site_urls(

backend/apps/scan/flows/subdomain_discovery_flow.py

@@ -41,28 +41,7 @@ import subprocess
 logger = logging.getLogger(__name__)
 
 
-def _setup_subdomain_directory(scan_workspace_dir: str) -> Path:
-    """
-    创建并验证子域名扫描工作目录
-    
-    Args:
-        scan_workspace_dir: 扫描工作空间目录
-        
-    Returns:
-        Path: 子域名扫描目录路径
-        
-    Raises:
-        RuntimeError: 目录创建或验证失败
-    """
-    result_dir = Path(scan_workspace_dir) / 'subdomain_discovery'
-    result_dir.mkdir(parents=True, exist_ok=True)
-    
-    if not result_dir.is_dir():
-        raise RuntimeError(f"子域名扫描目录创建失败: {result_dir}")
-    if not os.access(result_dir, os.W_OK):
-        raise RuntimeError(f"子域名扫描目录不可写: {result_dir}")
-    
-    return result_dir
+
 
 
 def _validate_and_normalize_target(target_name: str) -> str:
@@ -119,12 +98,7 @@ def _run_scans_parallel(
     
     # 生成时间戳（所有工具共用）
     timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
-    
-    # TODO: 接入代理池管理系统
-    # from apps.proxy.services import proxy_pool
-    # proxy_stats = proxy_pool.get_stats()
-    # logger.info(f"代理池状态: {proxy_stats['healthy']}/{proxy_stats['total']} 可用")
-    
+
     failures = []  # 记录命令构建失败的工具
     futures = {}
     
@@ -417,7 +391,8 @@ def subdomain_discovery_flow(
         )
         
         # Step 0: 准备工作
-        result_dir = _setup_subdomain_directory(scan_workspace_dir)
+        from apps.scan.utils import setup_scan_directory
+        result_dir = setup_scan_directory(scan_workspace_dir, 'subdomain_discovery')
         
         # 验证并规范化目标域名
         try:

backend/apps/scan/flows/url_fetch/main_flow.py

@@ -42,17 +42,7 @@ SITES_FILE_TOOLS = {'katana'}
 POST_PROCESS_TOOLS = {'uro', 'httpx'}
 
 
-def _setup_url_fetch_directory(scan_workspace_dir: str) -> Path:
-    """创建并验证 URL 获取工作目录"""
-    url_fetch_dir = Path(scan_workspace_dir) / 'url_fetch'
-    url_fetch_dir.mkdir(parents=True, exist_ok=True)
-    
-    if not url_fetch_dir.is_dir():
-        raise RuntimeError(f"URL 获取目录创建失败: {url_fetch_dir}")
-    if not os.access(url_fetch_dir, os.W_OK):
-        raise RuntimeError(f"URL 获取目录不可写: {url_fetch_dir}")
-    
-    return url_fetch_dir
+
 
 
 def _classify_tools(enabled_tools: dict) -> tuple[dict, dict, dict, dict]:
@@ -304,7 +294,8 @@ def url_fetch_flow(
         
         # Step 1: 准备工作目录
         logger.info("Step 1: 准备工作目录")
-        url_fetch_dir = _setup_url_fetch_directory(scan_workspace_dir)
+        from apps.scan.utils import setup_scan_directory
+        url_fetch_dir = setup_scan_directory(scan_workspace_dir, 'url_fetch')
         
         # Step 2: 分类工具（按输入类型）
         logger.info("Step 2: 分类工具")

backend/apps/scan/flows/url_fetch/sites_url_fetch_flow.py

@@ -40,8 +40,7 @@ def _export_sites_file(target_id: int, scan_id: int, target_name: str, output_di
     result = export_sites_task(
         output_file=output_file,
         target_id=target_id,
-        scan_id=scan_id,
-        target_name=target_name
+        scan_id=scan_id
     )
     
     count = result['asset_count']

backend/apps/scan/flows/vuln_scan/endpoints_vuln_scan_flow.py

@@ -25,10 +25,7 @@ from .utils import calculate_timeout_by_line_count
 logger = logging.getLogger(__name__)
 
 
-def _setup_vuln_scan_directory(scan_workspace_dir: str) -> Path:
-    vuln_scan_dir = Path(scan_workspace_dir) / "vuln_scan"
-    vuln_scan_dir.mkdir(parents=True, exist_ok=True)
-    return vuln_scan_dir
+
 
 
 @flow(
@@ -55,14 +52,14 @@ def endpoints_vuln_scan_flow(
         if not enabled_tools:
             raise ValueError("enabled_tools 不能为空")
 
-        vuln_scan_dir = _setup_vuln_scan_directory(scan_workspace_dir)
+        from apps.scan.utils import setup_scan_directory
+        vuln_scan_dir = setup_scan_directory(scan_workspace_dir, 'vuln_scan')
         endpoints_file = vuln_scan_dir / "input_endpoints.txt"
 
         # Step 1: 导出 Endpoint URL
         export_result = export_endpoints_task(
             target_id=target_id,
             output_file=str(endpoints_file),
-            target_name=target_name,  # 传入 target_name 用于生成默认端点
         )
         total_endpoints = export_result.get("total_count", 0)
 

backend/apps/scan/notifications/receivers.py

@@ -87,8 +87,8 @@ def on_all_workers_high_load(sender, worker_name, cpu, mem, **kwargs):
     """所有 Worker 高负载时的通知处理"""
     create_notification(
         title="系统负载较高",
-        message=f"所有节点负载较高，已选择负载最低的节点 {worker_name}（CPU: {cpu:.1f}%, 内存: {mem:.1f}%）执行任务，扫描速度可能受影响",
+        message=f"所有节点负载较高（最低负载节点 CPU: {cpu:.1f}%, 内存: {mem:.1f}%），系统将等待最多 10 分钟后分发任务，扫描速度可能受影响",
         level=NotificationLevel.MEDIUM,
         category=NotificationCategory.SYSTEM
     )
-    logger.warning("高负载通知已发送 - worker=%s, cpu=%.1f%%, mem=%.1f%%", worker_name, cpu, mem)
+    logger.warning("高负载通知已发送 - cpu=%.1f%%, mem=%.1f%%", cpu, mem)

backend/apps/scan/orchestrators/flow_orchestrator.py

@@ -206,6 +206,10 @@ class FlowOrchestrator:
             from apps.scan.flows.site_scan_flow import site_scan_flow
             return site_scan_flow
         
+        elif scan_type == 'fingerprint_detect':
+            from apps.scan.flows.fingerprint_detect_flow import fingerprint_detect_flow
+            return fingerprint_detect_flow
+        
         elif scan_type == 'directory_scan':
             from apps.scan.flows.directory_scan_flow import directory_scan_flow
             return directory_scan_flow

backend/apps/scan/scripts/run_cleanup.py

@@ -83,7 +83,7 @@ def cleanup_results(results_dir: str, retention_days: int) -> dict:
 
 def main():
     parser = argparse.ArgumentParser(description="清理任务")
-    parser.add_argument("--results_dir", type=str, default="/app/backend/results", help="扫描结果目录")
+    parser.add_argument("--results_dir", type=str, default="/opt/xingrin/results", help="扫描结果目录")
     parser.add_argument("--retention_days", type=int, default=7, help="保留天数")
     
     args = parser.parse_args()

backend/apps/scan/services/__init__.py

@@ -17,6 +17,8 @@ from .scan_state_service import ScanStateService
 from .scan_control_service import ScanControlService
 from .scan_stats_service import ScanStatsService
 from .scheduled_scan_service import ScheduledScanService
+from .blacklist_service import BlacklistService
+from .target_export_service import TargetExportService
 
 __all__ = [
     'ScanService',           # 主入口（向后兼容）
@@ -25,5 +27,7 @@ __all__ = [
     'ScanControlService',
     'ScanStatsService',
     'ScheduledScanService',
+    'BlacklistService',      # 黑名单过滤服务
+    'TargetExportService',   # 目标导出服务
 ]
 

backend/apps/scan/services/blacklist_service.py

@@ -0,0 +1,85 @@
+"""
+黑名单过滤服务
+
+过滤敏感域名（如 .gov、.edu、.mil 等）
+
+当前版本使用默认规则，后续将支持从前端配置加载。
+"""
+
+from typing import List, Optional
+from django.db.models import QuerySet
+import re
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+class BlacklistService:
+    """
+    黑名单过滤服务 - 过滤敏感域名
+    
+    TODO: 后续版本支持从前端配置加载黑名单规则
+    - 用户在开始扫描时配置黑名单 URL、域名、IP
+    - 黑名单规则存储在数据库中，与 Scan 或 Engine 关联
+    """
+    
+    # 默认黑名单正则规则
+    DEFAULT_PATTERNS = [
+        r'\.gov$',           # .gov 结尾
+        r'\.gov\.[a-z]{2}$', # .gov.cn, .gov.uk 等
+        r'\.edu$',           # .edu 结尾
+        r'\.edu\.[a-z]{2}$', # .edu.cn 等
+        r'\.mil$',           # .mil 结尾
+    ]
+    
+    def __init__(self, patterns: Optional[List[str]] = None):
+        """
+        初始化黑名单服务
+        
+        Args:
+            patterns: 正则表达式列表，None 使用默认规则
+        """
+        self.patterns = patterns or self.DEFAULT_PATTERNS
+        self._compiled_patterns = [re.compile(p) for p in self.patterns]
+    
+    def filter_queryset(
+        self,
+        queryset: QuerySet,
+        url_field: str = 'url'
+    ) -> QuerySet:
+        """
+        数据库层面过滤 queryset
+        
+        使用 PostgreSQL 正则表达式排除黑名单 URL
+        
+        Args:
+            queryset: 原始 queryset
+            url_field: URL 字段名
+            
+        Returns:
+            QuerySet: 过滤后的 queryset
+        """
+        for pattern in self.patterns:
+            queryset = queryset.exclude(**{f'{url_field}__regex': pattern})
+        return queryset
+    
+    def filter_url(self, url: str) -> bool:
+        """
+        检查单个 URL 是否通过黑名单过滤
+        
+        Args:
+            url: 要检查的 URL
+            
+        Returns:
+            bool: True 表示通过（不在黑名单），False 表示被过滤
+        """
+        for pattern in self._compiled_patterns:
+            if pattern.search(url):
+                return False
+        return True
+    
+    # TODO: 后续版本实现
+    # @classmethod
+    # def from_scan(cls, scan_id: int) -> 'BlacklistService':
+    #     """从数据库加载扫描配置的黑名单规则"""
+    #     pass

