chore: Clean up test artifacts and disable test workflow

- Moved sentence-transformers from core to optional dependencies in pyproject.toml
- Removed sentence-transformers from requirements.txt
- Added proper ImportError handling with helpful installation message
- This prevents ~2.5GB of NVIDIA CUDA libraries from being installed by default
- Users who need embedding features can install with: pip install 'crawl4ai[transformer]'

.github/workflows/release.yml

@@ -0,0 +1,141 @@
+name: Release Pipeline
+on:
+  push:
+    tags:
+      - 'v*'
+      - '!test-v*'  # Exclude test tags
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      
+      - name: Extract version from tag
+        id: get_version
+        run: |
+          TAG_VERSION=${GITHUB_REF#refs/tags/v}
+          echo "VERSION=$TAG_VERSION" >> $GITHUB_OUTPUT
+          echo "Releasing version: $TAG_VERSION"
+      
+      - name: Install package dependencies
+        run: |
+          pip install -e .
+      
+      - name: Check version consistency
+        run: |
+          TAG_VERSION=${{ steps.get_version.outputs.VERSION }}
+          PACKAGE_VERSION=$(python -c "from crawl4ai.__version__ import __version__; print(__version__)")
+          
+          echo "Tag version: $TAG_VERSION"
+          echo "Package version: $PACKAGE_VERSION"
+          
+          if [ "$TAG_VERSION" != "$PACKAGE_VERSION" ]; then
+            echo "❌ Version mismatch! Tag: $TAG_VERSION, Package: $PACKAGE_VERSION"
+            echo "Please update crawl4ai/__version__.py to match the tag version"
+            exit 1
+          fi
+          echo "✅ Version check passed: $TAG_VERSION"
+      
+      - name: Install build dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install build twine
+      
+      - name: Build package
+        run: python -m build
+      
+      - name: Check package
+        run: twine check dist/*
+      
+      - name: Upload to PyPI
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
+        run: |
+          echo "📦 Uploading to PyPI..."
+          twine upload dist/*
+          echo "✅ Package uploaded to https://pypi.org/project/crawl4ai/"
+      
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+      
+      - name: Extract major and minor versions
+        id: versions
+        run: |
+          VERSION=${{ steps.get_version.outputs.VERSION }}
+          MAJOR=$(echo $VERSION | cut -d. -f1)
+          MINOR=$(echo $VERSION | cut -d. -f1-2)
+          echo "MAJOR=$MAJOR" >> $GITHUB_OUTPUT
+          echo "MINOR=$MINOR" >> $GITHUB_OUTPUT
+      
+      - name: Build and push Docker images
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: true
+          tags: |
+            unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}
+            unclecode/crawl4ai:${{ steps.versions.outputs.MINOR }}
+            unclecode/crawl4ai:${{ steps.versions.outputs.MAJOR }}
+            unclecode/crawl4ai:latest
+          platforms: linux/amd64,linux/arm64
+      
+      - name: Create GitHub Release
+        uses: actions/create-release@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          tag_name: v${{ steps.get_version.outputs.VERSION }}
+          release_name: Release v${{ steps.get_version.outputs.VERSION }}
+          body: |
+            ## 🎉 Crawl4AI v${{ steps.get_version.outputs.VERSION }} Released!
+            
+            ### 📦 Installation
+            
+            **PyPI:**
+            ```bash
+            pip install crawl4ai==${{ steps.get_version.outputs.VERSION }}
+            ```
+            
+            **Docker:**
+            ```bash
+            docker pull unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}
+            docker pull unclecode/crawl4ai:latest
+            ```
+            
+            ### 📝 What's Changed
+            See [CHANGELOG.md](https://github.com/${{ github.repository }}/blob/main/CHANGELOG.md) for details.
