docs: Update release notes and docs for v0.7.0 with teh correct parameters and explanations

- Added Adaptive Crawling to Core section
- Added URL Seeding to Core section
- Added Adaptive Strategies to Advanced section

README.md

@@ -523,15 +523,18 @@ async def test_news_crawl():
 - **🧠 Adaptive Crawling**: Your crawler now learns and adapts to website patterns automatically:
   ```python
   config = AdaptiveConfig(
-      confidence_threshold=0.7,
+      confidence_threshold=0.7, # Min confidence to stop crawling
-      max_history=100,
+      max_depth=5, # Maximum crawl depth
-      learning_rate=0.2
+      max_pages=20, # Maximum number of pages to crawl
+      strategy="statistical"
   )
   
-  result = await crawler.arun(
+  async with AsyncWebCrawler() as crawler:
-      "https://news.example.com",
+      adaptive_crawler = AdaptiveCrawler(crawler, config)
-      config=CrawlerRunConfig(adaptive_config=config)
+      state = await adaptive_crawler.digest(
-  )
+          start_url="https://news.example.com",
+          query="latest news content"
+      )
   # Crawler learns patterns and improves extraction over time
   ```
 

docs/blog/release-v0.7.0.md

@@ -10,9 +10,8 @@ Today I'm releasing Crawl4AI v0.7.0—the Adaptive Intelligence Update. This rel
 
 - **Adaptive Crawling**: Your crawler now learns and adapts to website patterns
 - **Virtual Scroll Support**: Complete content extraction from infinite scroll pages
-- **Link Preview with 3-Layer Scoring**: Intelligent link analysis and prioritization
+- **Link Preview with Intelligent Scoring**: Intelligent link analysis and prioritization
 - **Async URL Seeder**: Discover thousands of URLs in seconds with intelligent filtering
-- **PDF Parsing**: Extract data from PDF documents
 - **Performance Optimizations**: Significant speed and memory improvements
 
 ## 🧠 Adaptive Crawling: Intelligence Through Pattern Learning
@@ -30,44 +29,34 @@ The Adaptive Crawler maintains a persistent state for each domain, tracking:
 - Extraction confidence scores
 
 ```python
-from crawl4ai import AdaptiveCrawler, AdaptiveConfig, CrawlState
+from crawl4ai import AsyncWebCrawler, AdaptiveCrawler, AdaptiveConfig
 
-# Initialize with custom learning parameters
+# Initialize with custom adaptive parameters
 config = AdaptiveConfig(
-    confidence_threshold=0.7,    # Min confidence to use learned patterns
+    confidence_threshold=0.7,    # Min confidence to stop crawling
-    max_history=100,            # Remember last 100 crawls per domain
+    max_depth=5,                # Maximum crawl depth
-    learning_rate=0.2,          # How quickly to adapt to changes
+    max_pages=20,               # Maximum number of pages to crawl
-    patterns_per_page=3,        # Patterns to learn per page type
+    top_k_links=3,              # Number of top links to follow per page
-    extraction_strategy='css'   # 'css' or 'xpath'
+    strategy="statistical",     # 'statistical' or 'embedding'
+    coverage_weight=0.4,        # Weight for coverage in confidence calculation
+    consistency_weight=0.3,     # Weight for consistency in confidence calculation
+    saturation_weight=0.3       # Weight for saturation in confidence calculation
 )
 
-adaptive_crawler = AdaptiveCrawler(config)
+# Initialize adaptive crawler with web crawler
-
-# First crawl - crawler learns the structure
 async with AsyncWebCrawler() as crawler:
-    result = await crawler.arun(
+    adaptive_crawler = AdaptiveCrawler(crawler, config)
-        "https://news.example.com/article/12345",
+    
-        config=CrawlerRunConfig(
+    # Crawl and learn patterns
-            adaptive_config=config,
+    state = await adaptive_crawler.digest(
-            extraction_hints={  # Optional hints to speed up learning
+        start_url="https://news.example.com/article/12345",
-                "title": "article h1",
+        query="latest news articles and content"
-                "content": "article .body-content"
-            }
-        )
     )
     
-    # Crawler identifies and stores patterns
+    # Access results and confidence
-    if result.success:
+    print(f"Confidence Level: {adaptive_crawler.confidence:.0%}")
-        state = adaptive_crawler.get_state("news.example.com")
+    print(f"Pages Crawled: {len(state.crawled_urls)}")
-        print(f"Learned {len(state.patterns)} patterns")
+    print(f"Knowledge Base: {len(adaptive_crawler.state.knowledge_base)} documents")
-        print(f"Confidence: {state.avg_confidence:.2%}")
-
-# Subsequent crawls - uses learned patterns
-result2 = await crawler.arun(
-    "https://news.example.com/article/67890",
-    config=CrawlerRunConfig(adaptive_config=config)
-)
-# Automatically extracts using learned patterns!
 ```
 
 **Expected Real-World Impact:**
@@ -92,9 +81,7 @@ twitter_config = VirtualScrollConfig(
     container_selector="[data-testid='primaryColumn']",
     scroll_count=20,                    # Number of scrolls
     scroll_by="container_height",       # Smart scrolling by container size
-    wait_after_scroll=1.0,             # Let content load
+    wait_after_scroll=1.0              # Let content load
-    capture_method="incremental",       # Capture new content on each scroll
-    deduplicate=True                   # Remove duplicate elements
 )
 
