Merge branch 'release/v0.7.1'

- Remove unused StealthConfig from browser_manager.py
- Update LinkPreviewConfig import path in __init__.py and examples
- Fix infinity handling in content_scraping_strategy.py (use 0 instead of float('inf'))
- Remove sanitize_json_data functions from API endpoints
- Add comprehensive C4A Script documentation to release notes
- Update v0.7.0 release notes with improved code examples
- Create v0.7.1 release notes focusing on cleanup and documentation improvements
- Update demo files with corrected import paths and examples
- Fix virtual scroll and adaptive crawling examples across documentation

🤖 Generated with Claude Code

Co-Authored-By: Claude <noreply@anthropic.com>

crawl4ai/__init__.py

@@ -3,7 +3,7 @@ import warnings
 
 from .async_webcrawler import AsyncWebCrawler, CacheMode
 # MODIFIED: Add SeedingConfig and VirtualScrollConfig here
-from .async_configs import BrowserConfig, CrawlerRunConfig, HTTPCrawlerConfig, LLMConfig, ProxyConfig, GeolocationConfig, SeedingConfig, VirtualScrollConfig
+from .async_configs import BrowserConfig, CrawlerRunConfig, HTTPCrawlerConfig, LLMConfig, ProxyConfig, GeolocationConfig, SeedingConfig, VirtualScrollConfig, LinkPreviewConfig
 
 from .content_scraping_strategy import (
     ContentScrapingStrategy,
@@ -173,6 +173,7 @@ __all__ = [
     "CompilationResult",
     "ValidationResult",
     "ErrorDetail",
+    "LinkPreviewConfig"
 ]
 
 

crawl4ai/__version__.py

@@ -1,7 +1,7 @@
 # crawl4ai/__version__.py
 
 # This is the version that will be used for stable releases
-__version__ = "0.7.0"
+__version__ = "0.7.1"
 
 # For nightly builds, this gets set during build process
 __nightly_version__ = None

crawl4ai/browser_manager.py

@@ -14,23 +14,8 @@ import hashlib
 from .js_snippet import load_js_script
 from .config import DOWNLOAD_PAGE_TIMEOUT
 from .async_configs import BrowserConfig, CrawlerRunConfig
-from playwright_stealth import StealthConfig
 from .utils import get_chromium_path
 
-stealth_config = StealthConfig(
-    webdriver=True,
-    chrome_app=True,
-    chrome_csi=True,
-    chrome_load_times=True,
-    chrome_runtime=True,
-    navigator_languages=True,
-    navigator_plugins=True,
-    navigator_permissions=True,
-    webgl_vendor=True,
-    outerdimensions=True,
-    navigator_hardware_concurrency=True,
-    media_codecs=True,
-)
 
 BROWSER_DISABLE_OPTIONS = [
     "--disable-background-networking",

crawl4ai/content_scraping_strategy.py

@@ -1145,10 +1145,10 @@ class LXMLWebScrapingStrategy(WebScrapingStrategy):
                         link_data["intrinsic_score"] = intrinsic_score
                     except Exception:
                         # Fail gracefully - assign default score
-                        link_data["intrinsic_score"] = float('inf')
+                        link_data["intrinsic_score"] = 0
                 else:
                     # No scoring enabled - assign infinity (all links equal priority)
-                    link_data["intrinsic_score"] = float('inf')
+                    link_data["intrinsic_score"] = 0
 
                 is_external = is_external_url(normalized_href, base_domain)
                 if is_external:

docs/blog/release-v0.7.0.md

@@ -30,33 +30,40 @@ The Adaptive Crawler maintains a persistent state for each domain, tracking:
 
 ```python
 from crawl4ai import AsyncWebCrawler, AdaptiveCrawler, AdaptiveConfig
+import asyncio
 
-# Initialize with custom adaptive parameters
+async def main():
-config = AdaptiveConfig(
-    confidence_threshold=0.7,    # Min confidence to stop crawling
-    max_depth=5,                # Maximum crawl depth
-    max_pages=20,               # Maximum number of pages to crawl
-    top_k_links=3,              # Number of top links to follow per page
-    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
-)
-
-# Initialize adaptive crawler with web crawler
-async with AsyncWebCrawler() as crawler:
-    adaptive_crawler = AdaptiveCrawler(crawler, config)
     
-    # Crawl and learn patterns
+    # Configure adaptive crawler
-    state = await adaptive_crawler.digest(
+    config = AdaptiveConfig(
-        start_url="https://news.example.com/article/12345",
+        strategy="statistical",  # or "embedding" for semantic understanding
-        query="latest news articles and content"
+        max_pages=10,
+        confidence_threshold=0.7,  # Stop at 70% confidence
+        top_k_links=3,  # Follow top 3 links per page
+        min_gain_threshold=0.05  # Need 5% information gain to continue
     )
     
-    # Access results and confidence
+    async with AsyncWebCrawler(verbose=False) as crawler:
-    print(f"Confidence Level: {adaptive_crawler.confidence:.0%}")
+        adaptive = AdaptiveCrawler(crawler, config)
-    print(f"Pages Crawled: {len(state.crawled_urls)}")
+        
-    print(f"Knowledge Base: {len(adaptive_crawler.state.knowledge_base)} documents")
+        print("Starting adaptive crawl about Python decorators...")
+        result = await adaptive.digest(
+            start_url="https://docs.python.org/3/glossary.html",
+            query="python decorators functions wrapping"
+        )
+        
+        print(f"\n✅ Crawling Complete!")
+        print(f"• Confidence Level: {adaptive.confidence:.0%}")
+        print(f"• Pages Crawled: {len(result.crawled_urls)}")
+        print(f"• Knowledge Base: {len(adaptive.state.knowledge_base)} documents")
+        
+        # Get most relevant content
+        relevant = adaptive.get_relevant_content(top_k=3)
+        print(f"\nMost Relevant Pages:")
+        for i, page in enumerate(relevant, 1):
+            print(f"{i}. {page['url']} (relevance: {page['score']:.2%})")
+
+asyncio.run(main())
 ```
 
 **Expected Real-World Impact:**
@@ -141,56 +148,47 @@ async with AsyncWebCrawler() as crawler:
 
 **My Solution:** I implemented a three-layer scoring system that analyzes links like a human would—considering their position, context, and relevance to your goals.
 
-### The Three-Layer Scoring System
+### Intelligent Link Analysis and Scoring
 
 ```python
-from crawl4ai import LinkPreviewConfig, CrawlerRunConfig, CacheMode
+import asyncio
+from crawl4ai import CrawlerRunConfig, CacheMode, AsyncWebCrawler
+from crawl4ai.adaptive_crawler import LinkPreviewConfig
 
-# Configure intelligent link analysis
+async def main():
-link_config = LinkPreviewConfig(
+    # Configure intelligent link analysis
-    include_internal=True,
+    link_config = LinkPreviewConfig(
-    include_external=False,
+        include_internal=True,
-    max_links=10,
+        include_external=False,
-    concurrency=5,
+        max_links=10,
-    query="python tutorial",  # For contextual scoring
+        concurrency=5,
-    score_threshold=0.3,
+        query="python tutorial",  # For contextual scoring
-    verbose=True
+        score_threshold=0.3,
-)
+        verbose=True
-
-# Use in your crawl
-result = await crawler.arun(
-    "https://tech-blog.example.com",
-    config=CrawlerRunConfig(
-        link_preview_config=link_config,
-        score_links=True,  # Enable intrinsic scoring
-        cache_mode=CacheMode.BYPASS
     )
-)
+    # Use in your crawl
+    async with AsyncWebCrawler() as crawler:
+        result = await crawler.arun(
+            "https://www.geeksforgeeks.org/",
+            config=CrawlerRunConfig(
+                link_preview_config=link_config,
+                score_links=True,  # Enable intrinsic scoring
+                cache_mode=CacheMode.BYPASS
+            )
+        )
 
-# Access scored and sorted links
+        # Access scored and sorted links
-if result.success and result.links:
+        if result.success and result.links:
-# Get scored links
+            for link in result.links.get("internal", []):
-internal_links = result.links.get("internal", [])
+                text = link.get('text', 'No text')[:40]
-scored_links = [l for l in internal_links if l.get("total_score")]
+                print(
-scored_links.sort(key=lambda x: x.get("total_score", 0), reverse=True)
+                    text,
+                    f"{link.get('intrinsic_score', 0):.1f}/10" if link.get('intrinsic_score') is not None else "0.0/10",
+                    f"{link.get('contextual_score', 0):.2f}/1" if link.get('contextual_score') is not None else "0.00/1",
+                    f"{link.get('total_score', 0):.3f}" if link.get('total_score') is not None else "0.000"
+                )
 
-# Create a scoring table
+asyncio.run(main())
-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:**
@@ -223,58 +221,34 @@ console.print(table)
 ### Technical Architecture
 