+          draft: false
+          prerelease: false
+      
+      - name: Summary
+        run: |
+          echo "## 🚀 Release Complete!" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### 📦 PyPI Package" >> $GITHUB_STEP_SUMMARY
+          echo "- Version: ${{ steps.get_version.outputs.VERSION }}" >> $GITHUB_STEP_SUMMARY
+          echo "- URL: https://pypi.org/project/crawl4ai/" >> $GITHUB_STEP_SUMMARY
+          echo "- Install: \`pip install crawl4ai==${{ steps.get_version.outputs.VERSION }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### 🐳 Docker Images" >> $GITHUB_STEP_SUMMARY
+          echo "- \`unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- \`unclecode/crawl4ai:${{ steps.versions.outputs.MINOR }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- \`unclecode/crawl4ai:${{ steps.versions.outputs.MAJOR }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- \`unclecode/crawl4ai:latest\`" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### 📋 GitHub Release" >> $GITHUB_STEP_SUMMARY
+          echo "https://github.com/${{ github.repository }}/releases/tag/v${{ steps.get_version.outputs.VERSION }}" >> $GITHUB_STEP_SUMMARY

.github/workflows/test-release.yml.disabled

@@ -0,0 +1,116 @@
+name: Test Release Pipeline
+on:
+  push:
+    tags:
+      - 'test-v*'
+
+jobs:
+  test-release:
+    runs-on: ubuntu-latest
+    
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      
+      - name: Extract version from tag
+        id: get_version
+        run: |
+          TAG_VERSION=${GITHUB_REF#refs/tags/test-v}
+          echo "VERSION=$TAG_VERSION" >> $GITHUB_OUTPUT
+          echo "Testing with version: $TAG_VERSION"
+      
+      - name: Install package dependencies
+        run: |
+          pip install -e .
+      
+      - name: Check version consistency
+        run: |
+          TAG_VERSION=${{ steps.get_version.outputs.VERSION }}
+          PACKAGE_VERSION=$(python -c "from crawl4ai.__version__ import __version__; print(__version__)")
+          
+          echo "Tag version: $TAG_VERSION"
+          echo "Package version: $PACKAGE_VERSION"
+          
+          if [ "$TAG_VERSION" != "$PACKAGE_VERSION" ]; then
+            echo "❌ Version mismatch! Tag: $TAG_VERSION, Package: $PACKAGE_VERSION"
+            echo "Please update crawl4ai/__version__.py to match the tag version"
+            exit 1
+          fi
+          echo "✅ Version check passed: $TAG_VERSION"
+      
+      - name: Install build dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install build twine
+      
+      - name: Build package
+        run: python -m build
+      
+      - name: Check package
+        run: twine check dist/*
+      
+      - name: Upload to Test PyPI
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.TEST_PYPI_TOKEN }}
+        run: |
+          echo "📦 Uploading to Test PyPI..."
+          twine upload --repository testpypi dist/* || {
+            if [ $? -eq 1 ]; then
+              echo "⚠️ Upload failed - likely version already exists on Test PyPI"
+              echo "Continuing anyway for test purposes..."
+            else
+              exit 1
+            fi
+          }
+          echo "✅ Test PyPI step complete"
+      
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+      
+      - name: Build and push Docker test images
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: true
+          tags: |
+            unclecode/crawl4ai:test-${{ steps.get_version.outputs.VERSION }}
+            unclecode/crawl4ai:test-latest
+          platforms: linux/amd64,linux/arm64
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+      
+      - name: Summary
+        run: |
+          echo "## 🎉 Test Release Complete!" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### 📦 Test PyPI Package" >> $GITHUB_STEP_SUMMARY
+          echo "- Version: ${{ steps.get_version.outputs.VERSION }}" >> $GITHUB_STEP_SUMMARY
+          echo "- URL: https://test.pypi.org/project/crawl4ai/" >> $GITHUB_STEP_SUMMARY
+          echo "- Install: \`pip install -i https://test.pypi.org/simple/ crawl4ai==${{ steps.get_version.outputs.VERSION }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### 🐳 Docker Test Images" >> $GITHUB_STEP_SUMMARY
+          echo "- \`unclecode/crawl4ai:test-${{ steps.get_version.outputs.VERSION }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- \`unclecode/crawl4ai:test-latest\`" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### 🧹 Cleanup Commands" >> $GITHUB_STEP_SUMMARY
+          echo "\`\`\`bash" >> $GITHUB_STEP_SUMMARY
+          echo "# Remove test tag" >> $GITHUB_STEP_SUMMARY