backend/apps/scan/services/target_export_service.py

@@ -0,0 +1,364 @@
+"""
+目标导出服务
+
+提供统一的目标提取和文件导出功能，支持：
+- URL 导出（流式写入 + 默认值回退）
+- 域名/IP 导出（用于端口扫描）
+- 黑名单过滤集成
+"""
+
+import ipaddress
+import logging
+from pathlib import Path
+from typing import Dict, Any, Optional, Iterator
+
+from django.db.models import QuerySet
+
+from .blacklist_service import BlacklistService
+
+logger = logging.getLogger(__name__)
+
+
+class TargetExportService:
+    """
+    目标导出服务 - 提供统一的目标提取和文件导出功能
+    
+    使用方式：
+        # Task 层决定数据源
+        queryset = WebSite.objects.filter(target_id=target_id).values_list('url', flat=True)
+        
+        # 使用导出服务
+        blacklist_service = BlacklistService()
+        export_service = TargetExportService(blacklist_service=blacklist_service)
+        result = export_service.export_urls(target_id, output_path, queryset)
+    """
+    
+    def __init__(self, blacklist_service: Optional[BlacklistService] = None):
+        """
+        初始化导出服务
+        
+        Args:
+            blacklist_service: 黑名单过滤服务，None 表示禁用过滤
+        """
+        self.blacklist_service = blacklist_service
+    
+    def export_urls(
+        self,
+        target_id: int,
+        output_path: str,
+        queryset: QuerySet,
+        url_field: str = 'url',
+        batch_size: int = 1000
+    ) -> Dict[str, Any]:
+        """
+        统一 URL 导出函数
+        
+        自动判断数据库有无数据：
+        - 有数据：流式写入数据库数据到文件
+        - 无数据：调用默认值生成器生成 URL
+        
+        Args:
+            target_id: 目标 ID
+            output_path: 输出文件路径
+            queryset: 数据源 queryset（由 Task 层构建，应为 values_list flat=True）
+            url_field: URL 字段名（用于黑名单过滤）
+            batch_size: 批次大小
+            
+        Returns:
+            dict: {
+                'success': bool,
+                'output_file': str,
+                'total_count': int
+            }
+            
+        Raises:
+            IOError: 文件写入失败
+        """
+        output_file = Path(output_path)
+        output_file.parent.mkdir(parents=True, exist_ok=True)
+        
+        logger.info("开始导出 URL - target_id=%s, output=%s", target_id, output_path)
+        
+        # 应用黑名单过滤（数据库层面）
+        if self.blacklist_service:
+            # 注意：queryset 应该是原始 queryset，不是 values_list
+            # 这里假设 Task 层传入的是 values_list，需要在 Task 层处理过滤
+            pass
+        
+        total_count = 0
+        try:
+            with open(output_file, 'w', encoding='utf-8', buffering=8192) as f:
+                for url in queryset.iterator(chunk_size=batch_size):
+                    if url:
+                        # Python 层面黑名单过滤
+                        if self.blacklist_service and not self.blacklist_service.filter_url(url):
+                            continue
+                        f.write(f"{url}\n")
+                        total_count += 1
+                        
+                        if total_count % 10000 == 0:
+                            logger.info("已导出 %d 个 URL...", total_count)
+        except IOError as e:
+            logger.error("文件写入失败: %s - %s", output_path, e)
+            raise
+        
+        # 默认值回退模式
+        if total_count == 0:
+            total_count = self._generate_default_urls(target_id, output_file)
+        
+        logger.info("✓ URL 导出完成 - 数量: %d, 文件: %s", total_count, output_path)
+        
+        return {
+            'success': True,
+            'output_file': str(output_file),
+            'total_count': total_count
+        }
+
+    def _generate_default_urls(
+        self,
+        target_id: int,
+        output_path: Path
+    ) -> int:
+        """
+        默认值生成器（内部函数）
+        
+        根据 Target 类型生成默认 URL：
+        - DOMAIN: http(s)://domain
+        - IP: http(s)://ip
+        - CIDR: 展开为所有 IP 的 http(s)://ip
+        - URL: 直接使用目标 URL
+        
+        Args:
+            target_id: 目标 ID
+            output_path: 输出文件路径
+            
+        Returns:
+            int: 写入的 URL 总数
+        """
+        from apps.targets.services import TargetService
+        from apps.targets.models import Target
+        
+        target_service = TargetService()
+        target = target_service.get_target(target_id)
+        
+        if not target:
+            logger.warning("Target ID %d 不存在，无法生成默认 URL", target_id)
+            return 0
+        
+        target_name = target.name
+        target_type = target.type
+        
+        logger.info("懒加载模式：Target 类型=%s, 名称=%s", target_type, target_name)
+        
+        total_urls = 0
+        
+        with open(output_path, 'w', encoding='utf-8', buffering=8192) as f:
+            if target_type == Target.TargetType.DOMAIN:
+                urls = [f"http://{target_name}", f"https://{target_name}"]
+                for url in urls:
+                    if self._should_write_url(url):
+                        f.write(f"{url}\n")
+                        total_urls += 1
+                        
+            elif target_type == Target.TargetType.IP:
+                urls = [f"http://{target_name}", f"https://{target_name}"]
+                for url in urls:
+                    if self._should_write_url(url):
+                        f.write(f"{url}\n")
+                        total_urls += 1
+                        
+            elif target_type == Target.TargetType.CIDR:
+                try:
+                    network = ipaddress.ip_network(target_name, strict=False)
+                    
+                    for ip in network.hosts():
+                        urls = [f"http://{ip}", f"https://{ip}"]
+                        for url in urls:
+                            if self._should_write_url(url):
+                                f.write(f"{url}\n")
+                                total_urls += 1
+                        
+                        if total_urls % 10000 == 0:
+                            logger.info("已生成 %d 个 URL...", total_urls)
+                    
+                    # /32 或 /128 特殊处理
+                    if total_urls == 0:
+                        ip = str(network.network_address)
+                        urls = [f"http://{ip}", f"https://{ip}"]
+                        for url in urls:
+                            if self._should_write_url(url):
+                                f.write(f"{url}\n")
+                                total_urls += 1
+                                
+                except ValueError as e:
+                    logger.error("CIDR 解析失败: %s - %s", target_name, e)
+                    raise ValueError(f"无效的 CIDR: {target_name}") from e
+                    
+            elif target_type == Target.TargetType.URL:
+                if self._should_write_url(target_name):
+                    f.write(f"{target_name}\n")
+                    total_urls = 1
+            else:
+                logger.warning("不支持的 Target 类型: %s", target_type)
+        
+        logger.info("✓ 懒加载生成默认 URL - 数量: %d", total_urls)
+        return total_urls
+    
+    def _should_write_url(self, url: str) -> bool:
+        """检查 URL 是否应该写入（通过黑名单过滤）"""
+        if self.blacklist_service:
+            return self.blacklist_service.filter_url(url)
+        return True
+
+    def export_targets(
+        self,
+        target_id: int,
+        output_path: str,
+        batch_size: int = 1000
+    ) -> Dict[str, Any]:
+        """
+        域名/IP 导出函数（用于端口扫描）
+        
+        根据 Target 类型选择导出逻辑：
+        - DOMAIN: 从 Subdomain 表流式导出子域名
+        - IP: 直接写入 IP 地址
+        - CIDR: 展开为所有主机 IP
+        
+        Args:
+            target_id: 目标 ID
+            output_path: 输出文件路径
+            batch_size: 批次大小
+            
+        Returns:
+            dict: {
+                'success': bool,
+                'output_file': str,
+                'total_count': int,
+                'target_type': str
+            }
+        """
+        from apps.targets.services import TargetService
+        from apps.targets.models import Target
+        from apps.asset.services.asset.subdomain_service import SubdomainService
+        
+        output_file = Path(output_path)
+        output_file.parent.mkdir(parents=True, exist_ok=True)
+        
+        # 获取 Target 信息
+        target_service = TargetService()
+        target = target_service.get_target(target_id)
+        
+        if not target:
+            raise ValueError(f"Target ID {target_id} 不存在")
+        
+        target_type = target.type
+        target_name = target.name
+        
+        logger.info(
+            "开始导出扫描目标 - Target ID: %d, Name: %s, Type: %s, 输出文件: %s",
+            target_id, target_name, target_type, output_path
+        )
+        
+        total_count = 0
+        
+        if target_type == Target.TargetType.DOMAIN:
+            total_count = self._export_domains(target_id, target_name, output_file, batch_size)
+            type_desc = "域名"
+            
+        elif target_type == Target.TargetType.IP:
+            total_count = self._export_ip(target_name, output_file)
+            type_desc = "IP"
+            
+        elif target_type == Target.TargetType.CIDR:
+            total_count = self._export_cidr(target_name, output_file)
+            type_desc = "CIDR IP"
+            
+        else:
+            raise ValueError(f"不支持的目标类型: {target_type}")
+        
+        logger.info(
+            "✓ 扫描目标导出完成 - 类型: %s, 总数: %d, 文件: %s",
+            type_desc, total_count, output_path
+        )
+        
+        return {
+            'success': True,
+            'output_file': str(output_file),
+            'total_count': total_count,
+            'target_type': target_type
+        }
+    
+    def _export_domains(
+        self,
+        target_id: int,
+        target_name: str,
+        output_path: Path,
+        batch_size: int
+    ) -> int:
+        """导出域名类型目标的子域名"""
+        from apps.asset.services.asset.subdomain_service import SubdomainService
+        
+        subdomain_service = SubdomainService()
+        domain_iterator = subdomain_service.iter_subdomain_names_by_target(
+            target_id=target_id,
+            chunk_size=batch_size
+        )
+        
+        total_count = 0
+        with open(output_path, 'w', encoding='utf-8', buffering=8192) as f:
+            for domain_name in domain_iterator:
+                if self._should_write_target(domain_name):
+                    f.write(f"{domain_name}\n")
+                    total_count += 1
+                    
+                    if total_count % 10000 == 0:
+                        logger.info("已导出 %d 个域名...", total_count)
+        
+        # 默认值模式：如果没有子域名，使用根域名
+        if total_count == 0:
+            logger.info("采用默认域名：%s (target_id=%d)", target_name, target_id)
+            if self._should_write_target(target_name):
+                with open(output_path, 'w', encoding='utf-8') as f:
+                    f.write(f"{target_name}\n")
+                total_count = 1
+        
+        return total_count
+    
+    def _export_ip(self, target_name: str, output_path: Path) -> int:
+        """导出 IP 类型目标"""
+        if self._should_write_target(target_name):
+            with open(output_path, 'w', encoding='utf-8') as f:
+                f.write(f"{target_name}\n")
+            return 1
+        return 0
+    
+    def _export_cidr(self, target_name: str, output_path: Path) -> int:
+        """导出 CIDR 类型目标，展开为每个 IP"""
+        network = ipaddress.ip_network(target_name, strict=False)
+        total_count = 0
+        
+        with open(output_path, 'w', encoding='utf-8', buffering=8192) as f:
+            for ip in network.hosts():
+                ip_str = str(ip)
+                if self._should_write_target(ip_str):
+                    f.write(f"{ip_str}\n")
+                    total_count += 1
+                    
+                    if total_count % 10000 == 0:
+                        logger.info("已导出 %d 个 IP...", total_count)
+        
+        # /32 或 /128 特殊处理
+        if total_count == 0:
+            ip_str = str(network.network_address)
+            if self._should_write_target(ip_str):
+                with open(output_path, 'w', encoding='utf-8') as f:
+                    f.write(f"{ip_str}\n")
+                total_count = 1
+        
+        return total_count
+    
+    def _should_write_target(self, target: str) -> bool:
+        """检查目标是否应该写入（通过黑名单过滤）"""
+        if self.blacklist_service:
+            return self.blacklist_service.filter_url(target)
+        return True

backend/apps/scan/tasks/__init__.py

@@ -9,9 +9,6 @@
 - Tasks 负责具体操作，Flow 负责编排
 """
 
