Fix: enhance fallback scoring for failed head extraction in LinkPreview. ref #1638

Fix: Wrong URL variable used for extraction of raw html

Dockerfile

@@ -167,6 +167,11 @@ RUN mkdir -p /home/appuser/.cache/ms-playwright \
 
 RUN crawl4ai-doctor
 
+# Ensure all cache directories belong to appuser
+# This fixes permission issues with .cache/url_seeder and other runtime cache dirs
+RUN mkdir -p /home/appuser/.cache \
+    && chown -R appuser:appuser /home/appuser/.cache
+
 # Copy application code
 COPY deploy/docker/* ${APP_HOME}/
 

crawl4ai/adaptive_crawler.py

@@ -728,18 +728,18 @@ class EmbeddingStrategy(CrawlStrategy):
         provider = llm_config_dict.get('provider', 'openai/gpt-4o-mini') if llm_config_dict else 'openai/gpt-4o-mini'
         api_token = llm_config_dict.get('api_token') if llm_config_dict else None
         
-        # response = perform_completion_with_backoff(
+        response = perform_completion_with_backoff(
-        #     provider=provider,
+            provider=provider,
-        #     prompt_with_variables=prompt,
+            prompt_with_variables=prompt,
-        #     api_token=api_token,
+            api_token=api_token,
-        #     json_response=True
+            json_response=True
-        # )
+        )
         
-        # variations = json.loads(response.choices[0].message.content)
+        variations = json.loads(response.choices[0].message.content)
         
         
         # # Mock data with more variations for split
-        variations ={'queries': ['what are the best vegetables to use in fried rice?', 'how do I make vegetable fried rice from scratch?', 'can you provide a quick recipe for vegetable fried rice?', 'what cooking techniques are essential for perfect fried rice with vegetables?', 'how to add flavor to vegetable fried rice?', 'are there any tips for making healthy fried rice with vegetables?']}
+        # variations ={'queries': ['what are the best vegetables to use in fried rice?', 'how do I make vegetable fried rice from scratch?', 'can you provide a quick recipe for vegetable fried rice?', 'what cooking techniques are essential for perfect fried rice with vegetables?', 'how to add flavor to vegetable fried rice?', 'are there any tips for making healthy fried rice with vegetables?']}
         
         
         # variations = {'queries': [

crawl4ai/async_webcrawler.py

@@ -617,11 +617,11 @@ class AsyncWebCrawler:
                 else config.chunking_strategy
             )
             sections = chunking.chunk(content)
-            # extracted_content = config.extraction_strategy.run(url, sections)
+            # extracted_content = config.extraction_strategy.run(_url, sections)
 
             # Use async version if available for better parallelism
             if hasattr(config.extraction_strategy, 'arun'):
-                extracted_content = await config.extraction_strategy.arun(url, sections)
+                extracted_content = await config.extraction_strategy.arun(_url, sections)
             else:
                 # Fallback to sync version run in thread pool to avoid blocking
                 extracted_content = await asyncio.to_thread(

crawl4ai/content_scraping_strategy.py

@@ -542,6 +542,19 @@ class LXMLWebScrapingStrategy(ContentScrapingStrategy):
             if el.tag in bypass_tags:
                 continue
 
+            # Skip elements inside <pre> or <code> tags where whitespace is significant
+            # This preserves whitespace-only spans (e.g., <span class="w"> </span>) in code blocks
+            is_in_code_block = False
+            ancestor = el.getparent()
+            while ancestor is not None:
+                if ancestor.tag in ("pre", "code"):
+                    is_in_code_block = True
+                    break
+                ancestor = ancestor.getparent()
+
+            if is_in_code_block:
+                continue
+
             text_content = (el.text_content() or "").strip()
             if (
                 len(text_content.split()) < word_count_threshold

crawl4ai/link_preview.py

@@ -336,8 +336,40 @@ class LinkPreview:
                 
                 updated_internal.append(updated_link)
             else:
-                # Keep original link unchanged
+                # # Keep original link unchanged
-                updated_internal.append(link)
+                # updated_internal.append(link)
+                
+                # Head extraction failed - calculate fallback scores
+                # Use URL-based scoring if query provided
+                contextual_score = None
+                if config.link_preview_config and config.link_preview_config.query:
+                    # Calculate URL-based relevance score as fallback
+                    contextual_score = self.seeder._calculate_url_relevance_score(
+                        config.link_preview_config.query,
+                        link.href
+                    )
+
+                # Create updated link with fallback scoring
+                updated_link = Link(
+                    href=link.href,
+                    text=link.text,
+                    title=link.title,
+                    base_domain=link.base_domain,
+                    head_data=None,  # No head data available
+                    head_extraction_status="failed",
+                    intrinsic_score=getattr(link, 'intrinsic_score', None),
+                    contextual_score=contextual_score
+                )
+
+                # Calculate total score even without head data
+                updated_link.total_score = calculate_total_score(
+                    intrinsic_score=updated_link.intrinsic_score,
+                    contextual_score=updated_link.contextual_score,
+                    score_links_enabled=getattr(config, 'score_links', False),
+                    query_provided=bool(config.link_preview_config and config.link_preview_config.query)
+                )
+
+                updated_internal.append(updated_link)
         