 ```python
+import asyncio
 from crawl4ai import AsyncUrlSeeder, SeedingConfig
 
-# Basic discovery - find all product pages
+async def main():
-seeder_config = SeedingConfig(
+    async with AsyncUrlSeeder() as seeder:
-    # Discovery sources
+        # Discover Python tutorial URLs
-    source="cc+sitemap",        # Sitemap + Common Crawl
+        config = SeedingConfig(
-    
+            source="sitemap",  # Use sitemap
-    # Filtering
+            pattern="*python*",  # URL pattern filter
-    pattern="*/product/*",      # URL pattern matching
+            extract_head=True,  # Get metadata
-    
+            query="python tutorial",  # For relevance scoring
-    # Validation
+            scoring_method="bm25",
-    live_check=True,           # Verify URLs are alive
+            score_threshold=0.2,
-    max_urls=50,             # Stop at 50 URLs
+            max_urls=10
-    
+        )
-    # Performance  
+        
-    concurrency=100,           # Maximum concurrent requests for live checks/head extraction
+        print("Discovering Python async tutorial URLs...")
-    hits_per_sec=10           # Rate limit in requests per second to avoid overwhelming servers
+        urls = await seeder.urls("https://www.geeksforgeeks.org/", config)
-)
+        
+        print(f"\n✅ Found {len(urls)} relevant URLs:")
+        for i, url_info in enumerate(urls[:5], 1):
+            print(f"\n{i}. {url_info['url']}")
+            if url_info.get('relevance_score'):
+                print(f"   Relevance: {url_info['relevance_score']:.3f}")
+            if url_info.get('head_data', {}).get('title'):
+                print(f"   Title: {url_info['head_data']['title'][:60]}...")
 
-async with AsyncUrlSeeder() as seeder:
+asyncio.run(main())
-    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="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",     # BM25 scoring method
-    score_threshold=0.4,       # High relevance only
-    
-    # Smart filtering
-    filter_nonsense_urls=True,  # Remove .xml, .txt, etc.
-    
-    force=True                 # Bypass cache
-)
-
-# Discover with progress tracking
-discovered = []
-async with AsyncUrlSeeder() as seeder:
-    discovered = await seeder.urls("https://physics-blog.com", research_config)
-    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['relevance_score']:.3f}")
-    print(f"Title: {url_data['head_data']['title']}")
 ```
 
 **Discovery Methods:**

docs/blog/release-v0.7.1.md

@@ -0,0 +1,43 @@
+# 🛠️ Crawl4AI v0.7.1: Minor Cleanup Update
+
+*July 17, 2025 • 2 min read*
+
+---
+
+A small maintenance release that removes unused code and improves documentation.
+
+## 🎯 What's Changed
+
+- **Removed unused StealthConfig** from `crawl4ai/browser_manager.py`
+- **Updated documentation** with better examples and parameter explanations
+- **Fixed virtual scroll configuration** examples in docs
+
+## 🧹 Code Cleanup
+
+Removed unused `StealthConfig` import and configuration that wasn't being used anywhere in the codebase. The project uses its own custom stealth implementation through JavaScript injection instead.
+
+```python
+# Removed unused code:
+from playwright_stealth import StealthConfig
+stealth_config = StealthConfig(...)  # This was never used
+```
+
+## 📖 Documentation Updates
+
+- Fixed adaptive crawling parameter examples
+- Updated session management documentation
+- Corrected virtual scroll configuration examples
+
+## 🚀 Installation
+
+```bash
+pip install crawl4ai==0.7.1
+```
+
+No breaking changes - upgrade directly from v0.7.0.
+
+---
+
+Questions? Issues? 
+- GitHub: [github.com/unclecode/crawl4ai](https://github.com/unclecode/crawl4ai)
+- Discord: [discord.gg/crawl4ai](https://discord.gg/jP8KfhDhyN)

docs/examples/link_head_extraction_example.py

@@ -18,7 +18,7 @@ Usage:
 
 import asyncio
 from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
-from crawl4ai.async_configs import LinkPreviewConfig
+from crawl4ai import LinkPreviewConfig
 
 
 async def basic_link_head_extraction():

docs/md_v2/blog/releases/0.7.0.md

@@ -30,33 +30,40 @@ The Adaptive Crawler maintains a persistent state for each domain, tracking:
 
 ```python
 from crawl4ai import AsyncWebCrawler, AdaptiveCrawler, AdaptiveConfig
+import asyncio
 
-# Initialize with custom adaptive parameters
+async def main():
-config = AdaptiveConfig(
-    confidence_threshold=0.7,    # Min confidence to stop crawling
-    max_depth=5,                # Maximum crawl depth
-    max_pages=20,               # Maximum number of pages to crawl
-    top_k_links=3,              # Number of top links to follow per page
-    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
-)
-
-# Initialize adaptive crawler with web crawler
-async with AsyncWebCrawler() as crawler:
-    adaptive_crawler = AdaptiveCrawler(crawler, config)
     
