fix(logger): ensure logger is a Logger instance in crawling strategies. ref #1437

- Fix URLPatternFilter serialization by preventing private __slots__ from being serialized as constructor params
  - Add public attributes to URLPatternFilter to store original constructor parameters for proper serialization
  - Handle property descriptors in CrawlResult.model_dump() to prevent JSON serialization errors
  - Ensure filter chains work correctly with Docker client and REST API

  The issue occurred because:
  1. Private implementation details (_simple_suffixes, etc.) were being serialized and passed as constructor arguments during deserialization
  2. Property descriptors were being included in the serialized output, causing "Object of type property is not JSON serializable" errors

  Changes:
  - async_configs.py: Comment out __slots__ serialization logic (lines 100-109)
  - filters.py: Add patterns, use_glob, reverse to URLPatternFilter __slots__ and store as public attributes
  - models.py: Convert property descriptors to strings in model_dump() instead of including them directly

README.md

@@ -373,7 +373,7 @@ async def main():
     
     async with AsyncWebCrawler(config=browser_config) as crawler:
         result = await crawler.arun(
-            url="https://docs.micronaut.io/4.7.6/guide/",
+            url="https://docs.micronaut.io/4.9.9/guide/",
             config=run_config
         )
         print(len(result.markdown.raw_markdown))
@@ -425,7 +425,7 @@ async def main():
             "type": "attribute",
             "attribute": "src"
         }
-    }
+    ]
 }
 
     extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)

crawl4ai/async_configs.py

@@ -97,13 +97,16 @@ def to_serializable_dict(obj: Any, ignore_default_value : bool = False) -> Dict:
                 if value != param.default and not ignore_default_value:
                     current_values[name] = to_serializable_dict(value)
         
-        if hasattr(obj, '__slots__'):
-            for slot in obj.__slots__:
-                if slot.startswith('_'):  # Handle private slots
-                    attr_name = slot[1:]  # Remove leading '_'
-                    value = getattr(obj, slot, None)
-                    if value is not None:
-                        current_values[attr_name] = to_serializable_dict(value)
+        # Don't serialize private __slots__ - they're internal implementation details
+        # not constructor parameters. This was causing URLPatternFilter to fail
+        # because _simple_suffixes was being serialized as 'simple_suffixes'
+        # if hasattr(obj, '__slots__'):
+        #     for slot in obj.__slots__:
+        #         if slot.startswith('_'):  # Handle private slots
+        #             attr_name = slot[1:]  # Remove leading '_'
+        #             value = getattr(obj, slot, None)
+        #             if value is not None:
+        #                 current_values[attr_name] = to_serializable_dict(value)
 
             
         

crawl4ai/async_crawler_strategy.back.py

@@ -824,7 +824,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
             except Error:
                 visibility_info = await self.check_visibility(page)
 
-                if self.browser_config.config.verbose:
+                if self.browser_config.verbose:
                     self.logger.debug(
                         message="Body visibility info: {info}",
                         tag="DEBUG",

crawl4ai/deep_crawling/bff_strategy.py

@@ -47,7 +47,13 @@ class BestFirstCrawlingStrategy(DeepCrawlStrategy):
         self.url_scorer = url_scorer
         self.include_external = include_external
         self.max_pages = max_pages
-        self.logger = logger or logging.getLogger(__name__)
+        # self.logger = logger or logging.getLogger(__name__)
+        # Ensure logger is always a Logger instance, not a dict from serialization
+        if isinstance(logger, logging.Logger):
+            self.logger = logger
+        else:
+            # Create a new logger if logger is None, dict, or any other non-Logger type
+            self.logger = logging.getLogger(__name__)
         self.stats = TraversalStats(start_time=datetime.now())
         self._cancel_event = asyncio.Event()
         self._pages_crawled = 0