+          echo "git tag -d test-v${{ steps.get_version.outputs.VERSION }}" >> $GITHUB_STEP_SUMMARY
+          echo "git push origin :test-v${{ steps.get_version.outputs.VERSION }}" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "# Remove Docker test images" >> $GITHUB_STEP_SUMMARY
+          echo "docker rmi unclecode/crawl4ai:test-${{ steps.get_version.outputs.VERSION }}" >> $GITHUB_STEP_SUMMARY
+          echo "docker rmi unclecode/crawl4ai:test-latest" >> $GITHUB_STEP_SUMMARY
+          echo "\`\`\`" >> $GITHUB_STEP_SUMMARY

README.md

@@ -28,7 +28,7 @@ Crawl4AI is the #1 trending GitHub repository, actively maintained by a vibrant
 
 [✨ Check out latest update v0.7.0](#-recent-updates)
 
-🎉 **Version 0.7.0 is now available!** The Adaptive Intelligence Update introduces groundbreaking features: Adaptive Crawling that learns website patterns, Virtual Scroll support for infinite pages, intelligent Link Preview with 3-layer scoring, Async URL Seeder for massive discovery, and significant performance improvements. [Read the release notes →](https://docs.crawl4ai.com/blog/release-v0.7.0)
+🎉 **Version 0.7.0 is now available!** The Adaptive Intelligence Update introduces groundbreaking features: Adaptive Crawling that learns website patterns, Virtual Scroll support for infinite pages, intelligent Link Preview with 3-layer scoring, Async URL Seeder for massive discovery, and significant performance improvements. [Read the release notes →](https://github.com/unclecode/crawl4ai/blob/main/docs/blog/release-v0.7.0.md)
 
 <details>
 <summary>🤓 <strong>My Personal Story</strong></summary>
@@ -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
   ```
 

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/async_crawler_strategy.py

@@ -824,7 +824,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
             except Error:
                 visibility_info = await self.check_visibility(page)
 
-                if self.browser_config.config.verbose:
+                if self.browser_config.verbose:
                     self.logger.debug(
                         message="Body visibility info: {info}",
                         tag="DEBUG",

crawl4ai/async_webcrawler.py

@@ -502,9 +502,12 @@ class AsyncWebCrawler:
             metadata = result.get("metadata", {})
         else:
             cleaned_html = sanitize_input_encode(result.cleaned_html)
-            media = result.media.model_dump()
+            # media = result.media.model_dump()
-            tables = media.pop("tables", [])
+            # tables = media.pop("tables", [])
-            links = result.links.model_dump()
+            # links = result.links.model_dump()
+            media = result.media.model_dump() if hasattr(result.media, 'model_dump') else result.media
+            tables = media.pop("tables", []) if isinstance(media, dict) else []
+            links = result.links.model_dump() if hasattr(result.links, 'model_dump') else result.links
             metadata = result.metadata
 
         fit_html = preprocess_html_for_schema(html_content=html, text_threshold= 500, max_size= 300_000)

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/cli.py

@@ -27,7 +27,10 @@ from crawl4ai import (
     PruningContentFilter,
     BrowserProfiler,
     DefaultMarkdownGenerator,
-    LLMConfig
+    LLMConfig,
+    BFSDeepCrawlStrategy,
+    DFSDeepCrawlStrategy,
+    BestFirstCrawlingStrategy,
 )
 from crawl4ai.config import USER_SETTINGS
 from litellm import completion
@@ -1014,9 +1017,11 @@ def cdp_cmd(user_data_dir: Optional[str], port: int, browser_type: str, headless
 @click.option("--question", "-q", help="Ask a question about the crawled content")
 @click.option("--verbose", "-v", is_flag=True)
 @click.option("--profile", "-p", help="Use a specific browser profile (by name)")
+@click.option("--deep-crawl", type=click.Choice(["bfs", "dfs", "best-first"]), help="Enable deep crawling with specified strategy (bfs, dfs, or best-first)")
+@click.option("--max-pages", type=int, default=10, help="Maximum number of pages to crawl in deep crawl mode")
 def crawl_cmd(url: str, browser_config: str, crawler_config: str, filter_config: str, 
            extraction_config: str, json_extract: str, schema: str, browser: Dict, crawler: Dict,
-           output: str, output_file: str, bypass_cache: bool, question: str, verbose: bool, profile: str):
+           output: str, output_file: str, bypass_cache: bool, question: str, verbose: bool, profile: str, deep_crawl: str, max_pages: int):
     """Crawl a website and extract content
     
     Simple Usage:
@@ -1156,6 +1161,27 @@ Always return valid, properly formatted JSON."""