-    # Crawl and learn patterns
+    # Configure adaptive crawler
-    state = await adaptive_crawler.digest(
+    config = AdaptiveConfig(
-        start_url="https://news.example.com/article/12345",
+        strategy="statistical",  # or "embedding" for semantic understanding
-        query="latest news articles and content"
+        max_pages=10,
+        confidence_threshold=0.7,  # Stop at 70% confidence
+        top_k_links=3,  # Follow top 3 links per page
+        min_gain_threshold=0.05  # Need 5% information gain to continue
     )
     
-    # Access results and confidence
+    async with AsyncWebCrawler(verbose=False) as crawler:
-    print(f"Confidence Level: {adaptive_crawler.confidence:.0%}")
+        adaptive = AdaptiveCrawler(crawler, config)
-    print(f"Pages Crawled: {len(state.crawled_urls)}")
+        
-    print(f"Knowledge Base: {len(adaptive_crawler.state.knowledge_base)} documents")
+        print("Starting adaptive crawl about Python decorators...")
+        result = await adaptive.digest(
+            start_url="https://docs.python.org/3/glossary.html",
+            query="python decorators functions wrapping"
+        )
+        
+        print(f"\n✅ Crawling Complete!")
+        print(f"• Confidence Level: {adaptive.confidence:.0%}")
+        print(f"• Pages Crawled: {len(result.crawled_urls)}")
+        print(f"• Knowledge Base: {len(adaptive.state.knowledge_base)} documents")
+        
+        # Get most relevant content
+        relevant = adaptive.get_relevant_content(top_k=3)
+        print(f"\nMost Relevant Pages:")
+        for i, page in enumerate(relevant, 1):
+            print(f"{i}. {page['url']} (relevance: {page['score']:.2%})")
+
+asyncio.run(main())
 ```
 
 **Expected Real-World Impact:**
@@ -141,56 +148,47 @@ async with AsyncWebCrawler() as crawler:
 
 **My Solution:** I implemented a three-layer scoring system that analyzes links like a human would—considering their position, context, and relevance to your goals.
 
-### The Three-Layer Scoring System
+### Intelligent Link Analysis and Scoring
 
 ```python
-from crawl4ai import LinkPreviewConfig, CrawlerRunConfig, CacheMode
+import asyncio
+from crawl4ai import CrawlerRunConfig, CacheMode, AsyncWebCrawler
+from crawl4ai.adaptive_crawler import LinkPreviewConfig
 
-# Configure intelligent link analysis
+async def main():
-link_config = LinkPreviewConfig(
+    # Configure intelligent link analysis
-    include_internal=True,
+    link_config = LinkPreviewConfig(
-    include_external=False,
+        include_internal=True,
-    max_links=10,
+        include_external=False,
-    concurrency=5,
+        max_links=10,
-    query="python tutorial",  # For contextual scoring
+        concurrency=5,
-    score_threshold=0.3,
+        query="python tutorial",  # For contextual scoring
-    verbose=True
+        score_threshold=0.3,
-)
+        verbose=True
-
-# Use in your crawl
-result = await crawler.arun(
-    "https://tech-blog.example.com",
-    config=CrawlerRunConfig(
-        link_preview_config=link_config,
-        score_links=True,  # Enable intrinsic scoring
-        cache_mode=CacheMode.BYPASS
     )
-)
+    # Use in your crawl
+    async with AsyncWebCrawler() as crawler:
+        result = await crawler.arun(
+            "https://www.geeksforgeeks.org/",
+            config=CrawlerRunConfig(
+                link_preview_config=link_config,
+                score_links=True,  # Enable intrinsic scoring
+                cache_mode=CacheMode.BYPASS
+            )
+        )
 
-# Access scored and sorted links
+        # Access scored and sorted links
-if result.success and result.links:
+        if result.success and result.links:
-# Get scored links
+            for link in result.links.get("internal", []):
-internal_links = result.links.get("internal", [])
+                text = link.get('text', 'No text')[:40]
-scored_links = [l for l in internal_links if l.get("total_score")]
+                print(
-scored_links.sort(key=lambda x: x.get("total_score", 0), reverse=True)
+                    text,
+                    f"{link.get('intrinsic_score', 0):.1f}/10" if link.get('intrinsic_score') is not None else "0.0/10",
+                    f"{link.get('contextual_score', 0):.2f}/1" if link.get('contextual_score') is not None else "0.00/1",
+                    f"{link.get('total_score', 0):.3f}" if link.get('total_score') is not None else "0.000"
+                )
 