crawl4ai/deep_crawling/bfs_strategy.py

@@ -38,7 +38,13 @@ class BFSDeepCrawlStrategy(DeepCrawlStrategy):
         self.include_external = include_external
         self.score_threshold = score_threshold
         self.max_pages = max_pages
-        self.logger = logger or logging.getLogger(__name__)
+        # self.logger = logger or logging.getLogger(__name__)
+        # Ensure logger is always a Logger instance, not a dict from serialization
+        if isinstance(logger, logging.Logger):
+            self.logger = logger
+        else:
+            # Create a new logger if logger is None, dict, or any other non-Logger type
+            self.logger = logging.getLogger(__name__)
         self.stats = TraversalStats(start_time=datetime.now())
         self._cancel_event = asyncio.Event()
         self._pages_crawled = 0

crawl4ai/deep_crawling/filters.py

@@ -120,6 +120,9 @@ class URLPatternFilter(URLFilter):
     """Pattern filter balancing speed and completeness"""
 
     __slots__ = (
+        "patterns",  # Store original patterns for serialization
+        "use_glob",  # Store original use_glob for serialization  
+        "reverse",   # Store original reverse for serialization
         "_simple_suffixes",
         "_simple_prefixes",
         "_domain_patterns",
@@ -142,6 +145,11 @@ class URLPatternFilter(URLFilter):
         reverse: bool = False,
     ):
         super().__init__()
+        # Store original constructor params for serialization
+        self.patterns = patterns
+        self.use_glob = use_glob
+        self.reverse = reverse
+        
         self._reverse = reverse
         patterns = [patterns] if isinstance(patterns, (str, Pattern)) else patterns
 

crawl4ai/models.py

@@ -253,6 +253,16 @@ class CrawlResult(BaseModel):
         requirements change, this is where you would update the logic.
         """
         result = super().model_dump(*args, **kwargs)
+        
+        # Remove any property descriptors that might have been included
+        # These deprecated properties should not be in the serialized output
+        for key in ['fit_html', 'fit_markdown', 'markdown_v2']:
+            if key in result and isinstance(result[key], property):
+                # del result[key]
+                # Nasrin: I decided to convert it to string instead of removing it.
+                result[key] = str(result[key])
+        
+        # Add the markdown field properly
         if self._markdown is not None:
             result["markdown"] = self._markdown.model_dump() 
         return result

deploy/docker/api.py

@@ -4,7 +4,7 @@ import asyncio
 from typing import List, Tuple, Dict
 from functools import partial
 from uuid import uuid4
-from datetime import datetime
+from datetime import datetime, timezone
 from base64 import b64encode
 
 import logging
@@ -576,7 +576,7 @@ async def handle_crawl_job(
     task_id = f"crawl_{uuid4().hex[:8]}"
     await redis.hset(f"task:{task_id}", mapping={
         "status": TaskStatus.PROCESSING,         # <-- keep enum values consistent
-        "created_at": datetime.utcnow().isoformat(),
+        "created_at": datetime.now(timezone.utc).replace(tzinfo=None).isoformat(),
         "url": json.dumps(urls),                 # store list as JSON string
         "result": "",
         "error": "",

docs/md_v2/core/url-seeding.md

@@ -102,16 +102,16 @@ async def smart_blog_crawler():
     
     # Step 2: Configure discovery - let's find all blog posts
     config = SeedingConfig(
-        source="sitemap",           # Use the website's sitemap
-        pattern="*/blog/*.html",    # Only blog posts
+        source="sitemap+cc",      # Use the website's sitemap+cc
+        pattern="*/courses/*",    # Only courses related posts
         extract_head=True,          # Get page metadata
         max_urls=100               # Limit for this example
     )
     
     # Step 3: Discover URLs from the Python blog
-    print("🔍 Discovering blog posts...")
+    print("🔍 Discovering course posts...")
     urls = await seeder.urls("realpython.com", config)
-    print(f"✅ Found {len(urls)} blog posts")
+    print(f"✅ Found {len(urls)} course posts")
     
