[버그수정]

crawler_platform/app/api/routes.py

@@ -11,6 +11,7 @@ from crawler_platform.app.config.loader import load_project_config
 from crawler_platform.app.core.crawler.discovery import discover_links
 from crawler_platform.app.core.crawler.fetchers import RobotsPolicy, make_fetcher
 from crawler_platform.app.core.crawler.pipeline import CrawlPipeline
+from crawler_platform.app.core.crawler.site_crawler import SiteCrawler
 from crawler_platform.app.core.database import models
 from crawler_platform.app.core.database.repository import KnowledgeRepository
 from crawler_platform.app.core.database.session import session_scope
@@ -30,6 +31,13 @@ class CrawlRequest(BaseModel):
     extractor_base_url: str | None = None
 
 
+class SiteCrawlRequest(CrawlRequest):
+    max_depth: int = 2
+    max_pages: int = 50
+    same_domain_only: bool = True
+    analyze_page_types: list[str] = Field(default_factory=lambda: ["product", "brand", "review"])
+
+
 class DiscoverRequest(BaseModel):
     config_path: str
     source_name: str
@@ -158,6 +166,34 @@ def register_routes(app, database_url: str) -> None:
                 raise HTTPException(status_code=400, detail=str(exc)) from exc
             return {"page_id": result.page_id, "claim_count": result.claim_count, "entity_count": result.entity_count}
 
+    @app.post("/crawl-site")
+    def crawl_site(request: SiteCrawlRequest):
+        config = load_project_config(request.config_path)
+        with session_scope(database_url) as session:
+            repo = KnowledgeRepository(session)
+            crawler = SiteCrawler(
+                repo,
+                extractor_for_domain(
+                    config.domain,
+                    provider=request.extractor_provider,
+                    model=request.extractor_model,
+                    base_url=request.extractor_base_url,
+                ),
+            )
+            try:
+                result = crawler.crawl_site(
+                    config,
+                    request.source_name,
+                    request.url,
+                    max_depth=max(request.max_depth, 0),
+                    max_pages=max(min(request.max_pages, 500), 1),
+                    same_domain_only=request.same_domain_only,
+                    analyze_page_types=set(request.analyze_page_types),
+                )
+            except Exception as exc:
+                raise HTTPException(status_code=400, detail=str(exc)) from exc
+            return asdict(result)
+
     @app.post("/discover")
     def discover(request: DiscoverRequest):
         config = load_project_config(request.config_path)