refactor(link_extractor): remove link_extractor and rename to link_preview

This change removes the link_extractor module and renames it to link_preview, streamlining the codebase. The removal of 395 lines of code reduces complexity and improves maintainability. Other files have been updated to reflect this change, ensuring consistency across the project.

BREAKING CHANGE: The link_extractor module has been deleted and replaced with link_preview. Update imports accordingly.

docs/examples/link_head_extraction_example.py

@@ -18,7 +18,7 @@ Usage:
 
 import asyncio
 from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
-from crawl4ai.async_configs import LinkExtractionConfig
+from crawl4ai.async_configs import LinkPreviewConfig
 
 
 async def basic_link_head_extraction():
@@ -30,7 +30,7 @@ async def basic_link_head_extraction():
     
     config = CrawlerRunConfig(
         # Enable link head extraction
-        link_extraction_config=LinkExtractionConfig(
+        link_preview_config=LinkPreviewConfig(
             include_internal=True,           # Process internal links
             include_external=False,          # Skip external links for this demo
             max_links=5,                    # Limit to 5 links
@@ -94,7 +94,7 @@ async def research_assistant_example():
     print("=" * 50)
     
     config = CrawlerRunConfig(
-        link_extraction_config=LinkExtractionConfig(
+        link_preview_config=LinkPreviewConfig(
             include_internal=True,
             include_external=True,
             include_patterns=["*/docs/*", "*/tutorial/*", "*/guide/*"],
@@ -149,7 +149,7 @@ async def api_discovery_example():
     print("=" * 50)
     
     config = CrawlerRunConfig(
-        link_extraction_config=LinkExtractionConfig(
+        link_preview_config=LinkPreviewConfig(
             include_internal=True,
             include_patterns=["*/api/*", "*/reference/*", "*/endpoint/*"],
             exclude_patterns=["*/deprecated/*", "*/v1/*"],  # Skip old versions
@@ -214,7 +214,7 @@ async def link_quality_analysis():
     print("=" * 50)
     
     config = CrawlerRunConfig(
-        link_extraction_config=LinkExtractionConfig(
+        link_preview_config=LinkPreviewConfig(
             include_internal=True,
             max_links=30,  # Analyze more links for better statistics
             concurrency=15,
@@ -281,7 +281,7 @@ async def pattern_filtering_example():
     filters = [
         {
             "name": "Documentation Only",
-            "config": LinkExtractionConfig(
+            "config": LinkPreviewConfig(
                 include_internal=True,
                 max_links=10,
                 concurrency=5,
@@ -292,7 +292,7 @@ async def pattern_filtering_example():
         },
         {
             "name": "API References Only", 
-            "config": LinkExtractionConfig(
+            "config": LinkPreviewConfig(
                 include_internal=True,
                 max_links=10,
                 concurrency=5,
@@ -303,7 +303,7 @@ async def pattern_filtering_example():
         },
         {
             "name": "Exclude Admin Areas",
-            "config": LinkExtractionConfig(
+            "config": LinkPreviewConfig(
                 include_internal=True,
                 max_links=10,
                 concurrency=5,
@@ -318,7 +318,7 @@ async def pattern_filtering_example():
             print(f"\n🔍 Testing: {filter_example['name']}")
             
             config = CrawlerRunConfig(
-                link_extraction_config=filter_example['config'],
+                link_preview_config=filter_example['config'],
                 score_links=True
             )
             

docs/md_v2/core/link-media.md

@@ -125,7 +125,7 @@ Here's a full example you can copy, paste, and run immediately:
 ```python
 import asyncio
 from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
-from crawl4ai.async_configs import LinkExtractionConfig
+from crawl4ai.async_configs import LinkPreviewConfig
 
 async def extract_link_heads_example():
     """
@@ -136,7 +136,7 @@ async def extract_link_heads_example():
     # Configure link head extraction
     config = CrawlerRunConfig(
         # Enable link head extraction with detailed configuration
-        link_extraction_config=LinkExtractionConfig(
+        link_preview_config=LinkPreviewConfig(
             include_internal=True,           # Extract from internal links
             include_external=False,          # Skip external links for this example
             max_links=10,                   # Limit to 10 links for demo
@@ -234,12 +234,12 @@ if __name__ == "__main__":
 
 ### 2.3 Configuration Deep Dive
 
-The `LinkExtractionConfig` class supports these options:
+The `LinkPreviewConfig` class supports these options:
 
 ```python
-from crawl4ai.async_configs import LinkExtractionConfig
+from crawl4ai.async_configs import LinkPreviewConfig
 
-link_extraction_config = LinkExtractionConfig(
+link_preview_config = LinkPreviewConfig(
     # BASIC SETTINGS
     verbose=True,                    # Show detailed logs (recommended for learning)
     
@@ -316,7 +316,7 @@ Find the most relevant documentation pages:
 ```python
 async def research_assistant():
     config = CrawlerRunConfig(
-        link_extraction_config=LinkExtractionConfig(
+        link_preview_config=LinkPreviewConfig(
             include_internal=True,
             include_external=True,
             include_patterns=["*/docs/*", "*/tutorial/*", "*/guide/*"],
@@ -348,7 +348,7 @@ Find all API endpoints and references:
 ```python
 async def api_discovery():
     config = CrawlerRunConfig(
-        link_extraction_config=LinkExtractionConfig(
+        link_preview_config=LinkPreviewConfig(
             include_internal=True,
             include_patterns=["*/api/*", "*/reference/*"],
             exclude_patterns=["*/deprecated/*"],
@@ -387,7 +387,7 @@ Analyze website structure and content quality:
 ```python
 async def quality_analysis():
     config = CrawlerRunConfig(
-        link_extraction_config=LinkExtractionConfig(
+        link_preview_config=LinkPreviewConfig(
             include_internal=True,
             max_links=200,
             concurrency=20,
@@ -434,7 +434,7 @@ async def quality_analysis():
 ```python
 # Check your configuration:
 config = CrawlerRunConfig(
-    link_extraction_config=LinkExtractionConfig(
+    link_preview_config=LinkPreviewConfig(
         verbose=True   # ← Enable to see what's happening
     )
 )
@@ -445,7 +445,7 @@ config = CrawlerRunConfig(
 # Make sure scoring is enabled:
 config = CrawlerRunConfig(
     score_links=True,  # ← Enable intrinsic scoring
-    link_extraction_config=LinkExtractionConfig(
+    link_preview_config=LinkPreviewConfig(
         query="your search terms"  # ← For contextual scoring
     )
 )
@@ -454,7 +454,7 @@ config = CrawlerRunConfig(
 **Process taking too long?**
 ```python
 # Optimize performance:
-link_extraction_config = LinkExtractionConfig(
+link_preview_config = LinkPreviewConfig(
     max_links=20,      # ← Reduce number
     concurrency=10,    # ← Increase parallelism
     timeout=3,         # ← Shorter timeout