     # Step 4: Filter for Python tutorials (using metadata!)
     tutorials = [
@@ -134,7 +134,8 @@ async def smart_blog_crawler():
     async with AsyncWebCrawler() as crawler:
         config = CrawlerRunConfig(
             only_text=True,
-            word_count_threshold=300  # Only substantial articles
+            word_count_threshold=300,  # Only substantial articles
+            stream=True
         )
         
         # Extract URLs and crawl them
@@ -155,7 +156,7 @@ asyncio.run(smart_blog_crawler())
 
 **What just happened?**
 
-1. We discovered all blog URLs from the sitemap
+1. We discovered all blog URLs from the sitemap+cc
 2. We filtered using metadata (no crawling needed!)
 3. We crawled only the relevant tutorials
 4. We saved tons of time and bandwidth
@@ -282,8 +283,8 @@ config = SeedingConfig(
     live_check=True,  # Verify each URL is accessible
     concurrency=20    # Check 20 URLs in parallel
 )
-
-urls = await seeder.urls("example.com", config)
+async with AsyncUrlSeeder() as seeder:
+    urls = await seeder.urls("example.com", config)
 
 # Now you can filter by status
 live_urls = [u for u in urls if u["status"] == "valid"]
@@ -311,8 +312,8 @@ This is where URL seeding gets really powerful. Instead of crawling entire pages
 config = SeedingConfig(
     extract_head=True  # Extract metadata from <head> section
 )
-
-urls = await seeder.urls("example.com", config)
+async with AsyncUrlSeeder() as seeder:
+    urls = await seeder.urls("example.com", config)
 
 # Now each URL has rich metadata
 for url in urls[:3]:
@@ -387,8 +388,8 @@ config = SeedingConfig(
     scoring_method="bm25",
     score_threshold=0.3
 )
-
-urls = await seeder.urls("example.com", config)
+async with AsyncUrlSeeder() as seeder:
+    urls = await seeder.urls("example.com", config)
 
 # URLs are scored based on:
 # 1. Domain parts matching (e.g., 'python' in python.example.com)
@@ -429,8 +430,8 @@ config = SeedingConfig(
     extract_head=True,
     live_check=True
 )
-
-urls = await seeder.urls("blog.example.com", config)
+async with AsyncUrlSeeder() as seeder:
+    urls = await seeder.urls("blog.example.com", config)
 
 # Analyze the results
 for url in urls[:5]:
@@ -488,8 +489,8 @@ config = SeedingConfig(
     scoring_method="bm25",       # Use BM25 algorithm
     score_threshold=0.3          # Minimum relevance score
 )
-
-urls = await seeder.urls("realpython.com", config)
+async with AsyncUrlSeeder() as seeder:
+    urls = await seeder.urls("realpython.com", config)
 
 # Results are automatically sorted by relevance!
 for url in urls[:5]:
@@ -511,8 +512,8 @@ config = SeedingConfig(
     score_threshold=0.5,
     max_urls=20
 )
-
-urls = await seeder.urls("docs.example.com", config)
+async with AsyncUrlSeeder() as seeder:
+    urls = await seeder.urls("docs.example.com", config)
 