-# Prefect Tasks
-from .workspace_tasks import create_scan_workspace_task
-
 # 子域名发现任务（已重构为多个子任务）
 from .subdomain_discovery import (
     run_subdomain_discovery_task,
@@ -19,17 +16,25 @@ from .subdomain_discovery import (
     save_domains_task,
 )
 
+# 指纹识别任务
+from .fingerprint_detect import (
+    export_urls_for_fingerprint_task,
+    run_xingfinger_and_stream_update_tech_task,
+)
+
 # 注意：
 # - subdomain_discovery_task 已重构为多个子任务（subdomain_discovery/）
 # - finalize_scan_task 已废弃（Handler 统一管理状态）
 # - initiate_scan_task 已迁移到 flows/initiate_scan_flow.py
 # - cleanup_old_scans_task 已迁移到 flows（cleanup_old_scans_flow）
+# - create_scan_workspace_task 已删除，直接使用 setup_scan_workspace()
 
 __all__ = [
-    # Prefect Tasks
-    'create_scan_workspace_task',
     # 子域名发现任务
     'run_subdomain_discovery_task',
     'merge_and_validate_task',
     'save_domains_task',
+    # 指纹识别任务
+    'export_urls_for_fingerprint_task',
+    'run_xingfinger_and_stream_update_tech_task',
 ]

backend/apps/scan/tasks/directory_scan/export_sites_task.py

@@ -1,20 +1,14 @@
 """
 导出站点 URL 到 TXT 文件的 Task
 
-使用流式处理，避免大量站点导致内存溢出
-支持默认值模式：如果没有站点，根据 Target 类型生成默认 URL
-- DOMAIN: http(s)://target_name
-- IP: http(s)://ip
-- CIDR: 展开为所有 IP 的 http(s)://ip
+使用 TargetExportService 统一处理导出逻辑和默认值回退
+数据源: WebSite.url
 """
 import logging
-import ipaddress
-from pathlib import Path
 from prefect import task
 
-from apps.asset.repositories import DjangoWebSiteRepository
-from apps.targets.services import TargetService
-from apps.targets.models import Target
+from apps.asset.models import WebSite
+from apps.scan.services import TargetExportService, BlacklistService
 
 logger = logging.getLogger(__name__)
 
@@ -24,19 +18,22 @@ def export_sites_task(
     target_id: int,
     output_file: str,
     batch_size: int = 1000,
-    target_name: str = None
 ) -> dict:
     """
     导出目标下的所有站点 URL 到 TXT 文件
 
-    使用流式处理，支持大规模数据导出（10万+站点）
-    支持默认值模式：如果没有站点，自动使用默认站点 URL（http(s)://target_name）
+    数据源: WebSite.url
+    
+    懒加载模式：
+    - 如果数据库为空，根据 Target 类型生成默认 URL
+    - DOMAIN: http(s)://domain
+    - IP: http(s)://ip
+    - CIDR: 展开为所有 IP 的 URL
 
     Args:
         target_id: 目标 ID
         output_file: 输出文件路径（绝对路径）
         batch_size: 每次读取的批次大小，默认 1000
-        target_name: 目标名称（用于默认值模式）
 
     Returns:
         dict: {
@@ -49,134 +46,26 @@ def export_sites_task(
         ValueError: 参数错误
         IOError: 文件写入失败
     """
-    try:
-        # 初始化 Repository
-        repository = DjangoWebSiteRepository()
-
-        logger.info("开始导出站点 URL - Target ID: %d, 输出文件: %s", target_id, output_file)
-
-        # 确保输出目录存在
-        output_path = Path(output_file)
-        output_path.parent.mkdir(parents=True, exist_ok=True)
-
-        # 使用 Repository 流式查询站点 URL
-        url_iterator = repository.get_urls_for_export(
-            target_id=target_id,
-            batch_size=batch_size
-        )
-
-        # 流式写入文件
-        total_count = 0
-        with open(output_path, 'w', encoding='utf-8', buffering=8192) as f:
-            for url in url_iterator:
-                # 每次只处理一个 URL，边读边写
-                f.write(f"{url}\n")
-                total_count += 1
-
-                # 每写入 10000 条记录打印一次进度
-                if total_count % 10000 == 0:
-                    logger.info("已导出 %d 个站点 URL...", total_count)
-
-        # ==================== 懒加载模式：根据 Target 类型生成默认 URL ====================
-        if total_count == 0:
-            total_count = _write_default_urls(target_id, target_name, output_path)
-
-        logger.info(
-            "✓ 站点 URL 导出完成 - 总数: %d, 文件: %s (%.2f KB)",
-            total_count,
-            str(output_path),  # 使用绝对路径
-            output_path.stat().st_size / 1024
-        )
-
-        return {
-            'success': True,
-            'output_file': str(output_path),
-            'total_count': total_count
-        }
-
-    except FileNotFoundError as e:
-        logger.error("输出目录不存在: %s", e)
-        raise
-    except PermissionError as e:
-        logger.error("文件写入权限不足: %s", e)
-        raise
-    except Exception as e:
-        logger.exception("导出站点 URL 失败: %s", e)
-        raise
-
-
-def _write_default_urls(target_id: int, target_name: str, output_path: Path) -> int:
-    """
-    懒加载模式：根据 Target 类型生成默认 URL
+    # 构建数据源 queryset（Task 层决定数据源）
+    queryset = WebSite.objects.filter(target_id=target_id).values_list('url', flat=True)
     
-    Args:
-        target_id: 目标 ID
-        target_name: 目标名称（可选，如果为空则从数据库查询）
-        output_path: 输出文件路径
-        
-    Returns:
-        int: 生成的 URL 数量
-    """
-    # 获取 Target 信息
-    target_service = TargetService()
-    target = target_service.get_target(target_id)
+    # 使用 TargetExportService 处理导出
+    blacklist_service = BlacklistService()
+    export_service = TargetExportService(blacklist_service=blacklist_service)
     
-    if not target:
-        logger.warning("Target ID %d 不存在，无法生成默认 URL", target_id)
-        return 0
+    result = export_service.export_urls(
+        target_id=target_id,
+        output_path=output_file,
+        queryset=queryset,
+        batch_size=batch_size
+    )
     
-    target_name = target.name
-    target_type = target.type
-    
-    logger.info("懒加载模式：Target 类型=%s, 名称=%s", target_type, target_name)
-    
-    total_urls = 0
-    
-    with open(output_path, 'w', encoding='utf-8', buffering=8192) as f:
-        if target_type == Target.TargetType.DOMAIN:
-            # 域名类型：生成 http(s)://domain
-            f.write(f"http://{target_name}\n")
-            f.write(f"https://{target_name}\n")
-            total_urls = 2
-            logger.info("✓ 域名默认 URL 已写入: http(s)://%s", target_name)
-            
-        elif target_type == Target.TargetType.IP:
-            # IP 类型：生成 http(s)://ip
-            f.write(f"http://{target_name}\n")
-            f.write(f"https://{target_name}\n")
-            total_urls = 2
-            logger.info("✓ IP 默认 URL 已写入: http(s)://%s", target_name)
-            
-        elif target_type == Target.TargetType.CIDR:
-            # CIDR 类型：展开为所有 IP 的 URL
-            try:
-                network = ipaddress.ip_network(target_name, strict=False)
-                
-                for ip in network.hosts():  # 排除网络地址和广播地址
-                    f.write(f"http://{ip}\n")
-                    f.write(f"https://{ip}\n")
-                    total_urls += 2
-                    
-                    if total_urls % 10000 == 0:
-                        logger.info("已生成 %d 个 URL...", total_urls)
-                
-                # 如果是 /32 或 /128（单个 IP），hosts() 会为空
-                if total_urls == 0:
-                    ip = str(network.network_address)
-                    f.write(f"http://{ip}\n")
-                    f.write(f"https://{ip}\n")
-                    total_urls = 2
-                
-                logger.info("✓ CIDR 默认 URL 已写入: %d 个 URL (来自 %s)", total_urls, target_name)
-                
-            except ValueError as e:
-                logger.error("CIDR 解析失败: %s - %s", target_name, e)
-                return 0
-        else:
-            logger.warning("不支持的 Target 类型: %s", target_type)
-            return 0
-    
-    return total_urls
+    # 保持返回值格式不变（向后兼容）
+    return {
+        'success': result['success'],
+        'output_file': result['output_file'],
+        'total_count': result['total_count']
+    }
 
 
 

backend/apps/scan/tasks/directory_scan/run_and_stream_save_directories_task.py

@@ -78,12 +78,12 @@ def _parse_and_validate_line(line: str) -> Optional[dict]:
         try:
             line_data = json.loads(line, strict=False)
         except json.JSONDecodeError:
-            logger.info("跳过非 JSON 行: %s", line)
+            # logger.debug("跳过非 JSON 行: %s", line)
             return None
         
         # 步骤 2: 验证数据类型
         if not isinstance(line_data, dict):
-            logger.info("跳过非字典数据")
+            logger.debug("跳过非字典数据")
             return None
         
         # 步骤 3: 验证必要字段

backend/apps/scan/tasks/fingerprint_detect/__init__.py

@@ -0,0 +1,15 @@
+"""
+指纹识别任务模块
+
+包含：
+- export_urls_for_fingerprint_task: 导出 URL 到文件
+- run_xingfinger_and_stream_update_tech_task: 流式执行 xingfinger 并更新 tech
+"""
+
+from .export_urls_task import export_urls_for_fingerprint_task
+from .run_xingfinger_task import run_xingfinger_and_stream_update_tech_task
+
+__all__ = [
+    'export_urls_for_fingerprint_task',
+    'run_xingfinger_and_stream_update_tech_task',
+]

backend/apps/scan/tasks/fingerprint_detect/export_urls_task.py

@@ -0,0 +1,65 @@
+"""
+导出 URL 任务
+
+用于指纹识别前导出目标下的 URL 到文件
+使用 TargetExportService 统一处理导出逻辑和默认值回退
+"""
+
+import logging
+
+from prefect import task
+
+from apps.asset.models import WebSite
+from apps.scan.services import TargetExportService, BlacklistService
+
+logger = logging.getLogger(__name__)
+
+
+@task(name="export_urls_for_fingerprint")
+def export_urls_for_fingerprint_task(
+    target_id: int,
+    output_file: str,
+    source: str = 'website',
+    batch_size: int = 1000
+) -> dict:
+    """
+    导出目标下的 URL 到文件（用于指纹识别）
+    
+    数据源: WebSite.url
+    
+    懒加载模式：
+    - 如果数据库为空，根据 Target 类型生成默认 URL
+    - DOMAIN: http(s)://domain
+    - IP: http(s)://ip
+    - CIDR: 展开为所有 IP 的 URL
+    - URL: 直接使用目标 URL
+    
+    Args:
+        target_id: 目标 ID
+        output_file: 输出文件路径
+        source: 数据源类型（保留参数，兼容旧调用）
+        batch_size: 批量读取大小
+    
+    Returns:
+        dict: {'output_file': str, 'total_count': int, 'source': str}
+    """
+    # 构建数据源 queryset（Task 层决定数据源）
+    queryset = WebSite.objects.filter(target_id=target_id).values_list('url', flat=True)
+    
+    # 使用 TargetExportService 处理导出
+    blacklist_service = BlacklistService()
+    export_service = TargetExportService(blacklist_service=blacklist_service)
+    
+    result = export_service.export_urls(
+        target_id=target_id,
+        output_path=output_file,
+        queryset=queryset,
+        batch_size=batch_size
+    )
+    
+    # 保持返回值格式不变（向后兼容）
+    return {
+        'output_file': result['output_file'],
+        'total_count': result['total_count'],
+        'source': source
+    }