 # For e-commerce product grids (Instagram style)
@@ -102,8 +89,7 @@ grid_config = VirtualScrollConfig(
     container_selector="main .product-grid",
     scroll_count=30,
     scroll_by=800,                     # Fixed pixel scrolling
-    wait_after_scroll=1.5,             # Images need time
+    wait_after_scroll=1.5              # Images need time
-    stop_on_no_change=True            # Smart stopping
 )
 
 # For news feeds with lazy loading
@@ -111,9 +97,7 @@ news_config = VirtualScrollConfig(
     container_selector=".article-feed",
     scroll_count=50,
     scroll_by="page_height",           # Viewport-based scrolling
-    wait_after_scroll=0.5,
+    wait_after_scroll=0.5              # Wait for content to load
-    wait_for_selector=".article-card",  # Wait for specific elements
-    timeout=30000                      # Max 30 seconds total
 )
 
 # Use it in your crawl
@@ -160,29 +144,17 @@ async with AsyncWebCrawler() as crawler:
 ### The Three-Layer Scoring System
 
 ```python
-from crawl4ai import LinkPreviewConfig
+from crawl4ai import LinkPreviewConfig, CrawlerRunConfig, CacheMode
 
 # Configure intelligent link analysis
 link_config = LinkPreviewConfig(
-    # What to analyze
     include_internal=True,
-    include_external=True,
+    include_external=False,
-    max_links=100,              # Analyze top 100 links
+    max_links=10,
-    
+    concurrency=5,
-    # Relevance scoring
+    query="python tutorial",  # For contextual scoring
-    query="machine learning tutorials",  # Your interest
+    score_threshold=0.3,
-    score_threshold=0.3,        # Minimum relevance score
+    verbose=True
-    
-    # Performance
-    concurrent_requests=10,     # Parallel processing
-    timeout_per_link=5000,      # 5s per link
-    
-    # Advanced scoring weights
-    scoring_weights={
-        "intrinsic": 0.3,       # Link quality indicators
-        "contextual": 0.5,      # Relevance to query
-        "popularity": 0.2       # Link prominence
-    }
 )
 
 # Use in your crawl
@@ -190,35 +162,51 @@ result = await crawler.arun(
     "https://tech-blog.example.com",
     config=CrawlerRunConfig(
         link_preview_config=link_config,
-        score_links=True
+        score_links=True,  # Enable intrinsic scoring
+        cache_mode=CacheMode.BYPASS
     )
 )
 
 # Access scored and sorted links
-for link in result.links["internal"][:10]:  # Top 10 internal links
+if result.success and result.links:
-    print(f"Score: {link['total_score']:.3f}")
+# Get scored links
-    print(f"  Intrinsic: {link['intrinsic_score']:.1f}/10")  # Position, attributes
+internal_links = result.links.get("internal", [])
-    print(f"  Contextual: {link['contextual_score']:.1f}/1")  # Relevance to query
+scored_links = [l for l in internal_links if l.get("total_score")]
-    print(f"  URL: {link['href']}")
+scored_links.sort(key=lambda x: x.get("total_score", 0), reverse=True)
-    print(f"  Title: {link['head_data']['title']}")
+
-    print(f"  Description: {link['head_data']['meta']['description'][:100]}...")
+# Create a scoring table
+table = Table(title="Link Scoring Results", box=box.ROUNDED)
+table.add_column("Link Text", style="cyan", width=40)
+table.add_column("Intrinsic Score", justify="center")
+table.add_column("Contextual Score", justify="center")
+table.add_column("Total Score", justify="center", style="bold green")
+
+for link in scored_links[:5]:
+    text = link.get('text', 'No text')[:40]
+    table.add_row(
+        text,
+        f"{link.get('intrinsic_score', 0):.1f}/10",
+        f"{link.get('contextual_score', 0):.2f}/1",
+        f"{link.get('total_score', 0):.3f}"
+    )
+
+console.print(table)
 ```
 
 **Scoring Components:**
 
-1. **Intrinsic Score (0-10)**: Based on link quality indicators
+1. **Intrinsic Score**: Based on link quality indicators
    - Position on page (navigation, content, footer)
    - Link attributes (rel, title, class names)
    - Anchor text quality and length
    - URL structure and depth
 
-2. **Contextual Score (0-1)**: Relevance to your query
+2. **Contextual Score**: Relevance to your query using BM25 algorithm
-   - Semantic similarity using embeddings
    - Keyword matching in link text and title
    - Meta description analysis
    - Content preview scoring
 
-3. **Total Score**: Weighted combination for final ranking
+3. **Total Score**: Combined score for final ranking
 
 **Expected Real-World Impact:**
 - **Research Efficiency**: Find relevant papers 10x faster by following only high-score links
@@ -240,53 +228,53 @@ from crawl4ai import AsyncUrlSeeder, SeedingConfig
 # Basic discovery - find all product pages
 seeder_config = SeedingConfig(
     # Discovery sources
-    source="sitemap+cc",        # Sitemap + Common Crawl
+    source="cc+sitemap",        # Sitemap + Common Crawl
     