 
         crawler_cfg.scraping_strategy = LXMLWebScrapingStrategy()    
 
+        # Handle deep crawling configuration
+        if deep_crawl:
+            if deep_crawl == "bfs":
+                crawler_cfg.deep_crawl_strategy = BFSDeepCrawlStrategy(
+                    max_depth=3,
+                    max_pages=max_pages
+                )
+            elif deep_crawl == "dfs":
+                crawler_cfg.deep_crawl_strategy = DFSDeepCrawlStrategy(
+                    max_depth=3,
+                    max_pages=max_pages
+                )
+            elif deep_crawl == "best-first":
+                crawler_cfg.deep_crawl_strategy = BestFirstCrawlingStrategy(
+                    max_depth=3,
+                    max_pages=max_pages
+                )
+            
+            if verbose:
+                console.print(f"[green]Deep crawling enabled:[/green] {deep_crawl} strategy, max {max_pages} pages")
+
         config = get_global_config()
         
         browser_cfg.verbose = config.get("VERBOSE", False)
@@ -1170,39 +1196,60 @@ Always return valid, properly formatted JSON."""
             verbose
         )
 
+        # Handle deep crawl results (list) vs single result
+        if isinstance(result, list):
+            if len(result) == 0:
+                click.echo("No results found during deep crawling")
+                return
+            # Use the first result for question answering and output
+            main_result = result[0]
+            all_results = result
+        else:
+            # Single result from regular crawling
+            main_result = result
+            all_results = [result]
+
         # Handle question
         if question:
             provider, token = setup_llm_config()
-            markdown = result.markdown.raw_markdown
+            markdown = main_result.markdown.raw_markdown
             anyio.run(stream_llm_response, url, markdown, question, provider, token)
             return
         
         # Handle output
         if not output_file:
             if output == "all":
-                click.echo(json.dumps(result.model_dump(), indent=2))
+                if isinstance(result, list):
+                    output_data = [r.model_dump() for r in all_results]
+                    click.echo(json.dumps(output_data, indent=2))
+                else:
+                    click.echo(json.dumps(main_result.model_dump(), indent=2))
             elif output == "json":
-                print(result.extracted_content)
+                print(main_result.extracted_content)
-                extracted_items = json.loads(result.extracted_content)
+                extracted_items = json.loads(main_result.extracted_content)
                 click.echo(json.dumps(extracted_items, indent=2))
                 
             elif output in ["markdown", "md"]:
-                click.echo(result.markdown.raw_markdown)
+                click.echo(main_result.markdown.raw_markdown)
             elif output in ["markdown-fit", "md-fit"]:
-                click.echo(result.markdown.fit_markdown)
+                click.echo(main_result.markdown.fit_markdown)
         else:
             if output == "all":
                 with open(output_file, "w") as f:
-                    f.write(json.dumps(result.model_dump(), indent=2))
+                    if isinstance(result, list):
+                        output_data = [r.model_dump() for r in all_results]
+                        f.write(json.dumps(output_data, indent=2))
+                    else:
+                        f.write(json.dumps(main_result.model_dump(), indent=2))
             elif output == "json":
                 with open(output_file, "w") as f:
-                    f.write(result.extracted_content)
+                    f.write(main_result.extracted_content)
             elif output in ["markdown", "md"]:
                 with open(output_file, "w") as f:
-                    f.write(result.markdown.raw_markdown)
+                    f.write(main_result.markdown.raw_markdown)
             elif output in ["markdown-fit", "md-fit"]:
                 with open(output_file, "w") as f:
-                    f.write(result.markdown.fit_markdown)
+                    f.write(main_result.markdown.fit_markdown)
             
     except Exception as e:
         raise click.ClickException(str(e))
@@ -1354,9 +1401,11 @@ def profiles_cmd():
 @click.option("--question", "-q", help="Ask a question about the crawled content")
 @click.option("--verbose", "-v", is_flag=True)
 @click.option("--profile", "-p", help="Use a specific browser profile (by name)")
+@click.option("--deep-crawl", type=click.Choice(["bfs", "dfs", "best-first"]), help="Enable deep crawling with specified strategy")
+@click.option("--max-pages", type=int, default=10, help="Maximum number of pages to crawl in deep crawl mode")
 def default(url: str, example: bool, browser_config: str, crawler_config: str, filter_config: str, 
         extraction_config: str, json_extract: str, schema: str, browser: Dict, crawler: Dict,