backend/apps/scan/tasks/fingerprint_detect/run_xingfinger_task.py

@@ -0,0 +1,300 @@
+"""
+xingfinger 执行任务
+
+流式执行 xingfinger 命令并实时更新 tech 字段
+"""
+
+import importlib
+import json
+import logging
+import subprocess
+from typing import Optional, Generator
+from urllib.parse import urlparse
+
+from django.db import connection
+from prefect import task
+
+from apps.scan.utils import execute_stream
+
+logger = logging.getLogger(__name__)
+
+
+# 数据源映射：source → (module_path, model_name, url_field)
+SOURCE_MODEL_MAP = {
+    'website': ('apps.asset.models', 'WebSite', 'url'),
+    # 以后扩展：
+    # 'endpoint': ('apps.asset.models', 'Endpoint', 'url'),
+    # 'directory': ('apps.asset.models', 'Directory', 'url'),
+}
+
+
+def _get_model_class(source: str):
+    """根据数据源类型获取 Model 类"""
+    if source not in SOURCE_MODEL_MAP:
+        raise ValueError(f"不支持的数据源: {source}")
+    
+    module_path, model_name, _ = SOURCE_MODEL_MAP[source]
+    module = importlib.import_module(module_path)
+    return getattr(module, model_name)
+
+
+def parse_xingfinger_line(line: str) -> tuple[str, list[str]] | None:
+    """
+    解析 xingfinger 单行 JSON 输出
+    
+    xingfinger 静默模式输出格式：
+    {"url": "https://example.com", "cms": "WordPress,PHP,nginx", ...}
+    
+    Returns:
+        tuple: (url, tech_list) 或 None（解析失败时）
+    """
+    try:
+        item = json.loads(line)
+        url = item.get('url', '').strip()
+        cms = item.get('cms', '')
+        
+        if not url or not cms:
+            return None
+        
+        # cms 字段按逗号分割，去除空白
+        techs = [t.strip() for t in cms.split(',') if t.strip()]
+        
+        return (url, techs) if techs else None
+        
+    except json.JSONDecodeError:
+        return None
+
+
+def bulk_merge_tech_field(
+    source: str,
+    url_techs_map: dict[str, list[str]],
+    target_id: int
+) -> dict:
+    """
+    批量合并 tech 数组字段（PostgreSQL 原生 SQL）
+    
+    使用 PostgreSQL 原生 SQL 实现高效的数组合并去重操作。
+    如果 URL 对应的记录不存在，会自动创建新记录。
+    
+    Returns:
+        dict: {'updated_count': int, 'created_count': int}
+    """
+    Model = _get_model_class(source)
+    table_name = Model._meta.db_table
+    
+    updated_count = 0
+    created_count = 0
+    
+    with connection.cursor() as cursor:
+        for url, techs in url_techs_map.items():
+            if not techs:
+                continue
+            
+            # 先尝试更新（PostgreSQL 数组合并去重）
+            sql = f"""
+                UPDATE {table_name}
+                SET tech = (
+                    SELECT ARRAY(SELECT DISTINCT unnest(
+                        COALESCE(tech, ARRAY[]::varchar[]) || %s::varchar[]
+                    ))
+                )
+                WHERE url = %s AND target_id = %s
+            """
+            
+            cursor.execute(sql, [techs, url, target_id])
+            
+            if cursor.rowcount > 0:
+                updated_count += cursor.rowcount
+            else:
+                # 记录不存在，创建新记录
+                try:
+                    # 从 URL 提取 host
+                    parsed = urlparse(url)
+                    host = parsed.hostname or ''
+                    
+                    # 插入新记录（带冲突处理）
+                    insert_sql = f"""
+                        INSERT INTO {table_name} (target_id, url, host, tech, created_at)
+                        VALUES (%s, %s, %s, %s::varchar[], NOW())
+                        ON CONFLICT (target_id, url) DO UPDATE SET
+                            tech = (
+                                SELECT ARRAY(SELECT DISTINCT unnest(
+                                    COALESCE({table_name}.tech, ARRAY[]::varchar[]) || EXCLUDED.tech
+                                ))
+                            )
+                    """
+                    cursor.execute(insert_sql, [target_id, url, host, techs])
+                    created_count += 1
+                    
+                except Exception as e:
+                    logger.warning("创建 %s 记录失败 (url=%s): %s", source, url, e)
+    
+    return {
+        'updated_count': updated_count,
+        'created_count': created_count
+    }
+
+
+def _parse_xingfinger_stream_output(
+    cmd: str,
+    tool_name: str,
+    cwd: Optional[str] = None,
+    timeout: Optional[int] = None,
+    log_file: Optional[str] = None
+) -> Generator[tuple[str, list[str]], None, None]:
+    """
+    流式解析 xingfinger 命令输出
+    
+    基于 execute_stream 实时处理 xingfinger 命令的 stdout，将每行 JSON 输出
+    转换为 (url, tech_list) 格式
+    """
+    logger.info("开始流式解析 xingfinger 命令输出 - 命令: %s", cmd)
+    
+    total_lines = 0
+    valid_records = 0
+    
+    try:
+        for line in execute_stream(cmd=cmd, tool_name=tool_name, cwd=cwd, shell=True, timeout=timeout, log_file=log_file):
+            total_lines += 1
+            
+            # 解析单行 JSON
+            result = parse_xingfinger_line(line)
+            if result is None:
+                continue
+            
+            valid_records += 1
+            yield result
+            
+            # 每处理 500 条记录输出一次进度
+            if valid_records % 500 == 0:
+                logger.info("已解析 %d 条有效记录...", valid_records)
+                
+    except subprocess.TimeoutExpired as e:
+        error_msg = f"xingfinger 命令执行超时 - 超过 {timeout} 秒"
+        logger.warning(error_msg)
+        raise RuntimeError(error_msg) from e
+    except Exception as e:
+        logger.error("流式解析 xingfinger 输出失败: %s", e, exc_info=True)
+        raise
+    
+    logger.info("流式解析完成 - 总行数: %d, 有效记录: %d", total_lines, valid_records)
+
+
+@task(name="run_xingfinger_and_stream_update_tech")
+def run_xingfinger_and_stream_update_tech_task(
+    cmd: str,
+    tool_name: str,
+    scan_id: int,
+    target_id: int,
+    source: str,
+    cwd: str,
+    timeout: int,
+    log_file: str,
+    batch_size: int = 100
+) -> dict:
+    """
+    流式执行 xingfinger 命令并实时更新 tech 字段
+    
+    根据 source 参数更新对应表的 tech 字段：
+    - website → WebSite.tech
+    - endpoint → Endpoint.tech（以后扩展）
+    
+    处理流程：
+    1. 流式执行 xingfinger 命令
+    2. 实时解析 JSON 输出
+    3. 累积到 batch_size 条后批量更新数据库
+    4. 使用 PostgreSQL 原生 SQL 进行数组合并去重
+    5. 如果记录不存在，自动创建
+    
+    Returns:
+        dict: {
+            'processed_records': int,
+            'updated_count': int,
+            'created_count': int,
+            'batch_count': int
+        }
+    """
+    logger.info(
+        "开始执行 xingfinger 并更新 tech - target_id=%s, source=%s, timeout=%s秒",
+        target_id, source, timeout
+    )
+    
+    data_generator = None
+    
+    try:
+        # 初始化统计
+        processed_records = 0
+        updated_count = 0
+        created_count = 0
+        batch_count = 0
+        
+        # 当前批次的 URL -> techs 映射
+        url_techs_map = {}
+        
+        # 流式处理
+        data_generator = _parse_xingfinger_stream_output(
+            cmd=cmd,
+            tool_name=tool_name,
+            cwd=cwd,
+            timeout=timeout,
+            log_file=log_file
+        )
+        
+        for url, techs in data_generator:
+            processed_records += 1
+            
+            # 累积到 url_techs_map
+            if url in url_techs_map:
+                # 合并同一 URL 的多次识别结果
+                url_techs_map[url].extend(techs)
+            else:
+                url_techs_map[url] = techs
+            
+            # 达到批次大小，执行批量更新
+            if len(url_techs_map) >= batch_size:
+                batch_count += 1
+                result = bulk_merge_tech_field(source, url_techs_map, target_id)
+                updated_count += result['updated_count']
+                created_count += result.get('created_count', 0)
+                
+                logger.debug(
+                    "批次 %d 完成 - 更新: %d, 创建: %d",
+                    batch_count, result['updated_count'], result.get('created_count', 0)
+                )
+                
+                # 清空批次
+                url_techs_map = {}
+        
+        # 处理最后一批
+        if url_techs_map:
+            batch_count += 1
+            result = bulk_merge_tech_field(source, url_techs_map, target_id)
+            updated_count += result['updated_count']
+            created_count += result.get('created_count', 0)
+        
+        logger.info(
+            "✓ xingfinger 执行完成 - 处理记录: %d, 更新: %d, 创建: %d, 批次: %d",
+            processed_records, updated_count, created_count, batch_count
+        )
+        
+        return {
+            'processed_records': processed_records,
+            'updated_count': updated_count,
+            'created_count': created_count,
+            'batch_count': batch_count
+        }
+        
+    except subprocess.TimeoutExpired:
+        logger.warning("⚠️ xingfinger 执行超时 - target_id=%s, timeout=%s秒", target_id, timeout)
+        raise
+    except Exception as e:
+        error_msg = f"xingfinger 执行失败: {e}"
+        logger.error(error_msg, exc_info=True)
+        raise RuntimeError(error_msg) from e
+    finally:
+        # 清理资源
+        if data_generator is not None:
+            try:
+                data_generator.close()
+            except Exception as e:
+                logger.debug("关闭生成器时出错: %s", e)

backend/apps/scan/tasks/port_scan/export_scan_targets_task.py

@@ -1,119 +1,21 @@
 """
 导出扫描目标到 TXT 文件的 Task
 
+使用 TargetExportService.export_targets() 统一处理导出逻辑
+
 根据 Target 类型决定导出内容：
 - DOMAIN: 从 Subdomain 表导出子域名
 - IP: 直接写入 target.name
 - CIDR: 展开 CIDR 范围内的所有 IP
-
-使用流式处理，避免大量数据导致内存溢出
 """
 import logging
-import ipaddress
-from pathlib import Path
 from prefect import task
 
