Merge pull request #1436 from unclecode/fix/docker-filter

fix(docker): resolve filter serialization and JSON encoding errors in deep crawl strategy

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/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