-        output: str, bypass_cache: bool, question: str, verbose: bool, profile: str):
+        output: str, bypass_cache: bool, question: str, verbose: bool, profile: str, deep_crawl: str, max_pages: int):
     """Crawl4AI CLI - Web content extraction tool
 
     Simple Usage:
@@ -1406,7 +1455,9 @@ def default(url: str, example: bool, browser_config: str, crawler_config: str, f
         bypass_cache=bypass_cache,
         question=question,
         verbose=verbose,
-        profile=profile
+        profile=profile,
+        deep_crawl=deep_crawl,
+        max_pages=max_pages
     )
 
 def main():

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:

crawl4ai/utils.py

@@ -3342,7 +3342,13 @@ async def get_text_embeddings(
     # Default: use sentence-transformers
     else:
         # Lazy load to avoid importing heavy libraries unless needed
-        from sentence_transformers import SentenceTransformer
+        try:
+            from sentence_transformers import SentenceTransformer
+        except ImportError:
+            raise ImportError(
+                "sentence-transformers is required for local embeddings. "
+                "Install it with: pip install 'crawl4ai[transformer]' or pip install sentence-transformers"
+            )
         
         # Cache the model in function attribute to avoid reloading
         if not hasattr(get_text_embeddings, '_models'):

deploy/docker/api.py

@@ -5,6 +5,7 @@ from typing import List, Tuple, Dict
 from functools import partial
 from uuid import uuid4
 from datetime import datetime
+from base64 import b64encode
 
 import logging
 from typing import Optional, AsyncGenerator
@@ -54,27 +55,6 @@ def _get_memory_mb():
         logger.warning(f"Could not get memory info: {e}")
         return None
 
-# --- Helper to sanitize JSON data ---
-def sanitize_json_data(data):
-    """
-    Recursively sanitize data to handle infinity and NaN values that are not JSON compliant.
-    """
-    import math
-    
-    if isinstance(data, dict):
-        return {k: sanitize_json_data(v) for k, v in data.items()}
-    elif isinstance(data, list):
-        return [sanitize_json_data(item) for item in data]
-    elif isinstance(data, float):
-        if math.isinf(data):
-            return "Infinity" if data > 0 else "-Infinity"
-        elif math.isnan(data):
-            return "NaN"
-        else:
-            return data
-    else:
-        return data
-
 
 async def handle_llm_qa(
     url: str,
@@ -392,10 +372,11 @@ async def stream_results(crawler: AsyncWebCrawler, results_gen: AsyncGenerator)
                 server_memory_mb = _get_memory_mb()
                 result_dict = result.model_dump()
                 result_dict['server_memory_mb'] = server_memory_mb
-                # Sanitize data to handle infinity values
+                # If PDF exists, encode it to base64
-                sanitized_dict = sanitize_json_data(result_dict)
+                if result_dict.get('pdf') is not None:
-                logger.info(f"Streaming result for {sanitized_dict.get('url', 'unknown')}")
+                    result_dict['pdf'] = b64encode(result_dict['pdf']).decode('utf-8')
-                data = json.dumps(sanitized_dict, default=datetime_handler) + "\n"
+                logger.info(f"Streaming result for {result_dict.get('url', 'unknown')}")
+                data = json.dumps(result_dict, default=datetime_handler) + "\n"
                 yield data.encode('utf-8')
             except Exception as e:
                 logger.error(f"Serialization error: {e}")
@@ -466,10 +447,19 @@ async def handle_crawl_request(
             mem_delta_mb = end_mem_mb - start_mem_mb # <--- Calculate delta
             peak_mem_mb = max(peak_mem_mb if peak_mem_mb else 0, end_mem_mb) # <--- Get peak memory
         logger.info(f"Memory usage: Start: {start_mem_mb} MB, End: {end_mem_mb} MB, Delta: {mem_delta_mb} MB, Peak: {peak_mem_mb} MB")
-                              
+
+        # Process results to handle PDF bytes
+        processed_results = []
+        for result in results:
+            result_dict = result.model_dump()
+            # If PDF exists, encode it to base64
+            if result_dict.get('pdf') is not None:
+                result_dict['pdf'] = b64encode(result_dict['pdf']).decode('utf-8')
+            processed_results.append(result_dict)
+            
         return {
             "success": True,
-            "results": [sanitize_json_data(result.model_dump()) for result in results],
+            "results": processed_results,
             "server_processing_time_s": end_time - start_time,
             "server_memory_delta_mb": mem_delta_mb,
             "server_peak_memory_mb": peak_mem_mb

deploy/docker/server.py

@@ -331,27 +331,6 @@ async def generate_pdf(
     return {"success": True, "pdf": base64.b64encode(pdf_data).decode()}
 
 
-def sanitize_json_data(data):
-    """
-    Recursively sanitize data to handle infinity and NaN values that are not JSON compliant.