     # Filtering
     pattern="*/product/*",      # URL pattern matching
-    ignore_patterns=["*/reviews/*", "*/questions/*"],
     
     # Validation
     live_check=True,           # Verify URLs are alive
-    max_urls=5000,             # Stop at 5000 URLs
+    max_urls=50,             # Stop at 50 URLs
     
     # Performance  
-    concurrency=100,           # Parallel requests
+    concurrency=100,           # Maximum concurrent requests for live checks/head extraction
-    hits_per_sec=10           # Rate limiting
+    hits_per_sec=10           # Rate limit in requests per second to avoid overwhelming servers
 )
 
-seeder = AsyncUrlSeeder(seeder_config)
+async with AsyncUrlSeeder() as seeder:
-urls = await seeder.discover("https://shop.example.com")
+    console.print("Discovering URLs from Python docs...")
+    urls = await seeder.urls("docs.python.org", seeding_config)
+    console.print(f"\n✓ Discovered {len(urls)} URLs")
 
 # Advanced: Relevance-based discovery
 research_config = SeedingConfig(
-    source="crawl+sitemap",    # Deep crawl + sitemap
+    source="sitemap+cc",       # Sitemap + Common Crawl
     pattern="*/blog/*",        # Blog posts only
     
     # Content relevance
     extract_head=True,         # Get meta tags
     query="quantum computing tutorials",
-    scoring_method="bm25",     # Or "semantic" (coming soon)
+    scoring_method="bm25",     # BM25 scoring method
     score_threshold=0.4,       # High relevance only
     
     # Smart filtering
     filter_nonsense_urls=True,  # Remove .xml, .txt, etc.
-    min_content_length=500,     # Skip thin content
     
     force=True                 # Bypass cache
 )
 
 # Discover with progress tracking
 discovered = []
-async for batch in seeder.discover_iter("https://physics-blog.com", research_config):
+async with AsyncUrlSeeder() as seeder:
-    discovered.extend(batch)
+    discovered = await seeder.urls("https://physics-blog.com", research_config)
-    print(f"Found {len(discovered)} relevant URLs so far...")
+    console.print(f"\n✓ Discovered {len(discovered)} URLs")
 
 # Results include scores and metadata
 for url_data in discovered[:5]:
     print(f"URL: {url_data['url']}")
-    print(f"Score: {url_data['score']:.3f}")
+    print(f"Score: {url_data['relevance_score']:.3f}")
-    print(f"Title: {url_data['title']}")
+    print(f"Title: {url_data['head_data']['title']}")
 ```
 
 **Discovery Methods:**
@@ -309,35 +297,18 @@ This release includes significant performance improvements through optimized res
 ### What We Optimized
 
