fix(deep_crawling): allow single-label hostnames

crawl4ai/deep_crawling/bfs_strategy.py

@@ -70,8 +70,6 @@ async def can_process_url(self, url: str, depth: int) -> bool:
                 raise ValueError("Missing scheme or netloc")
             if parsed.scheme not in ("http", "https"):
                 raise ValueError("Invalid scheme")
-            if "." not in parsed.netloc:
-                raise ValueError("Invalid domain")
         except Exception as e:
             self.logger.warning(f"Invalid URL: {url}, error: {e}")
             return False

tests/deep_crawling/test_deep_crawl_resume.py

@@ -628,6 +628,14 @@ async def test_filter_chain_still_works(self):
         assert await strategy.can_process_url("https://example.com/blog/post1", 1) == True
         assert await strategy.can_process_url("https://other.com/blog/post1", 1) == False
 
+    @pytest.mark.asyncio
+    async def test_single_label_hostname_is_valid(self):
+        """Single-label hostnames can reach the configured filter chain."""
+        filter_chain = FilterChain([DomainFilter(allowed_domains=["intranet"])])
+        strategy = BFSDeepCrawlStrategy(max_depth=1, filter_chain=filter_chain)
+
+        assert await strategy.can_process_url("https://intranet/docs", 1) is True
+
     @pytest.mark.asyncio
     async def test_url_scorer_still_works(self):
         """URL scoring integration unchanged."""