-    """
-    import math
-    
-    if isinstance(data, dict):
-        return {k: sanitize_json_data(v) for k, v in data.items()}
-    elif isinstance(data, list):
-        return [sanitize_json_data(item) for item in data]
-    elif isinstance(data, float):
-        if math.isinf(data):
-            return "Infinity" if data > 0 else "-Infinity"
-        elif math.isnan(data):
-            return "NaN"
-        else:
-            return data
-    else:
-        return data
-
-
 @app.post("/execute_js")
 @limiter.limit(config["rate_limiting"]["default_limit"])
 @mcp_tool("execute_js")
@@ -410,9 +389,7 @@ async def execute_js(
         results = await crawler.arun(url=body.url, config=cfg)
     # Return JSON-serializable dict of the first CrawlResult
     data = results[0].model_dump()
-    # Sanitize data to handle infinity values
+    return JSONResponse(data)
-    sanitized_data = sanitize_json_data(data)
-    return JSONResponse(sanitized_data)
 
 
 @app.get("/llm/{url:path}")

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 +29,41 @@ 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
+import asyncio
 
-# Initialize with custom learning parameters
+async def main():
-config = AdaptiveConfig(
+    
-    confidence_threshold=0.7,    # Min confidence to use learned patterns
+    # Configure adaptive crawler
-    max_history=100,            # Remember last 100 crawls per domain
+    config = AdaptiveConfig(
-    learning_rate=0.2,          # How quickly to adapt to changes
+        strategy="statistical",  # or "embedding" for semantic understanding
-    patterns_per_page=3,        # Patterns to learn per page type
+        max_pages=10,
-    extraction_strategy='css'   # 'css' or 'xpath'
+        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
-adaptive_crawler = AdaptiveCrawler(config)
-
-# First crawl - crawler learns the structure
-async with AsyncWebCrawler() as crawler:
-    result = await crawler.arun(
-        "https://news.example.com/article/12345",
-        config=CrawlerRunConfig(
-            adaptive_config=config,
-            extraction_hints={  # Optional hints to speed up learning
-                "title": "article h1",
-                "content": "article .body-content"
-            }
-        )
     )
     
-    # Crawler identifies and stores patterns
+    async with AsyncWebCrawler(verbose=False) as crawler:
-    if result.success:
+        adaptive = AdaptiveCrawler(crawler, config)
-        state = adaptive_crawler.get_state("news.example.com")
+        
-        print(f"Learned {len(state.patterns)} patterns")
+        print("Starting adaptive crawl about Python decorators...")
-        print(f"Confidence: {state.avg_confidence:.2%}")
+        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%})")
 
-# Subsequent crawls - uses learned patterns
+asyncio.run(main())
-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 +88,7 @@ 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 +96,7 @@ 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 +104,7 @@ 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
@@ -157,68 +148,63 @@ 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
+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
-    # What to analyze
+    link_config = LinkPreviewConfig(
-    include_internal=True,
+        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
-result = await crawler.arun(
-    "https://tech-blog.example.com",
-    config=CrawlerRunConfig(
-        link_preview_config=link_config,
-        score_links=True
     )
-)
+    # 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
-for link in result.links["internal"][:10]:  # Top 10 internal links
+        if result.success and result.links:
-    print(f"Score: {link['total_score']:.3f}")
+            for link in result.links.get("internal", []):
-    print(f"  Intrinsic: {link['intrinsic_score']:.1f}/10")  # Position, attributes
+                text = link.get('text', 'No text')[:40]
-    print(f"  Contextual: {link['contextual_score']:.1f}/1")  # Relevance to query
+                print(
-    print(f"  URL: {link['href']}")
+                    text,
-    print(f"  Title: {link['head_data']['title']}")
+                    f"{link.get('intrinsic_score', 0):.1f}/10" if link.get('intrinsic_score') is not None else "0.0/10",
-    print(f"  Description: {link['head_data']['meta']['description'][:100]}...")