-from apps.asset.services.asset.subdomain_service import SubdomainService
-from apps.targets.services import TargetService
-from apps.targets.models import Target  # 仅用于 TargetType 常量
+from apps.scan.services import TargetExportService, BlacklistService
 
 logger = logging.getLogger(__name__)
 
 
-def _export_domains(target_id: int, target_name: str, output_path: Path, batch_size: int) -> int:
-    """
-    导出域名类型目标的子域名（支持默认值模式）
-    
-    Args:
-        target_id: 目标 ID
-        target_name: 目标名称（域名）
-        output_path: 输出文件路径
-        batch_size: 批次大小
-    
-    Returns:
-        int: 导出的记录数
-    
-    默认值模式:
-        如果没有子域名，自动使用根域名作为默认子域名
-    """
-    subdomain_service = SubdomainService()
-    domain_iterator = subdomain_service.iter_subdomain_names_by_target(
-        target_id=target_id,
-        chunk_size=batch_size
-    )
-    
-    total_count = 0
-    with open(output_path, 'w', encoding='utf-8', buffering=8192) as f:
-        for domain_name in domain_iterator:
-            f.write(f"{domain_name}\n")
-            total_count += 1
-            
-            if total_count % 10000 == 0:
-                logger.info("已导出 %d 个域名...", total_count)
-    
-    # ==================== 采用默认域名：如果没有子域名，使用根域名 ====================
-    # 只写入文件供扫描工具使用，不写入数据库
-    # 数据库只存储扫描发现的真实资产
-    if total_count == 0:
-        logger.info("采用默认域名：%s (target_id=%d)", target_name, target_id)
-        
-        # 只写入文件，不写入数据库
-        with open(output_path, 'w', encoding='utf-8') as f:
-            f.write(f"{target_name}\n")
-        total_count = 1
-        
-        logger.info("✓ 默认域名已写入文件: %s", target_name)
-    
-    return total_count
-
-
-def _export_ip(target_name: str, output_path: Path) -> int:
-    """
-    导出 IP 类型目标
-    
-    Args:
-        target_name: IP 地址
-        output_path: 输出文件路径
-    
-    Returns:
-        int: 导出的记录数（始终为 1）
-    """
-    with open(output_path, 'w', encoding='utf-8') as f:
-        f.write(f"{target_name}\n")
-    return 1
-
-
-def _export_cidr(target_name: str, output_path: Path) -> int:
-    """
-    导出 CIDR 类型目标，展开为每个 IP
-    
-    Args:
-        target_name: CIDR 范围（如 192.168.1.0/24）
-        output_path: 输出文件路径
-    
-    Returns:
-        int: 导出的 IP 数量
-    """
-    network = ipaddress.ip_network(target_name, strict=False)
-    total_count = 0
-    
-    with open(output_path, 'w', encoding='utf-8', buffering=8192) as f:
-        for ip in network.hosts():  # 排除网络地址和广播地址
-            f.write(f"{ip}\n")
-            total_count += 1
-            
-            if total_count % 10000 == 0:
-                logger.info("已导出 %d 个 IP...", total_count)
-    
-    # 如果是 /32 或 /128（单个 IP），hosts() 会为空，需要特殊处理
-    if total_count == 0:
-        with open(output_path, 'w', encoding='utf-8') as f:
-            f.write(f"{network.network_address}\n")
-        total_count = 1
-    
-    return total_count
-
-
 @task(name="export_scan_targets")
 def export_scan_targets_task(
     target_id: int,
@@ -145,62 +47,20 @@ def export_scan_targets_task(
         ValueError: Target 不存在
         IOError: 文件写入失败
     """
-    try:
-        # 1. 通过 Service 层获取 Target
-        target_service = TargetService()
-        target = target_service.get_target(target_id)
-        if not target:
-            raise ValueError(f"Target ID {target_id} 不存在")
-        
-        target_type = target.type
-        target_name = target.name
-        
-        logger.info(
-            "开始导出扫描目标 - Target ID: %d, Name: %s, Type: %s, 输出文件: %s",
-            target_id, target_name, target_type, output_file
-        )
-
-        # 2. 确保输出目录存在
-        output_path = Path(output_file)
-        output_path.parent.mkdir(parents=True, exist_ok=True)
-
-        # 3. 根据类型导出
-        if target_type == Target.TargetType.DOMAIN:
-            total_count = _export_domains(target_id, target_name, output_path, batch_size)
-            type_desc = "域名"
-        elif target_type == Target.TargetType.IP:
-            total_count = _export_ip(target_name, output_path)
-            type_desc = "IP"
-        elif target_type == Target.TargetType.CIDR:
-            total_count = _export_cidr(target_name, output_path)
-            type_desc = "CIDR IP"
-        else:
-            raise ValueError(f"不支持的目标类型: {target_type}")
-
-        logger.info(
-            "✓ 扫描目标导出完成 - 类型: %s, 总数: %d, 文件: %s (%.2f KB)",
-            type_desc,
-            total_count,
-            str(output_path),
-            output_path.stat().st_size / 1024
-        )
-
-        return {
-            'success': True,
-            'output_file': str(output_path),
-            'total_count': total_count,
-            'target_type': target_type
-        }
-
-    except FileNotFoundError as e:
-        logger.error("输出目录不存在: %s", e)
-        raise
-    except PermissionError as e:
-        logger.error("文件写入权限不足: %s", e)
-        raise
-    except ValueError as e:
-        logger.error("参数错误: %s", e)
-        raise
-    except Exception as e:
-        logger.exception("导出扫描目标失败: %s", e)
-        raise
+    # 使用 TargetExportService 处理导出
+    blacklist_service = BlacklistService()
+    export_service = TargetExportService(blacklist_service=blacklist_service)
+    
+    result = export_service.export_targets(
+        target_id=target_id,
+        output_path=output_file,
+        batch_size=batch_size
+    )
+    
+    # 保持返回值格式不变（向后兼容）
+    return {
+        'success': result['success'],
+        'output_file': result['output_file'],
+        'total_count': result['total_count'],
+        'target_type': result['target_type']
+    }

backend/apps/scan/tasks/port_scan/run_and_stream_save_ports_task.py

@@ -212,7 +212,7 @@ def _parse_and_validate_line(line: str) -> Optional[PortScanRecord]:
         try:
             line_data = json.loads(line, strict=False)
         except json.JSONDecodeError:
-            logger.info("跳过非 JSON 行: %s", line)
+            # logger.info("跳过非 JSON 行: %s", line)
             return None
         
         # 步骤 2: 验证数据类型

backend/apps/scan/tasks/site_scan/export_site_urls_task.py

@@ -2,52 +2,65 @@
 导出站点URL到文件的Task
 
 直接使用 HostPortMapping 表查询 host+port 组合，拼接成URL格式写入文件
+使用 TargetExportService 处理默认值回退逻辑
 
-默认值模式：
-- 如果没有 HostPortMapping 数据，写入默认 URL 到文件（不写入数据库）
-- DOMAIN: http(s)://target_name
-- IP: http(s)://ip
-- CIDR: 展开为所有 IP 的 http(s)://ip
+特殊逻辑：
+- 80 端口：只生成 HTTP URL（省略端口号）
+- 443 端口：只生成 HTTPS URL（省略端口号）
+- 其他端口：生成 HTTP 和 HTTPS 两个URL（带端口号）
 """
 import logging
-import ipaddress
 from pathlib import Path
 from prefect import task
-from typing import Optional
 
 from apps.asset.services import HostPortMappingService
-from apps.targets.services import TargetService
-from apps.targets.models import Target
+from apps.scan.services import TargetExportService, BlacklistService
 
 logger = logging.getLogger(__name__)
 
 
+def _generate_urls_from_port(host: str, port: int) -> list[str]:
+    """
+    根据端口生成 URL 列表
+    
+    - 80 端口：只生成 HTTP URL（省略端口号）
+    - 443 端口：只生成 HTTPS URL（省略端口号）
+    - 其他端口：生成 HTTP 和 HTTPS 两个URL（带端口号）
+    """
+    if port == 80:
+        return [f"http://{host}"]
+    elif port == 443:
+        return [f"https://{host}"]
+    else:
+        return [f"http://{host}:{port}", f"https://{host}:{port}"]
+
+
 @task(name="export_site_urls")
 def export_site_urls_task(
     target_id: int,
     output_file: str,
-    target_name: Optional[str] = None,
     batch_size: int = 1000
 ) -> dict:
     """
     导出目标下的所有站点URL到文件（基于 HostPortMapping 表）
     
-    功能：
-    1. 从 HostPortMapping 表查询 target 下所有 host+port 组合
-    2. 拼接成URL格式（标准端口80/443将省略端口号）
-    3. 写入到指定文件中
+    数据源: HostPortMapping (host + port)
     
-    默认值模式（懒加载）：
-    - 如果没有 HostPortMapping 数据，根据 Target 类型生成默认 URL
-    - DOMAIN: http(s)://target_name
+    特殊逻辑：
+    - 80 端口：只生成 HTTP URL（省略端口号）
+    - 443 端口：只生成 HTTPS URL（省略端口号）
+    - 其他端口：生成 HTTP 和 HTTPS 两个URL（带端口号）
+    
+    懒加载模式：
+    - 如果数据库为空，根据 Target 类型生成默认 URL
+    - DOMAIN: http(s)://domain
     - IP: http(s)://ip
-    - CIDR: 展开为所有 IP 的 http(s)://ip
+    - CIDR: 展开为所有 IP 的 URL
     
     Args:
         target_id: 目标ID
         output_file: 输出文件路径（绝对路径）
-        target_name: 目标名称（用于懒加载时写入默认值）
-        batch_size: 每次处理的批次大小，默认1000（暂未使用，预留）
+        batch_size: 每次处理的批次大小
         