 # The highest scoring URLs will be API docs!
 ```
@@ -529,8 +530,8 @@ config = SeedingConfig(
     score_threshold=0.4,
     pattern="*/product/*"  # Combine with pattern matching
 )
-
-urls = await seeder.urls("shop.example.com", config)
+async with AsyncUrlSeeder() as seeder:
+    urls = await seeder.urls("shop.example.com", config)
 
 # Filter further by price (from metadata)
 affordable = [
@@ -550,8 +551,8 @@ config = SeedingConfig(
     scoring_method="bm25",
     score_threshold=0.35
 )
-
-urls = await seeder.urls("technews.com", config)
+async with AsyncUrlSeeder() as seeder:
+    urls = await seeder.urls("technews.com", config)
 
 # Filter by date
 from datetime import datetime, timedelta
@@ -591,8 +592,8 @@ for query in queries:
         score_threshold=0.4,
         max_urls=10  # Top 10 per topic
     )
-    
-    urls = await seeder.urls("learning-platform.com", config)
+    async with AsyncUrlSeeder() as seeder:
+        urls = await seeder.urls("learning-platform.com", config)
     all_tutorials.extend(urls)
 
 # Remove duplicates while preserving order
@@ -625,7 +626,8 @@ config = SeedingConfig(
 )
 
 # Returns a dictionary: {domain: [urls]}
-results = await seeder.many_urls(domains, config)
+async with AsyncUrlSeeder() as seeder:
+    results = await seeder.many_urls(domains, config)
 
 # Process results
 for domain, urls in results.items():
@@ -654,8 +656,8 @@ config = SeedingConfig(
     pattern="*/blog/*",
     max_urls=100
 )
-
-results = await seeder.many_urls(competitors, config)
+async with AsyncUrlSeeder() as seeder:
+    results = await seeder.many_urls(competitors, config)
 
 # Analyze content types
 for domain, urls in results.items():
@@ -690,8 +692,8 @@ config = SeedingConfig(
     score_threshold=0.3,
     max_urls=20  # Per site
 )
-
-results = await seeder.many_urls(educational_sites, config)
+async with AsyncUrlSeeder() as seeder:
+    results = await seeder.many_urls(educational_sites, config)
 
 # Find the best beginner tutorials
 all_tutorials = []
@@ -731,8 +733,8 @@ config = SeedingConfig(
     score_threshold=0.5,  # High threshold for relevance
     max_urls=10
 )
-
-results = await seeder.many_urls(news_sites, config)
+async with AsyncUrlSeeder() as seeder:
+    results = await seeder.many_urls(news_sites, config)
 
 # Collect all mentions
 mentions = []

tests/docker/test_filter_deep_crawl.py

@@ -0,0 +1,201 @@
+"""
+Test the complete fix for both the filter serialization and JSON serialization issues.
+"""
+
+import asyncio
+import httpx
+
+from crawl4ai import BrowserConfig, CacheMode, CrawlerRunConfig
+from crawl4ai.deep_crawling import BFSDeepCrawlStrategy, FilterChain, URLPatternFilter
+
+BASE_URL = "http://localhost:11234/"  # Adjust port as needed
+
+async def test_with_docker_client():
+    """Test using the Docker client (same as 1419.py)."""
+    from crawl4ai.docker_client import Crawl4aiDockerClient
+    
+    print("=" * 60)
+    print("Testing with Docker Client")
+    print("=" * 60)
+    
+    try:
+        async with Crawl4aiDockerClient(
+            base_url=BASE_URL,
+            verbose=True,
+        ) as client:
+            
+            # Create filter chain - testing the serialization fix
+            filter_chain = [
+                URLPatternFilter(
+                    # patterns=["*about*", "*privacy*", "*terms*"],
+                    patterns=["*advanced*"],
+                    reverse=True
+                ),
+            ]
+            
+            crawler_config = CrawlerRunConfig(
+                deep_crawl_strategy=BFSDeepCrawlStrategy(
+                    max_depth=2,  # Keep it shallow for testing
+                    # max_pages=5,  # Limit pages for testing
+                    filter_chain=FilterChain(filter_chain)
+                ),
+                cache_mode=CacheMode.BYPASS,
+            )
+            
+            print("\n1. Testing crawl with filters...")
+            results = await client.crawl(
+                ["https://docs.crawl4ai.com"],  # Simple test page
+                browser_config=BrowserConfig(headless=True),
+                crawler_config=crawler_config,
+            )
+            
+            if results:
+                print(f"✅ Crawl succeeded! Type: {type(results)}")
+                if hasattr(results, 'success'):
+                    print(f"✅ Results success: {results.success}")
+                    # Test that we can iterate results without JSON errors
+                    if hasattr(results, '__iter__'):
+                        for i, result in enumerate(results):
+                            if hasattr(result, 'url'):
+                                print(f"   Result {i}: {result.url[:50]}...")