-# Create a scoring table
+asyncio.run(main())
-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:**
@@ -223,58 +221,34 @@ console.print(table)
 ### Technical Architecture
 
 ```python
+import asyncio
 from crawl4ai import AsyncUrlSeeder, SeedingConfig
 
-# Basic discovery - find all product pages
+async def main():
-seeder_config = SeedingConfig(
+    async with AsyncUrlSeeder() as seeder:
-    # Discovery sources
+        # Discover Python tutorial URLs
-    source="cc+sitemap",        # Sitemap + Common Crawl
+        config = SeedingConfig(
-    
+            source="sitemap",  # Use sitemap
-    # Filtering
+            pattern="*python*",  # URL pattern filter
-    pattern="*/product/*",      # URL pattern matching
+            extract_head=True,  # Get metadata
-    
+            query="python tutorial",  # For relevance scoring
-    # Validation
+            scoring_method="bm25",
-    live_check=True,           # Verify URLs are alive
+            score_threshold=0.2,
-    max_urls=50,             # Stop at 50 URLs
+            max_urls=10
-    
+        )
-    # Performance  
+        
-    concurrency=100,           # Maximum concurrent requests for live checks/head extraction
+        print("Discovering Python async tutorial URLs...")
-    hits_per_sec=10           # Rate limit in requests per second to avoid overwhelming servers
+        urls = await seeder.urls("https://www.geeksforgeeks.org/", config)
-)
+        
+        print(f"\n✅ Found {len(urls)} relevant URLs:")
+        for i, url_info in enumerate(urls[:5], 1):
+            print(f"\n{i}. {url_info['url']}")
+            if url_info.get('relevance_score'):
+                print(f"   Relevance: {url_info['relevance_score']:.3f}")
+            if url_info.get('head_data', {}).get('title'):
+                print(f"   Title: {url_info['head_data']['title'][:60]}...")
 
-async with AsyncUrlSeeder() as seeder:
+asyncio.run(main())
-    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="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",     # BM25 scoring method
-    score_threshold=0.4,       # High relevance only
-    
-    # Smart filtering
-    filter_nonsense_urls=True,  # Remove .xml, .txt, etc.
-    
-    force=True                 # Bypass cache
-)
-
-# Discover with progress tracking
-discovered = []
-async with AsyncUrlSeeder() as seeder:
-    discovered = await seeder.urls("https://physics-blog.com", research_config)
-    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['relevance_score']:.3f}")
-    print(f"Title: {url_data['head_data']['title']}")
 ```
 
 **Discovery Methods:**

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 LinkPreviewConfig
+from crawl4ai import LinkPreviewConfig
 