     Returns:
         dict: {
@@ -61,155 +74,54 @@ def export_site_urls_task(
         ValueError: 参数错误
         IOError: 文件写入失败
     """
-    try:
-        logger.info("开始统计站点URL - Target ID: %d, 输出文件: %s", target_id, output_file)
-        
-        # 确保输出目录存在
-        output_path = Path(output_file)
-        output_path.parent.mkdir(parents=True, exist_ok=True)
-        
-        # 直接查询 HostPortMapping 表，按 host 排序
-        service = HostPortMappingService()
-        associations = service.iter_host_port_by_target(
-            target_id=target_id,
-            batch_size=batch_size,
-        )
-        
-        total_urls = 0
-        association_count = 0
-        
-        # 流式写入文件
-        with open(output_path, 'w', encoding='utf-8', buffering=8192) as f:
-            for assoc in associations:
-                association_count += 1
-                host = assoc['host']
-                port = assoc['port']
-                
-                # 根据端口号生成URL
-                # 80 端口：只生成 HTTP URL（省略端口号）
-                # 443 端口：只生成 HTTPS URL（省略端口号）
-                # 其他端口：生成 HTTP 和 HTTPS 两个URL（带端口号）
-                if port == 80:
-                    # HTTP 标准端口，省略端口号
-                    url = f"http://{host}"
-                    f.write(f"{url}\n")
-                    total_urls += 1
-                elif port == 443:
-                    # HTTPS 标准端口，省略端口号
-                    url = f"https://{host}"
-                    f.write(f"{url}\n")
-                    total_urls += 1
-                else:
-                    # 非标准端口，生成 HTTP 和 HTTPS 两个URL
-                    http_url = f"http://{host}:{port}"
-                    https_url = f"https://{host}:{port}"
-                    f.write(f"{http_url}\n")
-                    f.write(f"{https_url}\n")
-                    total_urls += 2
-                
-                # 每处理1000条记录打印一次进度
-                if association_count % 1000 == 0:
-                    logger.info("已处理 %d 条关联，生成 %d 个URL...", association_count, total_urls)
-        
-        logger.info(
-            "✓ 站点URL导出完成 - 关联数: %d, 总URL数: %d, 文件: %s (%.2f KB)",
-            association_count,
-            total_urls,
-            str(output_path),
-            output_path.stat().st_size / 1024
-        )
-        
-        # ==================== 懒加载模式：根据 Target 类型生成默认 URL ====================
-        if total_urls == 0:
-            total_urls = _write_default_urls(target_id, target_name, output_path)
-        
-        return {
-            'success': True,
-            'output_file': str(output_path),
-            'total_urls': total_urls,
-            'association_count': association_count
-        }
-        
-    except FileNotFoundError as e:
-        logger.error("输出目录不存在: %s", e)
-        raise
-    except PermissionError as e:
-        logger.error("文件写入权限不足: %s", e)
-        raise
-    except Exception as e:
-        logger.exception("导出站点URL失败: %s", e)
-        raise
-
-
-def _write_default_urls(target_id: int, target_name: Optional[str], output_path: Path) -> int:
-    """
-    懒加载模式：根据 Target 类型生成默认 URL
+    logger.info("开始统计站点URL - Target ID: %d, 输出文件: %s", target_id, output_file)
     
-    Args:
-        target_id: 目标 ID
-        target_name: 目标名称（可选，如果为空则从数据库查询）
-        output_path: 输出文件路径
-        
-    Returns:
-        int: 生成的 URL 数量
-    """
-    # 获取 Target 信息
-    target_service = TargetService()
-    target = target_service.get_target(target_id)
+    # 确保输出目录存在
+    output_path = Path(output_file)
+    output_path.parent.mkdir(parents=True, exist_ok=True)
     
-    if not target:
-        logger.warning("Target ID %d 不存在，无法生成默认 URL", target_id)
-        return 0
+    # 初始化黑名单服务
+    blacklist_service = BlacklistService()
     
-    target_name = target.name
-    target_type = target.type
-    
-    logger.info("懒加载模式：Target 类型=%s, 名称=%s", target_type, target_name)
+    # 直接查询 HostPortMapping 表，按 host 排序
+    service = HostPortMappingService()
+    associations = service.iter_host_port_by_target(
+        target_id=target_id,
+        batch_size=batch_size,
+    )
     
     total_urls = 0
+    association_count = 0
     
+    # 流式写入文件（特殊端口逻辑）
     with open(output_path, 'w', encoding='utf-8', buffering=8192) as f:
-        if target_type == Target.TargetType.DOMAIN:
-            # 域名类型：生成 http(s)://domain
-            f.write(f"http://{target_name}\n")
-            f.write(f"https://{target_name}\n")
-            total_urls = 2
-            logger.info("✓ 域名默认 URL 已写入: http(s)://%s", target_name)
+        for assoc in associations:
+            association_count += 1
+            host = assoc['host']
+            port = assoc['port']
             
-        elif target_type == Target.TargetType.IP:
-            # IP 类型：生成 http(s)://ip
-            f.write(f"http://{target_name}\n")
-            f.write(f"https://{target_name}\n")
-            total_urls = 2
-            logger.info("✓ IP 默认 URL 已写入: http(s)://%s", target_name)
+            # 根据端口号生成URL
+            for url in _generate_urls_from_port(host, port):
+                if blacklist_service.filter_url(url):
+                    f.write(f"{url}\n")
+                    total_urls += 1
             
-        elif target_type == Target.TargetType.CIDR:
-            # CIDR 类型：展开为所有 IP 的 URL
-            try:
-                network = ipaddress.ip_network(target_name, strict=False)
-                
-                for ip in network.hosts():  # 排除网络地址和广播地址
-                    f.write(f"http://{ip}\n")
-                    f.write(f"https://{ip}\n")
-                    total_urls += 2
-                    
-                    if total_urls % 10000 == 0:
-                        logger.info("已生成 %d 个 URL...", total_urls)
-                
-                # 如果是 /32 或 /128（单个 IP），hosts() 会为空
-                if total_urls == 0:
-                    ip = str(network.network_address)
-                    f.write(f"http://{ip}\n")
-                    f.write(f"https://{ip}\n")
-                    total_urls = 2
-                
-                logger.info("✓ CIDR 默认 URL 已写入: %d 个 URL (来自 %s)", total_urls, target_name)
-                
-            except ValueError as e:
-                logger.error("CIDR 解析失败: %s - %s", target_name, e)
-                return 0
-        else:
-            logger.warning("不支持的 Target 类型: %s", target_type)
-            return 0
+            if association_count % 1000 == 0:
+                logger.info("已处理 %d 条关联，生成 %d 个URL...", association_count, total_urls)
     
-    return total_urls
+    logger.info(
+        "✓ 站点URL导出完成 - 关联数: %d, 总URL数: %d, 文件: %s",
+        association_count, total_urls, str(output_path)
+    )
+    
+    # 默认值回退模式：使用 TargetExportService
+    if total_urls == 0:
+        export_service = TargetExportService(blacklist_service=blacklist_service)
+        total_urls = export_service._generate_default_urls(target_id, output_path)
+    
+    return {
+        'success': True,
+        'output_file': str(output_path),
+        'total_urls': total_urls,
+        'association_count': association_count
+    }

backend/apps/scan/tasks/site_scan/run_and_stream_save_websites_task.py

@@ -394,7 +394,7 @@ def _parse_and_validate_line(line: str) -> Optional[HttpxRecord]:
         try:
             line_data = json.loads(line, strict=False)
         except json.JSONDecodeError:
-            logger.info("跳过非 JSON 行: %s", line)
+            # logger.info("跳过非 JSON 行: %s", line)
             return None
         
         # 步骤 2: 验证数据类型

backend/apps/scan/tasks/url_fetch/export_sites_task.py

@@ -1,25 +1,16 @@
 """
 导出站点 URL 列表任务
 
-从 WebSite 表导出站点 URL 列表到文件（用于 katana 等爬虫工具）
-
-使用流式写入，避免内存溢出
-
-懒加载模式：
-- 如果 WebSite 表为空，根据 Target 类型生成默认 URL
-- DOMAIN: 写入 http(s)://domain
-- IP: 写入 http(s)://ip
-- CIDR: 展开为所有 IP
+使用 TargetExportService 统一处理导出逻辑和默认值回退
+数据源: WebSite.url（用于 katana 等爬虫工具）
 """
 
 import logging
-import ipaddress
-from pathlib import Path
 from prefect import task
 from typing import Optional
 
-from apps.targets.services import TargetService
-from apps.targets.models import Target
+from apps.asset.models import WebSite
+from apps.scan.services import TargetExportService, BlacklistService
 
 logger = logging.getLogger(__name__)
 
@@ -33,21 +24,23 @@ def export_sites_task(
     output_file: str,
     target_id: int,
     scan_id: int,
-    target_name: Optional[str] = None,
     batch_size: int = 1000
 ) -> dict:
     """
     导出站点 URL 列表到文件（用于 katana 等爬虫工具）
     
+    数据源: WebSite.url
+    
     懒加载模式：
-    - 如果 WebSite 表为空，根据 Target 类型生成默认 URL
-    - 数据库只存储"真实发现"的资产
+    - 如果数据库为空，根据 Target 类型生成默认 URL
+    - DOMAIN: http(s)://domain
+    - IP: http(s)://ip
+    - CIDR: 展开为所有 IP 的 URL
     
     Args:
         output_file: 输出文件路径
         target_id: 目标 ID
-        scan_id: 扫描 ID
-        target_name: 目标名称（用于懒加载时写入默认值）
+        scan_id: 扫描 ID（保留参数，兼容旧调用）
         batch_size: 批次大小（内存优化）
         
     Returns:
@@ -60,109 +53,22 @@ def export_sites_task(
         ValueError: 参数错误
         RuntimeError: 执行失败
     """
-    try:
-        logger.info("开始导出站点 URL 列表 - Target ID: %d", target_id)
-        
-        # 确保输出目录存在
-        output_path = Path(output_file)
-        output_path.parent.mkdir(parents=True, exist_ok=True)
-        
-        # 从 WebSite 表导出站点 URL
-        from apps.asset.services import WebSiteService
-        
-        website_service = WebSiteService()
-        
-        # 流式写入文件
-        asset_count = 0
-        with open(output_path, 'w') as f:
-            for url in website_service.iter_website_urls_by_target(target_id, batch_size):
-                f.write(f"{url}\n")
-                asset_count += 1
-                
-                if asset_count % batch_size == 0:
-                    f.flush()
-        
-        # ==================== 懒加载模式：根据 Target 类型生成默认 URL ====================
-        if asset_count == 0:
-            asset_count = _write_default_urls(target_id, target_name, output_path)
-        
-        logger.info("✓ 站点 URL 导出完成 - 文件: %s, 数量: %d", output_file, asset_count)
-        
-        return {
-            'output_file': output_file,
-            'asset_count': asset_count,
-        }
-        
-    except Exception as e:
-        logger.error("导出站点 URL 失败: %s", e, exc_info=True)
-        raise RuntimeError(f"导出站点 URL 失败: {e}") from e
-
-
-def _write_default_urls(target_id: int, target_name: Optional[str], output_path: Path) -> int:
-    """
-    懒加载模式：根据 Target 类型生成默认 URL 列表
+    # 构建数据源 queryset（Task 层决定数据源）
+    queryset = WebSite.objects.filter(target_id=target_id).values_list('url', flat=True)
     
-    Args:
-        target_id: 目标 ID
-        target_name: 目标名称
-        output_path: 输出文件路径
-        
-    Returns:
-        int: 生成的 URL 数量
-    """
-    target_service = TargetService()
-    target = target_service.get_target(target_id)
+    # 使用 TargetExportService 处理导出
+    blacklist_service = BlacklistService()
+    export_service = TargetExportService(blacklist_service=blacklist_service)
     
-    if not target:
-        logger.warning("Target ID %d 不存在，无法生成默认 URL", target_id)
-        return 0
+    result = export_service.export_urls(
+        target_id=target_id,
+        output_path=output_file,
+        queryset=queryset,
+        batch_size=batch_size
+    )
     