 ```python
-# Before v0.7.0 (slow)
+# Optimized crawling with v0.7.0 improvements
 results = []
 for url in urls:
-    result = await crawler.arun(url)
+    result = await crawler.arun(
-    results.append(result)
+        url,
-
+        config=CrawlerRunConfig(
-# After v0.7.0 (fast)
+            # Performance optimizations
-# Automatic batching and connection pooling
+            wait_until="domcontentloaded",  # Faster than networkidle
-results = await crawler.arun_batch(
+            cache_mode=CacheMode.ENABLED    # Enable caching
-    urls,
+        )
-    config=CrawlerRunConfig(
-        # New performance options
-        batch_size=10,              # Process 10 URLs concurrently
-        reuse_browser=True,         # Keep browser warm
-        eager_loading=False,        # Load only what's needed
-        streaming_extraction=True,  # Stream large extractions
-        
-        # Optimized defaults
-        wait_until="domcontentloaded",  # Faster than networkidle
-        exclude_external_resources=True, # Skip third-party assets
-        block_ads=True                  # Ad blocking built-in
     )
-)
+    results.append(result)
-
-# Memory-efficient streaming for large crawls
-async for result in crawler.arun_stream(large_url_list):
-    # Process results as they complete
-    await process_result(result)
-    # Memory is freed after each iteration
 ```
 
 **Performance Gains:**
@@ -347,24 +318,6 @@ async for result in crawler.arun_stream(large_url_list):
 - **Memory Usage**: 60% reduction with streaming processing
 - **Concurrent Crawls**: Handle 5x more parallel requests
 
-## 📄 PDF Support
-
-PDF extraction is now natively supported in Crawl4AI.
-
-```python
-# Extract data from PDF documents
-result = await crawler.arun(
-    "https://example.com/report.pdf",
-    config=CrawlerRunConfig(
-        pdf_extraction=True,
-        extraction_strategy=JsonCssExtractionStrategy({
-            # Works on converted PDF structure
-            "title": {"selector": "h1", "type": "text"},
-            "sections": {"selector": "h2", "type": "list"}
-        })
-    )
-)
-```
 
 ## 🔧 Important Changes
 

docs/md_v2/advanced/session-management.md

@@ -49,46 +49,75 @@ from crawl4ai import JsonCssExtractionStrategy
 from crawl4ai.cache_context import CacheMode
 
 async def crawl_dynamic_content():
-    async with AsyncWebCrawler() as crawler:
+    url = "https://github.com/microsoft/TypeScript/commits/main"
-        session_id = "github_commits_session"
+    session_id = "wait_for_session"
-        url = "https://github.com/microsoft/TypeScript/commits/main"
+    all_commits = []
-        all_commits = []
 
-        # Define extraction schema
+    js_next_page = """
-        schema = {
+    const commits = document.querySelectorAll('li[data-testid="commit-row-item"] h4');
-            "name": "Commit Extractor",
+    if (commits.length > 0) {
-            "baseSelector": "li.Box-sc-g0xbh4-0",
+        window.lastCommit = commits[0].textContent.trim();
-            "fields": [{
+    }
-                "name": "title", "selector": "h4.markdown-title", "type": "text"
+    const button = document.querySelector('a[data-testid="pagination-next-button"]');
-            }],
+    if (button) {button.click(); console.log('button clicked') }
-        }
+    """
-        extraction_strategy = JsonCssExtractionStrategy(schema)
 
-        # JavaScript and wait configurations
+    wait_for = """() => {
-        js_next_page = """document.querySelector('a[data-testid="pagination-next-button"]').click();"""
+        const commits = document.querySelectorAll('li[data-testid="commit-row-item"] h4');
-        wait_for = """() => document.querySelectorAll('li.Box-sc-g0xbh4-0').length > 0"""
+        if (commits.length === 0) return false;
-
+        const firstCommit = commits[0].textContent.trim();
-        # Crawl multiple pages
+        return firstCommit !== window.lastCommit;
+    }"""
+    
+    schema = {
+        "name": "Commit Extractor",
+        "baseSelector": "li[data-testid='commit-row-item']",
+        "fields": [
+            {
+                "name": "title",
+                "selector": "h4 a",
+                "type": "text",
+                "transform": "strip",
+            },
+        ],
+    }
+    extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)
+    
+    
+    browser_config = BrowserConfig(
+        verbose=True,
+        headless=False,
+    )
+        
+    async with AsyncWebCrawler(config=browser_config) as crawler:
         for page in range(3):
-            config = CrawlerRunConfig(
+            crawler_config = CrawlerRunConfig(
-                url=url,
                 session_id=session_id,
+                css_selector="li[data-testid='commit-row-item']",
                 extraction_strategy=extraction_strategy,
                 js_code=js_next_page if page > 0 else None,
                 wait_for=wait_for if page > 0 else None,
                 js_only=page > 0,
-                cache_mode=CacheMode.BYPASS
+                cache_mode=CacheMode.BYPASS,
+                capture_console_messages=True,
             )
-
+            
-            result = await crawler.arun(config=config)
+            result = await crawler.arun(url=url, config=crawler_config)
-            if result.success:
+            
+            if result.console_messages:
+                print(f"Page {page + 1} console messages:", result.console_messages)
+            
+            if result.extracted_content:
+                # print(f"Page {page + 1} result:", result.extracted_content)
                 commits = json.loads(result.extracted_content)
                 all_commits.extend(commits)
                 print(f"Page {page + 1}: Found {len(commits)} commits")
+            else:
+                print(f"Page {page + 1}: No content extracted")
 
+        print(f"Successfully crawled {len(all_commits)} commits across 3 pages")
         # Clean up session
         await crawler.crawler_strategy.kill_session(session_id)
-        return all_commits
 ```
 
 ---

docs/md_v2/advanced/virtual-scroll.md

@@ -91,13 +91,12 @@ async def crawl_twitter_timeline():
         wait_after_scroll=1.0  # Twitter needs time to load
     )
     
+    browser_config = BrowserConfig(headless=True)  # Set to False to watch it work
     config = CrawlerRunConfig(
-        virtual_scroll_config=virtual_config,
+        virtual_scroll_config=virtual_config
-        # Optional: Set headless=False to watch it work
-        # browser_config=BrowserConfig(headless=False)
     )
     
-    async with AsyncWebCrawler() as crawler:
+    async with AsyncWebCrawler(config=browser_config) as crawler:
         result = await crawler.arun(
             url="https://twitter.com/search?q=AI",
             config=config
@@ -200,7 +199,7 @@ Use **scan_full_page** when:
 Virtual Scroll works seamlessly with extraction strategies:
 
 ```python
-from crawl4ai import LLMExtractionStrategy
+from crawl4ai import LLMExtractionStrategy, LLMConfig
 
 # Define extraction schema
 schema = {
@@ -222,7 +221,7 @@ config = CrawlerRunConfig(
         scroll_count=20
     ),
     extraction_strategy=LLMExtractionStrategy(
-        provider="openai/gpt-4o-mini",
+        llm_config=LLMConfig(provider="openai/gpt-4o-mini"),
         schema=schema
     )
 )

docs/md_v2/blog/releases/0.7.0.md

@@ -10,9 +10,8 @@ Today I'm releasing Crawl4AI v0.7.0—the Adaptive Intelligence Update. This rel
 
 - **Adaptive Crawling**: Your crawler now learns and adapts to website patterns
 - **Virtual Scroll Support**: Complete content extraction from infinite scroll pages
-- **Link Preview with 3-Layer Scoring**: Intelligent link analysis and prioritization
+- **Link Preview with Intelligent Scoring**: Intelligent link analysis and prioritization
 - **Async URL Seeder**: Discover thousands of URLs in seconds with intelligent filtering
-- **PDF Parsing**: Extract data from PDF documents
 - **Performance Optimizations**: Significant speed and memory improvements
 
 ## 🧠 Adaptive Crawling: Intelligence Through Pattern Learning
@@ -30,44 +29,34 @@ The Adaptive Crawler maintains a persistent state for each domain, tracking:
 - Extraction confidence scores
 