 async def extract_link_heads_example():
     """
@@ -237,7 +237,7 @@ if __name__ == "__main__":
 The `LinkPreviewConfig` class supports these options:
 
 ```python
-from crawl4ai.async_configs import LinkPreviewConfig
+from crawl4ai import LinkPreviewConfig
 
 link_preview_config = LinkPreviewConfig(
     # BASIC SETTINGS

docs/releases_review/crawl4ai_v0_7_0_showcase.py

@@ -28,7 +28,7 @@ from rich import box
 
 from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, AdaptiveCrawler, AdaptiveConfig, BrowserConfig, CacheMode
 from crawl4ai import AsyncUrlSeeder, SeedingConfig
-from crawl4ai.async_configs import LinkPreviewConfig, VirtualScrollConfig
+from crawl4ai import LinkPreviewConfig, VirtualScrollConfig
 from crawl4ai import c4a_compile, CompilationResult
 
 # Initialize Rich console for beautiful output

docs/releases_review/v0_7_0_features_demo.py

@@ -13,14 +13,13 @@ from crawl4ai import (
     BrowserConfig,
     CacheMode,
     # New imports for v0.7.0
-    LinkPreviewConfig,
     VirtualScrollConfig,
+    LinkPreviewConfig,
     AdaptiveCrawler,
     AdaptiveConfig,
     AsyncUrlSeeder,
     SeedingConfig,
     c4a_compile,
-    CompilationResult
 )
 
 
@@ -170,16 +169,16 @@ async def demo_url_seeder():
         # Discover Python tutorial URLs
         config = SeedingConfig(
             source="sitemap",  # Use sitemap
-            pattern="*tutorial*",  # URL pattern filter
+            pattern="*python*",  # URL pattern filter
             extract_head=True,  # Get metadata
-            query="python async programming",  # For relevance scoring
+            query="python tutorial",  # For relevance scoring
             scoring_method="bm25",
             score_threshold=0.2,
             max_urls=10
         )
         
         print("Discovering Python async tutorial URLs...")
-        urls = await seeder.urls("docs.python.org", config)
+        urls = await seeder.urls("https://www.geeksforgeeks.org/", config)
         
         print(f"\n✅ Found {len(urls)} relevant URLs:")
         for i, url_info in enumerate(urls[:5], 1):
@@ -245,39 +244,6 @@ IF (EXISTS `.price-filter`) THEN CLICK `input[data-max-price="100"]`
         print(f"❌ Compilation error: {result.first_error.message}")
 
 
-async def demo_pdf_support():
-    """
-    Demo 6: PDF Parsing Support
-    
-    Shows how to extract content from PDF files.
-    Note: Requires 'pip install crawl4ai[pdf]'
-    """
-    print("\n" + "="*60)
-    print("📄 DEMO 6: PDF Parsing Support")
-    print("="*60)
-    
-    try:
-        # Check if PDF support is installed
-        import PyPDF2
-        
-        # Example: Process a PDF URL
-        config = CrawlerRunConfig(
-            cache_mode=CacheMode.BYPASS,
-            pdf=True,  # Enable PDF generation
-            extract_text_from_pdf=True  # Extract text content
-        )
-        
-        print("PDF parsing is available!")
-        print("You can now crawl PDF URLs and extract their content.")
-        print("\nExample usage:")
-        print('  result = await crawler.arun("https://example.com/document.pdf")')
-        print('  pdf_text = result.extracted_content  # Contains extracted text')
-        
-    except ImportError:
-        print("⚠️  PDF support not installed.")
-        print("Install with: pip install crawl4ai[pdf]")
-
-
 async def main():
     """Run all demos"""
     print("\n🚀 Crawl4AI v0.7.0 Feature Demonstrations")
@@ -289,7 +255,6 @@ async def main():
         ("Virtual Scroll", demo_virtual_scroll),
         ("URL Seeder", demo_url_seeder),
         ("C4A Script", demo_c4a_script),
-        ("PDF Support", demo_pdf_support)
     ]
     
     for name, demo_func in demos:
@@ -309,7 +274,6 @@ async def main():
     print("• Virtual Scroll: Capture all content from modern web pages")
     print("• URL Seeder: Pre-discover and filter URLs efficiently")
     print("• C4A Script: Simple language for complex automations")
-    print("• PDF Support: Extract content from PDF documents")
 
 
 if __name__ == "__main__":

tests/docker/simple_api_test.py

@@ -0,0 +1,345 @@
+#!/usr/bin/env python3
+"""
+Simple API Test for Crawl4AI Docker Server v0.7.0
+Uses only built-in Python modules to test all endpoints.
+"""
+
+import urllib.request
+import urllib.parse
+import json
+import time
+import sys
+from typing import Dict, List, Optional
+
+# Configuration
+BASE_URL = "http://localhost:11234"  # Change to your server URL
+TEST_TIMEOUT = 30
+
+class SimpleApiTester:
+    def __init__(self, base_url: str = BASE_URL):
+        self.base_url = base_url
+        self.token = None
+        self.results = []
+        
+    def log(self, message: str):
+        print(f"[INFO] {message}")
+    
+    def test_get_endpoint(self, endpoint: str) -> Dict:
+        """Test a GET endpoint"""
+        url = f"{self.base_url}{endpoint}"
+        start_time = time.time()
+        
+        try:
+            req = urllib.request.Request(url)
+            if self.token:
+                req.add_header('Authorization', f'Bearer {self.token}')
+            
+            with urllib.request.urlopen(req, timeout=TEST_TIMEOUT) as response:
+                response_time = time.time() - start_time
+                status_code = response.getcode()
+                content = response.read().decode('utf-8')
+                
+                # Try to parse JSON
+                try:
+                    data = json.loads(content)
+                except:
+                    data = {"raw_response": content[:200]}
+                
+                return {
+                    "endpoint": endpoint,