-    target_name = target.name
-    target_type = target.type
-    
-    logger.info("懒加载模式：Target 类型=%s, 名称=%s", target_type, target_name)
-    
-    total_urls = 0
-    
-    with open(output_path, 'w', encoding='utf-8', buffering=8192) as f:
-        if target_type == Target.TargetType.DOMAIN:
-            f.write(f"http://{target_name}\n")
-            f.write(f"https://{target_name}\n")
-            total_urls = 2
-            logger.info("✓ 域名默认 URL 已写入: http(s)://%s", target_name)
-            
-        elif target_type == Target.TargetType.IP:
-            f.write(f"http://{target_name}\n")
-            f.write(f"https://{target_name}\n")
-            total_urls = 2
-            logger.info("✓ IP 默认 URL 已写入: http(s)://%s", target_name)
-            
-        elif target_type == Target.TargetType.CIDR:
-            try:
-                network = ipaddress.ip_network(target_name, strict=False)
-                
-                for ip in network.hosts():
-                    f.write(f"http://{ip}\n")
-                    f.write(f"https://{ip}\n")
-                    total_urls += 2
-                    
-                    if total_urls % 10000 == 0:
-                        logger.info("已生成 %d 个 URL...", total_urls)
-                
-                # /32 或 /128 特殊处理
-                if total_urls == 0:
-                    ip = str(network.network_address)
-                    f.write(f"http://{ip}\n")
-                    f.write(f"https://{ip}\n")
-                    total_urls = 2
-                
-                logger.info("✓ CIDR 默认 URL 已写入: %d 个 URL (来自 %s)", total_urls, target_name)
-                
-            except ValueError as e:
-                logger.error("CIDR 解析失败: %s - %s", target_name, e)
-                return 0
-        else:
-            logger.warning("不支持的 Target 类型: %s", target_type)
-            return 0
-    
-    return total_urls
+    # 保持返回值格式不变（向后兼容）
+    return {
+        'output_file': result['output_file'],
+        'asset_count': result['total_count'],
+    }

backend/apps/scan/tasks/url_fetch/run_and_stream_save_urls_task.py

@@ -83,7 +83,7 @@ def _parse_and_validate_line(line: str) -> Optional[dict]:
         try:
             line_data = json.loads(line, strict=False)
         except json.JSONDecodeError:
-            logger.info("跳过非 JSON 行: %s", line)
+            # logger.info("跳过非 JSON 行: %s", line)
             return None
         
         # 验证数据类型

backend/apps/scan/tasks/vuln_scan/export_endpoints_task.py

@@ -1,25 +1,16 @@
 """导出 Endpoint URL 到文件的 Task
 
-基于 EndpointService.iter_endpoint_urls_by_target 按目标流式导出端点 URL，
-用于漏洞扫描（如 Dalfox XSS）的输入文件生成。
-
-默认值模式：
-- 如果没有 Endpoint，根据 Target 类型生成默认 URL
-- DOMAIN: http(s)://target_name
-- IP: http(s)://ip
-- CIDR: 展开为所有 IP 的 http(s)://ip
+使用 TargetExportService 统一处理导出逻辑和默认值回退
+数据源: Endpoint.url
 """
 
 import logging
-import ipaddress
-from pathlib import Path
 from typing import Dict, Optional
 
 from prefect import task
 
-from apps.asset.services import EndpointService
-from apps.targets.services import TargetService
-from apps.targets.models import Target
+from apps.asset.models import Endpoint
+from apps.scan.services import TargetExportService, BlacklistService
 
 logger = logging.getLogger(__name__)
 
@@ -29,17 +20,21 @@ def export_endpoints_task(
     target_id: int,
     output_file: str,
     batch_size: int = 1000,
-    target_name: Optional[str] = None,
 ) -> Dict[str, object]:
     """导出目标下的所有 Endpoint URL 到文本文件。
 
-    默认值模式：如果没有 Endpoint，根据 Target 类型生成默认 URL
+    数据源: Endpoint.url
+    
+    懒加载模式：
+    - 如果数据库为空，根据 Target 类型生成默认 URL
+    - DOMAIN: http(s)://domain
+    - IP: http(s)://ip
+    - CIDR: 展开为所有 IP 的 URL
 
     Args:
         target_id: 目标 ID
         output_file: 输出文件路径（绝对路径）
         batch_size: 每次从数据库迭代的批大小
-        target_name: 目标名称（用于默认值模式）
 
     Returns:
         dict: {
@@ -48,117 +43,23 @@ def export_endpoints_task(
             "total_count": int,
         }
     """
-    try:
-        logger.info("开始导出 Endpoint URL - Target ID: %d, 输出文件: %s", target_id, output_file)
-
-        output_path = Path(output_file)
-        output_path.parent.mkdir(parents=True, exist_ok=True)
-
-        service = EndpointService()
-        url_iterator = service.iter_endpoint_urls_by_target(target_id, chunk_size=batch_size)
-
-        total_count = 0
-        with open(output_path, "w", encoding="utf-8", buffering=8192) as f:
-            for url in url_iterator:
-                f.write(f"{url}\n")
-                total_count += 1
-
-                if total_count % 10000 == 0:
-                    logger.info("已导出 %d 个 Endpoint URL...", total_count)
-
-        # ==================== 懒加载模式：根据 Target 类型生成默认 URL ====================
-        if total_count == 0:
-            total_count = _write_default_urls(target_id, target_name, output_path)
-
-        logger.info(
-            "✓ Endpoint URL 导出完成 - 总数: %d, 文件: %s (%.2f KB)",
-            total_count,
-            str(output_path),
-            output_path.stat().st_size / 1024,
-        )
-
-        return {
-            "success": True,
-            "output_file": str(output_path),
-            "total_count": total_count,
-        }
-
-    except FileNotFoundError as e:
-        logger.error("输出目录不存在: %s", e)
-        raise
-    except PermissionError as e:
-        logger.error("文件写入权限不足: %s", e)
-        raise
-    except Exception as e:
-        logger.exception("导出 Endpoint URL 失败: %s", e)
-        raise
-
-
-def _write_default_urls(target_id: int, target_name: Optional[str], output_path: Path) -> int:
-    """
-    懒加载模式：根据 Target 类型生成默认 URL
+    # 构建数据源 queryset（Task 层决定数据源）
+    queryset = Endpoint.objects.filter(target_id=target_id).values_list('url', flat=True)
     
-    Args:
-        target_id: 目标 ID
-        target_name: 目标名称（可选，如果为空则从数据库查询）
-        output_path: 输出文件路径
-        
-    Returns:
-        int: 生成的 URL 数量
-    """
-    target_service = TargetService()
-    target = target_service.get_target(target_id)
+    # 使用 TargetExportService 处理导出
+    blacklist_service = BlacklistService()
+    export_service = TargetExportService(blacklist_service=blacklist_service)
     
-    if not target:
-        logger.warning("Target ID %d 不存在，无法生成默认 URL", target_id)
-        return 0
+    result = export_service.export_urls(
+        target_id=target_id,
+        output_path=output_file,
+        queryset=queryset,
+        batch_size=batch_size
+    )
     
-    target_name = target.name
-    target_type = target.type
-    
-    logger.info("懒加载模式：Target 类型=%s, 名称=%s", target_type, target_name)
-    
-    total_urls = 0
-    
-    with open(output_path, 'w', encoding='utf-8', buffering=8192) as f:
-        if target_type == Target.TargetType.DOMAIN:
-            f.write(f"http://{target_name}\n")
-            f.write(f"https://{target_name}\n")
-            total_urls = 2
-            logger.info("✓ 域名默认 URL 已写入: http(s)://%s", target_name)
-            
-        elif target_type == Target.TargetType.IP:
-            f.write(f"http://{target_name}\n")
-            f.write(f"https://{target_name}\n")
-            total_urls = 2
-            logger.info("✓ IP 默认 URL 已写入: http(s)://%s", target_name)
-            
-        elif target_type == Target.TargetType.CIDR:
-            try:
-                network = ipaddress.ip_network(target_name, strict=False)
-                
-                for ip in network.hosts():
-                    f.write(f"http://{ip}\n")
-                    f.write(f"https://{ip}\n")
-                    total_urls += 2
-                    
-                    if total_urls % 10000 == 0:
-                        logger.info("已生成 %d 个 URL...", total_urls)
-                
-                # /32 或 /128 特殊处理
-                if total_urls == 0:
-                    ip = str(network.network_address)
-                    f.write(f"http://{ip}\n")
-                    f.write(f"https://{ip}\n")
-                    total_urls = 2
-                
-                logger.info("✓ CIDR 默认 URL 已写入: %d 个 URL (来自 %s)", total_urls, target_name)
-                
-            except ValueError as e:
-                logger.error("CIDR 解析失败: %s - %s", target_name, e)
-                return 0
-        else:
-            logger.warning("不支持的 Target 类型: %s", target_type)
-            return 0
-    
-    return total_urls
+    # 保持返回值格式不变（向后兼容）
+    return {
+        "success": result['success'],
+        "output_file": result['output_file'],
+        "total_count": result['total_count'],
+    }

backend/apps/scan/tasks/vuln_scan/run_and_stream_save_dalfox_vulns_task.py

@@ -112,7 +112,7 @@ def _parse_and_validate_line(line: str) -> Optional[dict]:
         try:
             data = json.loads(raw, strict=False)
         except json.JSONDecodeError:
-            logger.info("跳过非 JSON 行: %s", raw)
+            # logger.info("跳过非 JSON 行: %s", raw)
             return None
 
         if not isinstance(data, dict):

backend/apps/scan/tasks/vuln_scan/run_and_stream_save_nuclei_vulns_task.py

@@ -111,7 +111,7 @@ def _parse_and_validate_line(line: str) -> Optional[dict]:
             # Nuclei 输出的 response 字段可能包含原始 HTTP 响应，其中有控制字符
             data = json.loads(raw, strict=False)
         except json.JSONDecodeError:
-            logger.info("跳过非 JSON 行: %s", raw)
+            # logger.info("跳过非 JSON 行: %s", raw)
             return None
 
         if not isinstance(data, dict):

backend/apps/scan/tasks/workspace_tasks.py

@@ -1,54 +0,0 @@
-"""
-工作空间相关的 Prefect Tasks
-
-负责扫描工作空间的创建、验证和管理
-"""
-
-from pathlib import Path
-from prefect import task
-import logging
-
-logger = logging.getLogger(__name__)
-
-
-@task(
-    name="create_scan_workspace",
-    description="创建并验证 Scan 工作空间目录",
-    retries=2,
-    retry_delay_seconds=5
-)
-def create_scan_workspace_task(scan_workspace_dir: str) -> Path:
-    """
-    创建并验证 Scan 工作空间目录
-    
-    Args:
-        scan_workspace_dir: Scan 工作空间目录路径
-    
-    Returns:
-        Path: 创建的 Scan 工作空间路径对象
-    
-    Raises:
-        OSError: 目录创建失败或不可写
-    """
-    scan_workspace_path = Path(scan_workspace_dir)
-    
-    # 创建目录
-    try:
-        scan_workspace_path.mkdir(parents=True, exist_ok=True)
-        logger.info("✓ Scan 工作空间已创建: %s", scan_workspace_path)
-    except OSError as e:
-        logger.error("创建 Scan 工作空间失败: %s - %s", scan_workspace_dir, e)
-        raise
-    
-    # 验证目录是否可写
-    test_file = scan_workspace_path / ".test_write"
-    try:
-        test_file.touch()
-        test_file.unlink()
-        logger.info("✓ Scan 工作空间验证通过（可写）: %s", scan_workspace_path)
-    except OSError as e:
-        error_msg = f"Scan 工作空间不可写: {scan_workspace_path}"
-        logger.error(error_msg)
-        raise OSError(error_msg) from e
-    
-    return scan_workspace_path

backend/apps/scan/utils/__init__.py

@@ -10,11 +10,15 @@ from .command_executor import execute_and_wait, execute_stream
 from .wordlist_helpers import ensure_wordlist_local
 from .nuclei_helpers import ensure_nuclei_templates_local
 from .performance import FlowPerformanceTracker, CommandPerformanceTracker
+from .workspace_utils import setup_scan_workspace, setup_scan_directory
 from . import config_parser
 