 ```python
-from crawl4ai import AdaptiveCrawler, AdaptiveConfig, CrawlState
+from crawl4ai import AsyncWebCrawler, AdaptiveCrawler, AdaptiveConfig
 
-# Initialize with custom learning parameters
+# Initialize with custom adaptive parameters
 config = AdaptiveConfig(
-    confidence_threshold=0.7,    # Min confidence to use learned patterns
+    confidence_threshold=0.7,    # Min confidence to stop crawling
-    max_history=100,            # Remember last 100 crawls per domain
+    max_depth=5,                # Maximum crawl depth
-    learning_rate=0.2,          # How quickly to adapt to changes
+    max_pages=20,               # Maximum number of pages to crawl
-    patterns_per_page=3,        # Patterns to learn per page type
+    top_k_links=3,              # Number of top links to follow per page
-    extraction_strategy='css'   # 'css' or 'xpath'
+    strategy="statistical",     # 'statistical' or 'embedding'
+    coverage_weight=0.4,        # Weight for coverage in confidence calculation
+    consistency_weight=0.3,     # Weight for consistency in confidence calculation
+    saturation_weight=0.3       # Weight for saturation in confidence calculation
 )
 
-adaptive_crawler = AdaptiveCrawler(config)
+# Initialize adaptive crawler with web crawler
-
-# First crawl - crawler learns the structure
 async with AsyncWebCrawler() as crawler:
-    result = await crawler.arun(
+    adaptive_crawler = AdaptiveCrawler(crawler, config)
-        "https://news.example.com/article/12345",
+    
-        config=CrawlerRunConfig(
+    # Crawl and learn patterns
-            adaptive_config=config,
+    state = await adaptive_crawler.digest(
-            extraction_hints={  # Optional hints to speed up learning
+        start_url="https://news.example.com/article/12345",
-                "title": "article h1",
+        query="latest news articles and content"
-                "content": "article .body-content"
-            }
-        )
     )
     
-    # Crawler identifies and stores patterns
+    # Access results and confidence
-    if result.success:
+    print(f"Confidence Level: {adaptive_crawler.confidence:.0%}")
-        state = adaptive_crawler.get_state("news.example.com")
+    print(f"Pages Crawled: {len(state.crawled_urls)}")
-        print(f"Learned {len(state.patterns)} patterns")
+    print(f"Knowledge Base: {len(adaptive_crawler.state.knowledge_base)} documents")
-        print(f"Confidence: {state.avg_confidence:.2%}")
-
-# Subsequent crawls - uses learned patterns
-result2 = await crawler.arun(
-    "https://news.example.com/article/67890",
-    config=CrawlerRunConfig(adaptive_config=config)
-)
-# Automatically extracts using learned patterns!
 ```
 
 **Expected Real-World Impact:**
@@ -92,9 +81,7 @@ twitter_config = VirtualScrollConfig(
     container_selector="[data-testid='primaryColumn']",
     scroll_count=20,                    # Number of scrolls
     scroll_by="container_height",       # Smart scrolling by container size
-    wait_after_scroll=1.0,             # Let content load
+    wait_after_scroll=1.0              # Let content load
-    capture_method="incremental",       # Capture new content on each scroll
-    deduplicate=True                   # Remove duplicate elements
 )
 
 # For e-commerce product grids (Instagram style)
@@ -102,8 +89,7 @@ grid_config = VirtualScrollConfig(
     container_selector="main .product-grid",
     scroll_count=30,
     scroll_by=800,                     # Fixed pixel scrolling
-    wait_after_scroll=1.5,             # Images need time
+    wait_after_scroll=1.5              # Images need time
-    stop_on_no_change=True            # Smart stopping
 )
 
 # For news feeds with lazy loading
@@ -111,9 +97,7 @@ news_config = VirtualScrollConfig(
     container_selector=".article-feed",
     scroll_count=50,
     scroll_by="page_height",           # Viewport-based scrolling
-    wait_after_scroll=0.5,
+    wait_after_scroll=0.5              # Wait for content to load
-    wait_for_selector=".article-card",  # Wait for specific elements
-    timeout=30000                      # Max 30 seconds total
 )
 
 # Use it in your crawl
@@ -160,29 +144,17 @@ async with AsyncWebCrawler() as crawler:
 ### The Three-Layer Scoring System
 
 ```python
-from crawl4ai import LinkPreviewConfig
+from crawl4ai import LinkPreviewConfig, CrawlerRunConfig, CacheMode
 