+                    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"
+                )
+
+asyncio.run(main())
 ```
 
 **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
@@ -235,58 +221,34 @@ for link in result.links["internal"][:10]:  # Top 10 internal links
 ### 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="sitemap+cc",        # 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
-    ignore_patterns=["*/reviews/*", "*/questions/*"],
+            query="python tutorial",  # For relevance scoring
-    
+            scoring_method="bm25",
-    # Validation
+            score_threshold=0.2,
-    live_check=True,           # Verify URLs are alive
+            max_urls=10
-    max_urls=5000,             # Stop at 5000 URLs
+        )
-    
+        
-    # Performance  
+        print("Discovering Python async tutorial URLs...")
-    concurrency=100,           # Parallel requests
+        urls = await seeder.urls("https://www.geeksforgeeks.org/", config)
-    hits_per_sec=10           # Rate limiting
+        
-)
+        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]}...")
 
-seeder = AsyncUrlSeeder(seeder_config)
+asyncio.run(main())
-urls = await seeder.discover("https://shop.example.com")
-
-# Advanced: Relevance-based discovery
-research_config = SeedingConfig(
-    source="crawl+sitemap",    # Deep crawl + sitemap
-    pattern="*/blog/*",        # Blog posts only
-    
-    # Content relevance
-    extract_head=True,         # Get meta tags
-    query="quantum computing tutorials",
-    scoring_method="bm25",     # Or "semantic" (coming soon)
-    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):
-    discovered.extend(batch)
-    print(f"Found {len(discovered)} relevant URLs so far...")
-
-# 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"Title: {url_data['title']}")
 ```
 
 **Discovery Methods:**
@@ -309,35 +271,18 @@ 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 +292,6 @@ 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/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/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 +29,41 @@ 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
+import asyncio
 
-# Initialize with custom learning parameters
+async def main():
-config = AdaptiveConfig(
+    
-    confidence_threshold=0.7,    # Min confidence to use learned patterns
+    # Configure adaptive crawler
-    max_history=100,            # Remember last 100 crawls per domain
+    config = AdaptiveConfig(
-    learning_rate=0.2,          # How quickly to adapt to changes
+        strategy="statistical",  # or "embedding" for semantic understanding
-    patterns_per_page=3,        # Patterns to learn per page type
+        max_pages=10,
-    extraction_strategy='css'   # 'css' or 'xpath'
+        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
-adaptive_crawler = AdaptiveCrawler(config)
-
-# First crawl - crawler learns the structure
-async with AsyncWebCrawler() as crawler:
-    result = await crawler.arun(
-        "https://news.example.com/article/12345",
-        config=CrawlerRunConfig(
-            adaptive_config=config,
-            extraction_hints={  # Optional hints to speed up learning
-                "title": "article h1",
-                "content": "article .body-content"
-            }
-        )
     )
     
-    # Crawler identifies and stores patterns
+    async with AsyncWebCrawler(verbose=False) as crawler:
-    if result.success:
+        adaptive = AdaptiveCrawler(crawler, config)
-        state = adaptive_crawler.get_state("news.example.com")
+        
-        print(f"Learned {len(state.patterns)} patterns")
+        print("Starting adaptive crawl about Python decorators...")
-        print(f"Confidence: {state.avg_confidence:.2%}")
+        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%})")
 
-# Subsequent crawls - uses learned patterns
+asyncio.run(main())
-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 +88,7 @@ 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 +96,7 @@ 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 +104,7 @@ 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
@@ -157,68 +148,63 @@ 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
+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
-    # What to analyze
+    link_config = LinkPreviewConfig(
-    include_internal=True,
+        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
-result = await crawler.arun(
-    "https://tech-blog.example.com",
-    config=CrawlerRunConfig(
-        link_preview_config=link_config,
-        score_links=True
     )
-)
+    # 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
-for link in result.links["internal"][:10]:  # Top 10 internal links
+        if result.success and result.links:
-    print(f"Score: {link['total_score']:.3f}")
+            for link in result.links.get("internal", []):
-    print(f"  Intrinsic: {link['intrinsic_score']:.1f}/10")  # Position, attributes
+                text = link.get('text', 'No text')[:40]
-    print(f"  Contextual: {link['contextual_score']:.1f}/1")  # Relevance to query
+                print(
-    print(f"  URL: {link['href']}")
+                    text,
-    print(f"  Title: {link['head_data']['title']}")
+                    f"{link.get('intrinsic_score', 0):.1f}/10" if link.get('intrinsic_score') is not None else "0.0/10",
-    print(f"  Description: {link['head_data']['meta']['description'][:100]}...")