+                    "method": "GET",
+                    "status": "PASS" if status_code < 400 else "FAIL",
+                    "status_code": status_code,
+                    "response_time": response_time,
+                    "data": data
+                }
+        except Exception as e:
+            response_time = time.time() - start_time
+            return {
+                "endpoint": endpoint,
+                "method": "GET",
+                "status": "FAIL",
+                "status_code": None,
+                "response_time": response_time,
+                "error": str(e)
+            }
+    
+    def test_post_endpoint(self, endpoint: str, payload: Dict) -> Dict:
+        """Test a POST endpoint"""
+        url = f"{self.base_url}{endpoint}"
+        start_time = time.time()
+        
+        try:
+            data = json.dumps(payload).encode('utf-8')
+            req = urllib.request.Request(url, data=data, method='POST')
+            req.add_header('Content-Type', 'application/json')
+            
+            if self.token:
+                req.add_header('Authorization', f'Bearer {self.token}')
+            
+            with urllib.request.urlopen(req, timeout=TEST_TIMEOUT) as response:
+                response_time = time.time() - start_time
+                status_code = response.getcode()
+                content = response.read().decode('utf-8')
+                
+                # Try to parse JSON
+                try:
+                    data = json.loads(content)
+                except:
+                    data = {"raw_response": content[:200]}
+                
+                return {
+                    "endpoint": endpoint,
+                    "method": "POST",
+                    "status": "PASS" if status_code < 400 else "FAIL",
+                    "status_code": status_code,
+                    "response_time": response_time,
+                    "data": data
+                }
+        except Exception as e:
+            response_time = time.time() - start_time
+            return {
+                "endpoint": endpoint,
+                "method": "POST",
+                "status": "FAIL",
+                "status_code": None,
+                "response_time": response_time,
+                "error": str(e)
+            }
+    
+    def print_result(self, result: Dict):
+        """Print a formatted test result"""
+        status_color = {
+            "PASS": "✅",
+            "FAIL": "❌",
+            "SKIP": "⏭️"
+        }
+        
+        print(f"{status_color[result['status']]} {result['method']} {result['endpoint']} "
+              f"| {result['response_time']:.3f}s | Status: {result['status_code'] or 'N/A'}")
+        
+        if result['status'] == 'FAIL' and 'error' in result:
+            print(f"    Error: {result['error']}")
+        
+        self.results.append(result)
+    
+    def run_all_tests(self):
+        """Run all API tests"""
+        print("🚀 Starting Crawl4AI v0.7.0 API Test Suite")
+        print(f"📡 Testing server at: {self.base_url}")
+        print("=" * 60)
+        
+        # # Test basic endpoints
+        # print("\n=== BASIC ENDPOINTS ===")
+        
+        # # Health check
+        # result = self.test_get_endpoint("/health")
+        # self.print_result(result)
+        
+        
+        # # Schema endpoint
+        # result = self.test_get_endpoint("/schema")
+        # self.print_result(result)
+        
+        # # Metrics endpoint
+        # result = self.test_get_endpoint("/metrics")
+        # self.print_result(result)
+        
+        # # Root redirect
+        # result = self.test_get_endpoint("/")
+        # self.print_result(result)
+        
+        # # Test authentication
+        # print("\n=== AUTHENTICATION ===")
+        
+        # # Get token
+        # token_payload = {"email": "test@example.com"}
+        # result = self.test_post_endpoint("/token", token_payload)
+        # self.print_result(result)
+        
+        # # Extract token if successful
+        # if result['status'] == 'PASS' and 'data' in result:
+        #     token = result['data'].get('access_token')
+        #     if token:
+        #         self.token = token
+        #         self.log(f"Successfully obtained auth token: {token[:20]}...")
+        
+        # Test core APIs
+        print("\n=== CORE APIs ===")
+        
+        test_url = "https://example.com"
+        
+        # Test markdown endpoint
+        md_payload = {
+            "url": test_url,
+            "f": "fit",
+            "q": "test query",
+            "c": "0"
+        }
+        result = self.test_post_endpoint("/md", md_payload)
+        # print(result['data'].get('markdown', ''))
+        self.print_result(result)
+        
+        # Test HTML endpoint
+        html_payload = {"url": test_url}
+        result = self.test_post_endpoint("/html", html_payload)
+        self.print_result(result)
+        
+        # Test screenshot endpoint
+        screenshot_payload = {
+            "url": test_url,
+            "screenshot_wait_for": 2
+        }
+        result = self.test_post_endpoint("/screenshot", screenshot_payload)
+        self.print_result(result)
+        
+        # Test PDF endpoint
+        pdf_payload = {"url": test_url}
+        result = self.test_post_endpoint("/pdf", pdf_payload)
+        self.print_result(result)
+        
+        # Test JavaScript execution
+        js_payload = {
+            "url": test_url,
+            "scripts": ["(() => document.title)()"]
+        }