 # Configure intelligent link analysis
 link_config = LinkPreviewConfig(
-    # What to analyze
     include_internal=True,
-    include_external=True,
+    include_external=False,
-    max_links=100,              # Analyze top 100 links
+    max_links=10,
-    
+    concurrency=5,
-    # Relevance scoring
+    query="python tutorial",  # For contextual scoring
-    query="machine learning tutorials",  # Your interest
+    score_threshold=0.3,
-    score_threshold=0.3,        # Minimum relevance score
+    verbose=True
-    
-    # Performance
-    concurrent_requests=10,     # Parallel processing
-    timeout_per_link=5000,      # 5s per link
-    
-    # Advanced scoring weights
-    scoring_weights={
-        "intrinsic": 0.3,       # Link quality indicators
-        "contextual": 0.5,      # Relevance to query
-        "popularity": 0.2       # Link prominence
-    }
 )
 
 # Use in your crawl
@@ -190,35 +162,51 @@ result = await crawler.arun(
     "https://tech-blog.example.com",
     config=CrawlerRunConfig(
         link_preview_config=link_config,
-        score_links=True
+        score_links=True,  # Enable intrinsic scoring
+        cache_mode=CacheMode.BYPASS
     )
 )
 
 # Access scored and sorted links
-for link in result.links["internal"][:10]:  # Top 10 internal links
+if result.success and result.links:
-    print(f"Score: {link['total_score']:.3f}")
+# Get scored links
-    print(f"  Intrinsic: {link['intrinsic_score']:.1f}/10")  # Position, attributes
+internal_links = result.links.get("internal", [])
-    print(f"  Contextual: {link['contextual_score']:.1f}/1")  # Relevance to query
+scored_links = [l for l in internal_links if l.get("total_score")]
-    print(f"  URL: {link['href']}")
+scored_links.sort(key=lambda x: x.get("total_score", 0), reverse=True)
-    print(f"  Title: {link['head_data']['title']}")
+
-    print(f"  Description: {link['head_data']['meta']['description'][:100]}...")
+# Create a scoring table
+table = Table(title="Link Scoring Results", box=box.ROUNDED)
+table.add_column("Link Text", style="cyan", width=40)
+table.add_column("Intrinsic Score", justify="center")
+table.add_column("Contextual Score", justify="center")
+table.add_column("Total Score", justify="center", style="bold green")
+
+for link in scored_links[:5]:
+    text = link.get('text', 'No text')[:40]
+    table.add_row(
+        text,
+        f"{link.get('intrinsic_score', 0):.1f}/10",
+        f"{link.get('contextual_score', 0):.2f}/1",
+        f"{link.get('total_score', 0):.3f}"
+    )
+
+console.print(table)
 ```
 
 **Scoring Components:**
 
-1. **Intrinsic Score (0-10)**: Based on link quality indicators
+1. **Intrinsic Score**: Based on link quality indicators
    - Position on page (navigation, content, footer)
    - Link attributes (rel, title, class names)
    - Anchor text quality and length
    - URL structure and depth
 
-2. **Contextual Score (0-1)**: Relevance to your query
+2. **Contextual Score**: Relevance to your query using BM25 algorithm
-   - Semantic similarity using embeddings
    - Keyword matching in link text and title
    - Meta description analysis
    - Content preview scoring
 
-3. **Total Score**: Weighted combination for final ranking
+3. **Total Score**: Combined score for final ranking
 
 **Expected Real-World Impact:**
 - **Research Efficiency**: Find relevant papers 10x faster by following only high-score links
@@ -240,53 +228,53 @@ from crawl4ai import AsyncUrlSeeder, SeedingConfig
 # Basic discovery - find all product pages
 seeder_config = SeedingConfig(
     # Discovery sources
-    source="sitemap+cc",        # Sitemap + Common Crawl
+    source="cc+sitemap",        # Sitemap + Common Crawl
     
     # Filtering
     pattern="*/product/*",      # URL pattern matching
-    ignore_patterns=["*/reviews/*", "*/questions/*"],
     
     # Validation
     live_check=True,           # Verify URLs are alive
-    max_urls=5000,             # Stop at 5000 URLs
+    max_urls=50,             # Stop at 50 URLs
     
     # Performance  
-    concurrency=100,           # Parallel requests
+    concurrency=100,           # Maximum concurrent requests for live checks/head extraction
-    hits_per_sec=10           # Rate limiting
+    hits_per_sec=10           # Rate limit in requests per second to avoid overwhelming servers
 )
 
-seeder = AsyncUrlSeeder(seeder_config)
+async with AsyncUrlSeeder() as seeder:
-urls = await seeder.discover("https://shop.example.com")
+    console.print("Discovering URLs from Python docs...")
+    urls = await seeder.urls("docs.python.org", seeding_config)
+    console.print(f"\n✓ Discovered {len(urls)} URLs")
 
 # Advanced: Relevance-based discovery
 research_config = SeedingConfig(
-    source="crawl+sitemap",    # Deep crawl + sitemap
+    source="sitemap+cc",       # Sitemap + Common Crawl
     pattern="*/blog/*",        # Blog posts only
     
     # Content relevance
     extract_head=True,         # Get meta tags
     query="quantum computing tutorials",
-    scoring_method="bm25",     # Or "semantic" (coming soon)
+    scoring_method="bm25",     # BM25 scoring method
     score_threshold=0.4,       # High relevance only
     
     # Smart filtering
     filter_nonsense_urls=True,  # Remove .xml, .txt, etc.
-    min_content_length=500,     # Skip thin content
     
     force=True                 # Bypass cache
 )
 
 # Discover with progress tracking
 discovered = []
-async for batch in seeder.discover_iter("https://physics-blog.com", research_config):
+async with AsyncUrlSeeder() as seeder:
-    discovered.extend(batch)
+    discovered = await seeder.urls("https://physics-blog.com", research_config)
-    print(f"Found {len(discovered)} relevant URLs so far...")
+    console.print(f"\n✓ Discovered {len(discovered)} URLs")
 
 # Results include scores and metadata
 for url_data in discovered[:5]:
     print(f"URL: {url_data['url']}")
-    print(f"Score: {url_data['score']:.3f}")
+    print(f"Score: {url_data['relevance_score']:.3f}")
-    print(f"Title: {url_data['title']}")
+    print(f"Title: {url_data['head_data']['title']}")
 ```
 