+                    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"
+                )
+
+asyncio.run(main())
 ```
 
 **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
@@ -235,58 +221,34 @@ for link in result.links["internal"][:10]:  # Top 10 internal links
 ### 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="sitemap+cc",        # 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
-    ignore_patterns=["*/reviews/*", "*/questions/*"],
+            query="python tutorial",  # For relevance scoring
-    
+            scoring_method="bm25",
-    # Validation
+            score_threshold=0.2,
-    live_check=True,           # Verify URLs are alive
+            max_urls=10
-    max_urls=5000,             # Stop at 5000 URLs
+        )
-    
+        
-    # Performance  
+        print("Discovering Python async tutorial URLs...")
-    concurrency=100,           # Parallel requests
+        urls = await seeder.urls("https://www.geeksforgeeks.org/", config)
-    hits_per_sec=10           # Rate limiting
+        
-)
+        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]}...")
 
-seeder = AsyncUrlSeeder(seeder_config)
+asyncio.run(main())
-urls = await seeder.discover("https://shop.example.com")
-
-# Advanced: Relevance-based discovery
-research_config = SeedingConfig(
-    source="crawl+sitemap",    # Deep crawl + sitemap
-    pattern="*/blog/*",        # Blog posts only
-    
-    # Content relevance
-    extract_head=True,         # Get meta tags
-    query="quantum computing tutorials",
-    scoring_method="bm25",     # Or "semantic" (coming soon)
-    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):
-    discovered.extend(batch)
-    print(f"Found {len(discovered)} relevant URLs so far...")
-
-# 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"Title: {url_data['title']}")
 ```
 
 **Discovery Methods:**
@@ -309,35 +271,18 @@ 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 +292,6 @@ 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/c4a-script.md

@@ -52,11 +52,9 @@ That's it! In just a few lines, you've automated a complete search workflow.
 
 Want to learn by doing? We've got you covered:
 
-**🚀 [Live Demo](https://docs.crawl4ai.com/c4a-script/demo)** - Try C4A-Script in your browser right now!
+**🚀 [Live Demo](https://docs.crawl4ai.com/apps/c4a-script/)** - Try C4A-Script in your browser right now!
 
-**📁 [Tutorial Examples](/examples/c4a_script/)** - Complete examples with source code
+**📁 [Tutorial Examples](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/c4a_script/)** - Complete examples with source code
-
-**🛠️ [Local Tutorial](/examples/c4a_script/tutorial/)** - Run the interactive tutorial on your machine
 
 ### Running the Tutorial Locally
 

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/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

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__":

pyproject.toml

@@ -44,7 +44,6 @@ dependencies = [
     "brotli>=1.1.0",
     "humanize>=4.10.0",
     "lark>=1.2.2",
-    "sentence-transformers>=2.2.0",
     "alphashape>=1.3.1",
     "shapely>=2.0.0"
 ]
@@ -62,8 +61,8 @@ classifiers = [
 [project.optional-dependencies]
 pdf = ["PyPDF2"]  
 torch = ["torch", "nltk", "scikit-learn"]
-transformer = ["transformers", "tokenizers"]
+transformer = ["transformers", "tokenizers", "sentence-transformers"]
-cosine = ["torch", "transformers", "nltk"]
+cosine = ["torch", "transformers", "nltk", "sentence-transformers"]
 sync = ["selenium"]
 all = [
     "PyPDF2",
@@ -72,8 +71,8 @@ all = [
     "scikit-learn",
     "transformers",
     "tokenizers",
-    "selenium",
+    "sentence-transformers",
-    "PyPDF2"  
+    "selenium"
 ]
 
 [project.scripts]

requirements.txt

@@ -24,7 +24,6 @@ cssselect>=1.2.0
 chardet>=5.2.0
 brotli>=1.1.0
 httpx[http2]>=0.27.2
-sentence-transformers>=2.2.0
 alphashape>=1.3.1
 shapely>=2.0.0
 

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():