+        result = self.test_post_endpoint("/execute_js", js_payload)
+        self.print_result(result)
+        
+        # Test crawl endpoint
+        crawl_payload = {
+            "urls": [test_url],
+            "browser_config": {},
+            "crawler_config": {}
+        }
+        result = self.test_post_endpoint("/crawl", crawl_payload)
+        self.print_result(result)
+        
+        # Test config dump
+        config_payload = {"code": "CrawlerRunConfig()"}
+        result = self.test_post_endpoint("/config/dump", config_payload)
+        self.print_result(result)
+        
+        # Test LLM endpoint
+        llm_endpoint = f"/llm/{test_url}?q=Extract%20main%20content"
+        result = self.test_get_endpoint(llm_endpoint)
+        self.print_result(result)
+        
+        # Test ask endpoint
+        ask_endpoint = "/ask?context_type=all&query=crawl4ai&max_results=5"
+        result = self.test_get_endpoint(ask_endpoint)
+        print(result)
+        self.print_result(result)
+        
+        # Test job APIs
+        print("\n=== JOB APIs ===")
+        
+        # Test LLM job
+        llm_job_payload = {
+            "url": test_url,
+            "q": "Extract main content",
+            "cache": False
+        }
+        result = self.test_post_endpoint("/llm/job", llm_job_payload)
+        self.print_result(result)
+        
+        # Test crawl job
+        crawl_job_payload = {
+            "urls": [test_url],
+            "browser_config": {},
+            "crawler_config": {}
+        }
+        result = self.test_post_endpoint("/crawl/job", crawl_job_payload)
+        self.print_result(result)
+        
+        # Test MCP
+        print("\n=== MCP APIs ===")
+        
+        # Test MCP schema
+        result = self.test_get_endpoint("/mcp/schema")
+        self.print_result(result)
+        
+        # Test error handling
+        print("\n=== ERROR HANDLING ===")
+        
+        # Test invalid URL
+        invalid_payload = {"url": "invalid-url", "f": "fit"}
+        result = self.test_post_endpoint("/md", invalid_payload)
+        self.print_result(result)
+        
+        # Test invalid endpoint
+        result = self.test_get_endpoint("/nonexistent")
+        self.print_result(result)
+        
+        # Print summary
+        self.print_summary()
+    
+    def print_summary(self):
+        """Print test results summary"""
+        print("\n" + "=" * 60)
+        print("📊 TEST RESULTS SUMMARY")
+        print("=" * 60)
+        
+        total = len(self.results)
+        passed = sum(1 for r in self.results if r['status'] == 'PASS')
+        failed = sum(1 for r in self.results if r['status'] == 'FAIL')
+        
+        print(f"Total Tests: {total}")
+        print(f"✅ Passed: {passed}")
+        print(f"❌ Failed: {failed}")
+        print(f"📈 Success Rate: {(passed/total)*100:.1f}%")
+        
+        if failed > 0:
+            print("\n❌ FAILED TESTS:")
+            for result in self.results:
+                if result['status'] == 'FAIL':
+                    print(f"  • {result['method']} {result['endpoint']}")
+                    if 'error' in result:
+                        print(f"    Error: {result['error']}")
+        
+        # Performance statistics
+        response_times = [r['response_time'] for r in self.results if r['response_time'] > 0]
+        if response_times:
+            avg_time = sum(response_times) / len(response_times)
+            max_time = max(response_times)
+            print(f"\n⏱️  Average Response Time: {avg_time:.3f}s")
+            print(f"⏱️  Max Response Time: {max_time:.3f}s")
+        
+        # Save detailed report
+        report_file = f"crawl4ai_test_report_{int(time.time())}.json"
+        with open(report_file, 'w') as f:
+            json.dump({
+                "timestamp": time.time(),
+                "server_url": self.base_url,
+                "version": "0.7.0",
+                "summary": {
+                    "total": total,
+                    "passed": passed,
+                    "failed": failed
+                },
+                "results": self.results
+            }, f, indent=2)
+        
+        print(f"\n📄 Detailed report saved to: {report_file}")
+
+def main():
+    """Main test runner"""
+    import argparse
+    
+    parser = argparse.ArgumentParser(description='Crawl4AI v0.7.0 API Test Suite')
+    parser.add_argument('--url', default=BASE_URL, help='Base URL of the server')
+    
+    args = parser.parse_args()
+    
+    tester = SimpleApiTester(args.url)
+    
+    try:
+        tester.run_all_tests()
+    except KeyboardInterrupt:
+        print("\n🛑 Test suite interrupted by user")
+    except Exception as e:
+        print(f"\n💥 Test suite failed with error: {e}")
+        sys.exit(1)
+
+if __name__ == "__main__":
+    main()

tests/test_link_extractor.py

@@ -5,7 +5,7 @@ Test script for Link Extractor functionality
 
 from crawl4ai.models import Link
 from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
-from crawl4ai.async_configs import LinkPreviewConfig
+from crawl4ai import LinkPreviewConfig
 import asyncio
 import sys
 import os
@@ -237,7 +237,7 @@ def test_config_examples():
             print(f"     {key}: {value}")
 
         print("   Usage:")
-        print("     from crawl4ai.async_configs import LinkPreviewConfig")
+        print("     from crawl4ai import LinkPreviewConfig")
         print("     config = CrawlerRunConfig(")
         print("         link_preview_config=LinkPreviewConfig(")
         for key, value in config_dict.items():