 **Discovery Methods:**
@@ -309,35 +297,18 @@ This release includes significant performance improvements through optimized res
 ### What We Optimized
 
 ```python
-# Before v0.7.0 (slow)
+# Optimized crawling with v0.7.0 improvements
 results = []
 for url in urls:
-    result = await crawler.arun(url)
+    result = await crawler.arun(
-    results.append(result)
+        url,
-
+        config=CrawlerRunConfig(
-# After v0.7.0 (fast)
+            # Performance optimizations
-# Automatic batching and connection pooling
+            wait_until="domcontentloaded",  # Faster than networkidle
-results = await crawler.arun_batch(
+            cache_mode=CacheMode.ENABLED    # Enable caching
-    urls,
+        )
-    config=CrawlerRunConfig(
-        # New performance options
-        batch_size=10,              # Process 10 URLs concurrently
-        reuse_browser=True,         # Keep browser warm
-        eager_loading=False,        # Load only what's needed
-        streaming_extraction=True,  # Stream large extractions
-        
-        # Optimized defaults
-        wait_until="domcontentloaded",  # Faster than networkidle
-        exclude_external_resources=True, # Skip third-party assets
-        block_ads=True                  # Ad blocking built-in
     )
-)
+    results.append(result)
-
-# Memory-efficient streaming for large crawls
-async for result in crawler.arun_stream(large_url_list):
-    # Process results as they complete
-    await process_result(result)
-    # Memory is freed after each iteration
 ```
 
 **Performance Gains:**
@@ -347,24 +318,6 @@ async for result in crawler.arun_stream(large_url_list):
 - **Memory Usage**: 60% reduction with streaming processing
 - **Concurrent Crawls**: Handle 5x more parallel requests
 
-## 📄 PDF Support
-
-PDF extraction is now natively supported in Crawl4AI.
-
-```python
-# Extract data from PDF documents
-result = await crawler.arun(
-    "https://example.com/report.pdf",
-    config=CrawlerRunConfig(
-        pdf_extraction=True,
-        extraction_strategy=JsonCssExtractionStrategy({
-            # Works on converted PDF structure
-            "title": {"selector": "h1", "type": "text"},
-            "sections": {"selector": "h2", "type": "list"}
-        })
-    )
-)
-```
 
 ## 🔧 Important Changes
 

docs/md_v2/core/adaptive-crawling.md

@@ -35,7 +35,7 @@ from crawl4ai import AsyncWebCrawler, AdaptiveCrawler
 
 async def main():
     async with AsyncWebCrawler() as crawler:
-        # Create an adaptive crawler
+        # Create an adaptive crawler (config is optional)
         adaptive = AdaptiveCrawler(crawler)
         
         # Start crawling with a query
@@ -59,13 +59,13 @@ async def main():
 from crawl4ai import AdaptiveConfig
 
 config = AdaptiveConfig(
-    confidence_threshold=0.7,    # Stop when 70% confident (default: 0.8)
+    confidence_threshold=0.8,    # Stop when 80% confident (default: 0.7)
-    max_pages=20,               # Maximum pages to crawl (default: 50)
+    max_pages=30,               # Maximum pages to crawl (default: 20)
-    top_k_links=3,              # Links to follow per page (default: 5)
+    top_k_links=5,              # Links to follow per page (default: 3)
     min_gain_threshold=0.05     # Minimum expected gain to continue (default: 0.1)
 )
 