+                            else:
+                                print(f"   Result {i}: {str(result)[:50]}...")
+                else:
+                    # Handle list of results
+                    print(f"✅ Got {len(results)} results")
+                    for i, result in enumerate(results[:3]):  # Show first 3
+                        print(f"   Result {i}: {result.url[:50]}...")
+            else:
+                print("❌ Crawl failed - no results returned")
+                return False
+                
+        print("\n✅ Docker client test completed successfully!")
+        return True
+        
+    except Exception as e:
+        print(f"❌ Docker client test failed: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+
+async def test_with_rest_api():
+    """Test using REST API directly."""
+    print("\n" + "=" * 60)
+    print("Testing with REST API")
+    print("=" * 60)
+    
+    # Create filter configuration
+    deep_crawl_strategy_payload = {
+        "type": "BFSDeepCrawlStrategy",
+        "params": {
+            "max_depth": 2,
+            # "max_pages": 5,
+            "filter_chain": {
+                "type": "FilterChain",
+                "params": {
+                    "filters": [
+                        {
+                            "type": "URLPatternFilter",
+                            "params": {
+                                "patterns": ["*advanced*"],
+                                "reverse": True
+                            }
+                        }
+                    ]
+                }
+            }
+        }
+    }
+    
+    crawl_payload = {
+        "urls": ["https://docs.crawl4ai.com"],
+        "browser_config": {"type": "BrowserConfig", "params": {"headless": True}},
+        "crawler_config": {
+            "type": "CrawlerRunConfig",
+            "params": {
+                "deep_crawl_strategy": deep_crawl_strategy_payload,
+                "cache_mode": "bypass"
+            }
+        }
+    }
+    
+    try:
+        async with httpx.AsyncClient() as client:
+            print("\n1. Sending crawl request to REST API...")
+            response = await client.post(
+                f"{BASE_URL}crawl",
+                json=crawl_payload,
+                timeout=30
+            )
+            
+            if response.status_code == 200:
+                print(f"✅ REST API returned 200 OK")
+                data = response.json()
+                if data.get("success"):
+                    results = data.get("results", [])
+                    print(f"✅ Got {len(results)} results")
+                    for i, result in enumerate(results[:3]):
+                        print(f"   Result {i}: {result.get('url', 'unknown')[:50]}...")
+                else:
+                    print(f"❌ Crawl not successful: {data}")
+                    return False
+            else:
+                print(f"❌ REST API returned {response.status_code}")
+                print(f"   Response: {response.text[:500]}")
+                return False
+                
+        print("\n✅ REST API test completed successfully!")
+        return True
+        
+    except Exception as e:
+        print(f"❌ REST API test failed: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+
+async def main():
+    """Run all tests."""
+    print("\n🧪 TESTING COMPLETE FIX FOR DOCKER FILTER AND JSON ISSUES")
+    print("=" * 60)
+    print("Make sure the server is running with the updated code!")
+    print("=" * 60)
+    
+    results = []
+    
+    # Test 1: Docker client
+    docker_passed = await test_with_docker_client()
+    results.append(("Docker Client", docker_passed))
+    
+    # Test 2: REST API
+    rest_passed = await test_with_rest_api()
+    results.append(("REST API", rest_passed))
+    
+    # Summary
+    print("\n" + "=" * 60)
+    print("FINAL TEST SUMMARY")
+    print("=" * 60)
+    
+    all_passed = True
+    for test_name, passed in results:
+        status = "✅ PASSED" if passed else "❌ FAILED"
+        print(f"{test_name:20} {status}")
+        if not passed:
+            all_passed = False
+    
+    print("=" * 60)
+    if all_passed:
+        print("🎉 ALL TESTS PASSED! Both issues are fully resolved!")
+        print("\nThe fixes:")
+        print("1. Filter serialization: Fixed by not serializing private __slots__")
+        print("2. JSON serialization: Fixed by removing property descriptors from model_dump()")
+    else:
+        print("⚠️ Some tests failed. Please check the server logs for details.")
+    
+    return 0 if all_passed else 1
+
+
+if __name__ == "__main__":
+    import sys
+    sys.exit(asyncio.run(main()))