         # Update external links
         updated_external = []
@@ -374,8 +406,40 @@ class LinkPreview:
                 
                 updated_external.append(updated_link)
             else:
-                # Keep original link unchanged
+                # # Keep original link unchanged
-                updated_external.append(link)
+                # updated_external.append(link)
+                
+                # Head extraction failed - calculate fallback scores
+                # Use URL-based scoring if query provided
+                contextual_score = None
+                if config.link_preview_config and config.link_preview_config.query:
+                    # Calculate URL-based relevance score as fallback
+                    contextual_score = self.seeder._calculate_url_relevance_score(
+                        config.link_preview_config.query,
+                        link.href
+                    )
+
+                # Create updated link with fallback scoring
+                updated_link = Link(
+                    href=link.href,
+                    text=link.text,
+                    title=link.title,
+                    base_domain=link.base_domain,
+                    head_data=None,  # No head data available
+                    head_extraction_status="failed",
+                    intrinsic_score=getattr(link, 'intrinsic_score', None),
+                    contextual_score=contextual_score
+                )
+
+                # Calculate total score even without head data
+                updated_link.total_score = calculate_total_score(
+                    intrinsic_score=updated_link.intrinsic_score,
+                    contextual_score=updated_link.contextual_score,
+                    score_links_enabled=getattr(config, 'score_links', False),
+                    query_provided=bool(config.link_preview_config and config.link_preview_config.query)
+                )
+
+                updated_external.append(updated_link)
         
         # Sort links by relevance score if available
         if any(hasattr(link, 'head_data') and link.head_data and 'relevance_score' in link.head_data 

tests/general/test_async_webcrawler.py

@@ -9,6 +9,21 @@ from crawl4ai import (
     RateLimiter,
     CacheMode
 )
+from crawl4ai.extraction_strategy import ExtractionStrategy
+
+class MockExtractionStrategy(ExtractionStrategy):
+    """Mock extraction strategy for testing URL parameter handling"""
+
+    def __init__(self):
+        super().__init__()
+        self.run_calls = []
+
+    def extract(self, url: str, html: str, *args, **kwargs):
+        return [{"test": "data"}]
+
+    def run(self, url: str, sections: List[str], *args, **kwargs):
+        self.run_calls.append(url)
+        return super().run(url, sections, *args, **kwargs)
 
 @pytest.mark.asyncio
 @pytest.mark.parametrize("viewport", [
@@ -142,8 +157,72 @@ async def test_error_handling(error_url):
         assert not result.success
         assert result.error_message is not None
 
+@pytest.mark.asyncio
+async def test_extraction_strategy_run_with_regular_url():
+    """
+    Regression test for extraction_strategy.run URL parameter handling with regular URLs.
+
+    This test verifies that when is_raw_html=False (regular URL),
+    extraction_strategy.run is called with the actual URL.
+    """
+    browser_config = BrowserConfig(
+        browser_type="chromium",
+        headless=True
+    )
+
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        mock_strategy = MockExtractionStrategy()
+
+        # Test regular URL (is_raw_html=False)
+        regular_url = "https://example.com"
+        result = await crawler.arun(
+            url=regular_url,
+            config=CrawlerRunConfig(
+                page_timeout=30000,
+                extraction_strategy=mock_strategy,
+                cache_mode=CacheMode.BYPASS
+            )
+        )
+
+        assert result.success
+        assert len(mock_strategy.run_calls) == 1
+        assert mock_strategy.run_calls[0] == regular_url, f"Expected '{regular_url}', got '{mock_strategy.run_calls[0]}'"
+
+@pytest.mark.asyncio
+async def test_extraction_strategy_run_with_raw_html():
+    """
+    Regression test for extraction_strategy.run URL parameter handling with raw HTML.
+
+    This test verifies that when is_raw_html=True (URL starts with "raw:"),
+    extraction_strategy.run is called with "Raw HTML" instead of the actual URL.
+    """
+    browser_config = BrowserConfig(
+        browser_type="chromium",
+        headless=True
+    )
+
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        mock_strategy = MockExtractionStrategy()
+
+        # Test raw HTML URL (is_raw_html=True automatically set)
+        raw_html_url = "raw:<html><body><h1>Test HTML</h1><p>This is a test.</p></body></html>"
+        result = await crawler.arun(
+            url=raw_html_url,
+            config=CrawlerRunConfig(
+                page_timeout=30000,
+                extraction_strategy=mock_strategy,
+                cache_mode=CacheMode.BYPASS
+            )
+        )
+
+        assert result.success
+        assert len(mock_strategy.run_calls) == 1
+        assert mock_strategy.run_calls[0] == "Raw HTML", f"Expected 'Raw HTML', got '{mock_strategy.run_calls[0]}'"
+
 if __name__ == "__main__":
     asyncio.run(test_viewport_config((1024, 768)))
     asyncio.run(test_memory_management())
     asyncio.run(test_rate_limiting())
     asyncio.run(test_javascript_execution())
+    asyncio.run(test_extraction_strategy_run_with_regular_url())
+    asyncio.run(test_extraction_strategy_run_with_raw_html())