-adaptive = AdaptiveCrawler(crawler, config=config)
+adaptive = AdaptiveCrawler(crawler, config)
 ```
 
 ## Crawling Strategies
@@ -198,8 +198,8 @@ if result.metrics.get('is_irrelevant', False):
 The confidence score (0-1) indicates how sufficient the gathered information is:
 - **0.0-0.3**: Insufficient information, needs more crawling
 - **0.3-0.6**: Partial information, may answer basic queries
-- **0.6-0.8**: Good coverage, can answer most queries
+- **0.6-0.7**: Good coverage, can answer most queries
-- **0.8-1.0**: Excellent coverage, comprehensive information
+- **0.7-1.0**: Excellent coverage, comprehensive information
 
 ### Statistics Display
 
@@ -257,9 +257,9 @@ new_adaptive.import_knowledge_base("knowledge_base.jsonl")
 - Avoid overly broad queries
 
 ### 2. Threshold Tuning
-- Start with default (0.8) for general use
+- Start with default (0.7) for general use
-- Lower to 0.6-0.7 for exploratory crawling
+- Lower to 0.5-0.6 for exploratory crawling
-- Raise to 0.9+ for exhaustive coverage
+- Raise to 0.8+ for exhaustive coverage
 
 ### 3. Performance Optimization
 - Use appropriate `max_pages` limits

docs/md_v2/core/url-seeding.md

@@ -137,7 +137,7 @@ async def smart_blog_crawler():
             word_count_threshold=300  # Only substantial articles
         )
         
-        # Extract URLs and stream results as they come
+        # Extract URLs and crawl them
         tutorial_urls = [t["url"] for t in tutorials[:10]]
         results = await crawler.arun_many(tutorial_urls, config=config)
         
@@ -231,7 +231,7 @@ Common Crawl is a massive public dataset that regularly crawls the entire web. I
 
 ```python
 # Use both sources
-config = SeedingConfig(source="cc+sitemap")
+config = SeedingConfig(source="sitemap+cc")
 urls = await seeder.urls("example.com", config)
 ```
 
@@ -241,13 +241,13 @@ The `SeedingConfig` object is your control panel. Here's everything you can conf
 
 | Parameter | Type | Default | Description |
 |-----------|------|---------|-------------|
-| `source` | str | "cc" | URL source: "cc" (Common Crawl), "sitemap", or "cc+sitemap" |
+| `source` | str | "sitemap+cc" | URL source: "cc" (Common Crawl), "sitemap", or "sitemap+cc" |
 | `pattern` | str | "*" | URL pattern filter (e.g., "*/blog/*", "*.html") |
 | `extract_head` | bool | False | Extract metadata from page `<head>` |
 | `live_check` | bool | False | Verify URLs are accessible |
 | `max_urls` | int | -1 | Maximum URLs to return (-1 = unlimited) |
 | `concurrency` | int | 10 | Parallel workers for fetching |
-| `hits_per_sec` | int | None | Rate limit for requests |
+| `hits_per_sec` | int | 5 | Rate limit for requests |
 | `force` | bool | False | Bypass cache, fetch fresh data |
 | `verbose` | bool | False | Show detailed progress |
 | `query` | str | None | Search query for BM25 scoring |
@@ -522,7 +522,7 @@ urls = await seeder.urls("docs.example.com", config)
 ```python
 # Find specific products
 config = SeedingConfig(
-    source="cc+sitemap",  # Use both sources
+    source="sitemap+cc",  # Use both sources
     extract_head=True,
     query="wireless headphones noise canceling",
     scoring_method="bm25",
@@ -782,7 +782,7 @@ class ResearchAssistant:
         
         # Step 1: Discover relevant URLs
         config = SeedingConfig(
-            source="cc+sitemap",     # Maximum coverage
+            source="sitemap+cc",     # Maximum coverage
             extract_head=True,       # Get metadata
             query=topic,             # Research topic
             scoring_method="bm25",   # Smart scoring
@@ -832,7 +832,8 @@ class ResearchAssistant:
             # Extract URLs and crawl all articles
             article_urls = [article['url'] for article in top_articles]
             results = []
-            async for result in await crawler.arun_many(article_urls, config=config):
+            crawl_results = await crawler.arun_many(article_urls, config=config)
+            async for result in crawl_results:
                 if result.success:
                     results.append({
                         'url': result.url,
@@ -933,10 +934,10 @@ config = SeedingConfig(concurrency=10, hits_per_sec=5)
 # When crawling many URLs
 async with AsyncWebCrawler() as crawler:
     # Assuming urls is a list of URL strings
-    results = await crawler.arun_many(urls, config=config)
+    crawl_results = await crawler.arun_many(urls, config=config)
     
     # Process as they arrive
-    async for result in results:
+    async for result in crawl_results:
         process_immediately(result)  # Don't wait for all
 ```
 
@@ -1020,7 +1021,7 @@ config = SeedingConfig(
 
 # E-commerce product discovery
 config = SeedingConfig(
-    source="cc+sitemap",
+    source="sitemap+cc",
     pattern="*/product/*",
     extract_head=True,
     live_check=True

mkdocs.yml

@@ -25,6 +25,8 @@ nav:
     - "Command Line Interface": "core/cli.md"
     - "Simple Crawling": "core/simple-crawling.md"
     - "Deep Crawling": "core/deep-crawling.md"
+    - "Adaptive Crawling": "core/adaptive-crawling.md"
+    - "URL Seeding": "core/url-seeding.md"
     - "C4A-Script": "core/c4a-script.md"
     - "Crawler Result": "core/crawler-result.md"
     - "Browser, Crawler & LLM Config": "core/browser-crawler-config.md"
@@ -37,6 +39,7 @@ nav:
     - "Link & Media": "core/link-media.md"
   - Advanced:
     - "Overview": "advanced/advanced-features.md"
+    - "Adaptive Strategies": "advanced/adaptive-strategies.md"
     - "Virtual Scroll": "advanced/virtual-scroll.md"
     - "File Downloading": "advanced/file-downloading.md"
     - "Lazy Loading": "advanced/lazy-loading.md"