 __all__ = [
     # 目录清理
     'remove_directory',
+    # 工作空间
+    'setup_scan_workspace',  # 创建 Scan 根工作空间
+    'setup_scan_directory',  # 创建扫描子目录
     # 命令构建
     'build_scan_command',    # 扫描工具命令构建（基于 f-string）
     # 命令执行

backend/apps/scan/utils/config_parser.py

@@ -169,26 +169,23 @@ def parse_enabled_tools_from_dict(
             )
         
         if enabled_value:
-            # 检查 timeout 必需参数
-            if 'timeout' not in config:
-                raise ValueError(f"工具 {name} 缺少必需参数 'timeout'")
+            # timeout 默认为 'auto'，由具体 Flow 自动计算
+            timeout_value = config.get('timeout', 'auto')
             
             # 验证 timeout 值的有效性
-            timeout_value = config['timeout']
-            
-            if timeout_value == 'auto':
-                # 允许 'auto'，由具体 Flow 处理
-                pass
-            elif isinstance(timeout_value, int):
-                if timeout_value <= 0:
-                    raise ValueError(f"工具 {name} 的 timeout 参数无效（{timeout_value}），必须大于0")
-            else:
-                raise ValueError(
-                    f"工具 {name} 的 timeout 参数类型错误：期望 int 或 'auto'，实际 {type(timeout_value).__name__}"
-                )
+            if timeout_value != 'auto':
+                if isinstance(timeout_value, int):
+                    if timeout_value <= 0:
+                        raise ValueError(f"工具 {name} 的 timeout 参数无效（{timeout_value}），必须大于0")
+                else:
+                    raise ValueError(
+                        f"工具 {name} 的 timeout 参数类型错误：期望 int 或 'auto'，实际 {type(timeout_value).__name__}"
+                    )
             
             # 将配置 key 中划线转为下划线，统一给下游代码使用
-            enabled_tools[name] = _normalize_config_keys(config)
+            normalized_config = _normalize_config_keys(config)
+            normalized_config['timeout'] = timeout_value  # 确保 timeout 存在
+            enabled_tools[name] = normalized_config
     
     logger.info(f"扫描类型: {scan_type}, 启用工具: {len(enabled_tools)}/{len(tools)}")
     

backend/apps/scan/utils/fingerprint_helpers.py

@@ -0,0 +1,230 @@
+"""指纹文件本地缓存工具
+
+提供 Worker 侧的指纹文件缓存和版本校验功能，用于：
+- 指纹识别扫描 (fingerprint_detect_flow)
+"""
+
+import json
+import logging
+import os
+
+from django.conf import settings
+
+logger = logging.getLogger(__name__)
+
+
+# 指纹库映射：lib_name → ensure_func_name
+FINGERPRINT_LIB_MAP = {
+    'ehole': 'ensure_ehole_fingerprint_local',
+    'goby': 'ensure_goby_fingerprint_local',
+    'wappalyzer': 'ensure_wappalyzer_fingerprint_local',
+}
+
+
+def ensure_ehole_fingerprint_local() -> str:
+    """
+    确保本地存在最新的 EHole 指纹文件（带缓存）
+    
+    流程：
+    1. 获取当前指纹库版本
+    2. 检查缓存文件是否存在且版本匹配
+    3. 版本不匹配则重新导出
+    
+    Returns:
+        str: 本地指纹文件路径
+    
+    使用场景：
+        Worker 执行扫描任务前调用，获取最新指纹文件路径
+    """
+    from apps.engine.services.fingerprints import EholeFingerprintService
+    
+    service = EholeFingerprintService()
+    current_version = service.get_fingerprint_version()
+    
+    # 缓存目录和文件
+    base_dir = getattr(settings, 'FINGERPRINTS_BASE_PATH', '/opt/xingrin/fingerprints')
+    os.makedirs(base_dir, exist_ok=True)
+    cache_file = os.path.join(base_dir, 'ehole.json')
+    version_file = os.path.join(base_dir, 'ehole.version')
+    
+    # 检查缓存版本
+    cached_version = None
+    if os.path.exists(version_file):
+        try:
+            with open(version_file, 'r') as f:
+                cached_version = f.read().strip()
+        except OSError as e:
+            logger.warning("读取版本文件失败: %s", e)
+    
+    # 版本匹配，直接返回缓存
+    if cached_version == current_version and os.path.exists(cache_file):
+        logger.info("EHole 指纹文件缓存有效（版本匹配）: %s", cache_file)
+        return cache_file
+    
+    # 版本不匹配，重新导出
+    logger.info(
+        "EHole 指纹文件需要更新: cached=%s, current=%s",
+        cached_version, current_version
+    )
+    count = service.export_to_file(cache_file)
+    
+    # 写入版本文件
+    try:
+        with open(version_file, 'w') as f:
+            f.write(current_version)
+    except OSError as e:
+        logger.warning("写入版本文件失败: %s", e)
+    
+    logger.info("EHole 指纹文件已更新: %s", cache_file)
+    return cache_file
+
+
+def ensure_goby_fingerprint_local() -> str:
+    """
+    确保本地存在最新的 Goby 指纹文件（带缓存）
+    
+    Returns:
+        str: 本地指纹文件路径
+    """
+    from apps.engine.services.fingerprints import GobyFingerprintService
+    
+    service = GobyFingerprintService()
+    current_version = service.get_fingerprint_version()
+    
+    # 缓存目录和文件
+    base_dir = getattr(settings, 'FINGERPRINTS_BASE_PATH', '/opt/xingrin/fingerprints')
+    os.makedirs(base_dir, exist_ok=True)
+    cache_file = os.path.join(base_dir, 'goby.json')
+    version_file = os.path.join(base_dir, 'goby.version')
+    
+    # 检查缓存版本
+    cached_version = None
+    if os.path.exists(version_file):
+        try:
+            with open(version_file, 'r') as f:
+                cached_version = f.read().strip()
+        except OSError as e:
+            logger.warning("读取 Goby 版本文件失败: %s", e)
+    
+    # 版本匹配，直接返回缓存
+    if cached_version == current_version and os.path.exists(cache_file):
+        logger.info("Goby 指纹文件缓存有效（版本匹配）: %s", cache_file)
+        return cache_file
+    
+    # 版本不匹配，重新导出
+    logger.info(
+        "Goby 指纹文件需要更新: cached=%s, current=%s",
+        cached_version, current_version
+    )
+    # Goby 导出格式是数组，直接写入
+    data = service.get_export_data()
+    with open(cache_file, 'w', encoding='utf-8') as f:
+        json.dump(data, f, ensure_ascii=False)
+    
+    # 写入版本文件
+    try:
+        with open(version_file, 'w') as f:
+            f.write(current_version)
+    except OSError as e:
+        logger.warning("写入 Goby 版本文件失败: %s", e)
+    
+    logger.info("Goby 指纹文件已更新: %s", cache_file)
+    return cache_file
+
+
+def ensure_wappalyzer_fingerprint_local() -> str:
+    """
+    确保本地存在最新的 Wappalyzer 指纹文件（带缓存）
+    
+    Returns:
+        str: 本地指纹文件路径
+    """
+    from apps.engine.services.fingerprints import WappalyzerFingerprintService
+    
+    service = WappalyzerFingerprintService()
+    current_version = service.get_fingerprint_version()
+    
+    # 缓存目录和文件
+    base_dir = getattr(settings, 'FINGERPRINTS_BASE_PATH', '/opt/xingrin/fingerprints')
+    os.makedirs(base_dir, exist_ok=True)
+    cache_file = os.path.join(base_dir, 'wappalyzer.json')
+    version_file = os.path.join(base_dir, 'wappalyzer.version')
+    
+    # 检查缓存版本
+    cached_version = None
+    if os.path.exists(version_file):
+        try:
+            with open(version_file, 'r') as f:
+                cached_version = f.read().strip()
+        except OSError as e:
+            logger.warning("读取 Wappalyzer 版本文件失败: %s", e)
+    
+    # 版本匹配，直接返回缓存
+    if cached_version == current_version and os.path.exists(cache_file):
+        logger.info("Wappalyzer 指纹文件缓存有效（版本匹配）: %s", cache_file)
+        return cache_file
+    
+    # 版本不匹配，重新导出
+    logger.info(
+        "Wappalyzer 指纹文件需要更新: cached=%s, current=%s",
+        cached_version, current_version
+    )
+    # Wappalyzer 导出格式是 {"apps": {...}}
+    data = service.get_export_data()
+    with open(cache_file, 'w', encoding='utf-8') as f:
+        json.dump(data, f, ensure_ascii=False)
+    
+    # 写入版本文件
+    try:
+        with open(version_file, 'w') as f:
+            f.write(current_version)
+    except OSError as e:
+        logger.warning("写入 Wappalyzer 版本文件失败: %s", e)
+    
+    logger.info("Wappalyzer 指纹文件已更新: %s", cache_file)
+    return cache_file
+
+
+def get_fingerprint_paths(lib_names: list) -> dict:
+    """
+    获取多个指纹库的本地路径
+    
+    Args:
+        lib_names: 指纹库名称列表，如 ['ehole', 'goby']
+        
+    Returns:
+        dict: {lib_name: local_path}，如 {'ehole': '/opt/xingrin/fingerprints/ehole.json'}
+        
+    示例：
+        paths = get_fingerprint_paths(['ehole'])
+        # {'ehole': '/opt/xingrin/fingerprints/ehole.json'}
+    """
+    paths = {}
+    for lib_name in lib_names:
+        if lib_name not in FINGERPRINT_LIB_MAP:
+            logger.warning("不支持的指纹库: %s，跳过", lib_name)
+            continue
+        
+        ensure_func_name = FINGERPRINT_LIB_MAP[lib_name]
+        # 获取当前模块中的函数
+        ensure_func = globals().get(ensure_func_name)
+        if ensure_func is None:
+            logger.warning("指纹库 %s 的导出函数 %s 未实现，跳过", lib_name, ensure_func_name)
+            continue
+        
+        try:
+            paths[lib_name] = ensure_func()
+        except Exception as e:
+            logger.error("获取指纹库 %s 路径失败: %s", lib_name, e)
+            continue
+    
+    return paths
+
+
+__all__ = [
+    "ensure_ehole_fingerprint_local",
+    "ensure_goby_fingerprint_local",
+    "ensure_wappalyzer_fingerprint_local",
+    "get_fingerprint_paths",
+    "FINGERPRINT_LIB_MAP",
+]