fix: /crawl/sources 包含独立爬虫来源 + trigger 支持 spider_name

- sources 接口原来只返回 GXGP 子来源，遗漏了大化县政府网
- trigger 接口现在支持 spider_name 参数指定单个爬虫

app/api/crawl.py

@@ -9,7 +9,10 @@ router = APIRouter()
 @router.post("/crawl/trigger")
 async def trigger_crawl(request: CrawlTriggerRequest):
     service = get_crawl_service()
-    names = service.get_spider_names()
+    if request.spider_name:
+        names = [request.spider_name]
+    else:
+        names = service.get_spider_names()
 
     all_results = []
     total_stored = 0
@@ -46,9 +49,20 @@ async def crawl_sources():
 
     from app.config import settings
     sources = json.loads(settings.announcement_sources)
-    return {
+    result = [
-        "sources": [
+        {"code": code, "name": info["name"], "type": info["type"]}
-            {"code": code, "name": info["name"], "type": info["type"]}
+        for code, info in sources.items()
-            for code, info in sources.items()
+    ]
-        ]
+    # 加入独立爬虫来源（非 GXGP 子来源的独立 Spider）
-    }
+    service = get_crawl_service()
+    for name in service.get_spider_names():
+        if name == "gxgp":
+            continue  # gxgp 的子来源已在上面列出
+        spider = service.spiders.get(name)
+        if spider:
+            result.append({
+                "code": spider.source_code,
+                "name": spider.source_name,
+                "type": "independent",
+            })
+    return {"sources": result}

app/models/schemas.py

@@ -29,6 +29,7 @@ class AnnouncementListResponse(BaseModel):
 
 
 class CrawlTriggerRequest(BaseModel):
+    spider_name: str | None = None
     keywords: list[str] | None = None
     sources: list[str] | None = None
     manual: bool = False