fix: update package versions in requirements.txt for compatibility

- Acknowledge contributor paulokuong for fixing RAWL4_AI_BASE_DIRECTORY issue
  - Refine base directory handling in `setup.py`
  - Clarify Playwright installation instructions and improve error handling

.gitignore

@@ -214,3 +214,4 @@ git_issues.md
 todo_executor.md
 protect-all-except-feature.sh
 manage-collab.sh
+publish.sh

CONTRIBUTORS.md

@@ -21,6 +21,7 @@ We would like to thank the following people for their contributions to Crawl4AI:
 - [nelzomal](https://github.com/nelzomal) - Enhance development installation instructions [#286](https://github.com/unclecode/crawl4ai/pull/286)
 - [HamzaFarhan](https://github.com/HamzaFarhan) - Handled the cases where markdown_with_citations, references_markdown, and filtered_html might not be defined [#293](https://github.com/unclecode/crawl4ai/pull/293)
 - [NanmiCoder](https://github.com/NanmiCoder) - fix: crawler strategy exception handling and fixes [#271](https://github.com/unclecode/crawl4ai/pull/271)
+- [paulokuong](https://github.com/paulokuong) - fix: RAWL4_AI_BASE_DIRECTORY should be Path object instead of string [#298](https://github.com/unclecode/crawl4ai/pull/298)
 
 
 ## Other Contributors

README.md

@@ -1,4 +1,4 @@
-# 🔥🕷️ Crawl4AI: LLM Friendly Web Crawler & Scraper
+# 🔥🕷️ Crawl4AI: Crawl Smarter, Faster, Freely. For AI.
 
 <a href="https://trendshift.io/repositories/11716" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11716" alt="unclecode%2Fcrawl4ai | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 
@@ -9,22 +9,114 @@
 [![GitHub Pull Requests](https://img.shields.io/github/issues-pr/unclecode/crawl4ai)](https://github.com/unclecode/crawl4ai/pulls)
 [![License](https://img.shields.io/github/license/unclecode/crawl4ai)](https://github.com/unclecode/crawl4ai/blob/main/LICENSE)
 
-Crawl4AI simplifies asynchronous web crawling and data extraction, making it accessible for large language models (LLMs) and AI applications. 🆓🌐
+Crawl4AI is the #1 trending GitHub repository, actively maintained by a vibrant community. It delivers blazing-fast, AI-ready web crawling tailored for LLMs, AI agents, and data pipelines. Open source, flexible, and built for real-time performance, Crawl4AI empowers developers with unmatched speed, precision, and deployment ease.  
 
-## New in 0.3.74 ✨
+[✨ Check out latest update v0.3.745](#-recent-updates)
+
+## 🧐 Why Crawl4AI?
+
+1. **Built for LLMs**: Creates smart, concise Markdown optimized for RAG and fine-tuning applications.  
+2. **Lightning Fast**: Delivers results 6x faster with real-time, cost-efficient performance.  
+3. **Flexible Browser Control**: Offers session management, proxies, and custom hooks for seamless data access.  
+4. **Heuristic Intelligence**: Uses advanced algorithms for efficient extraction, reducing reliance on costly models.  
+5. **Open Source & Deployable**: Fully open-source with no API keys—ready for Docker and cloud integration.  
+6. **Thriving Community**: Actively maintained by a vibrant community and the #1 trending GitHub repository.
+
+## 🚀 Quick Start 
+
+1. Install Crawl4AI:
+```bash
+pip install crawl4ai
+```
+
+2. Run a simple web crawl:
+```python
+import asyncio
+from crawl4ai import AsyncWebCrawler, CacheMode
+
+async def main():
+    async with AsyncWebCrawler(verbose=True) as crawler:
+        result = await crawler.arun(url="https://www.nbcnews.com/business")
+        # Soone will be change to result.markdown
+        print(result.markdown_v2.raw_markdown) 
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+## ✨ Features 
+
+<details>
+<summary>📝 <strong>Markdown Generation</strong></summary>
+
+- 🧹 **Clean Markdown**: Generates clean, structured Markdown with accurate formatting.
+- 🎯 **Fit Markdown**: Heuristic-based filtering to remove noise and irrelevant parts for AI-friendly processing.
+- 🔗 **Citations and References**: Converts page links into a numbered reference list with clean citations.
+- 🛠️ **Custom Strategies**: Users can create their own Markdown generation strategies tailored to specific needs.
+- 📚 **BM25 Algorithm**: Employs BM25-based filtering for extracting core information and removing irrelevant content. 
+</details>
+
+<details>
+<summary>📊 <strong>Structured Data Extraction</strong></summary>
+
+- 🤖 **LLM-Driven Extraction**: Supports all LLMs (open-source and proprietary) for structured data extraction.
+- 🧱 **Chunking Strategies**: Implements chunking (topic-based, regex, sentence-level) for targeted content processing.
+- 🌌 **Cosine Similarity**: Find relevant content chunks based on user queries for semantic extraction.
+- 🔎 **CSS-Based Extraction**: Fast schema-based data extraction using XPath and CSS selectors.
+- 🔧 **Schema Definition**: Define custom schemas for extracting structured JSON from repetitive patterns.
+
+</details>
+
+<details>
+<summary>🌐 <strong>Browser Integration</strong></summary>
+
+- 🖥️ **Managed Browser**: Use user-owned browsers with full control, avoiding bot detection.
+- 🔄 **Remote Browser Control**: Connect to Chrome Developer Tools Protocol for remote, large-scale data extraction.
+- 🔒 **Session Management**: Preserve browser states and reuse them for multi-step crawling.
+- 🧩 **Proxy Support**: Seamlessly connect to proxies with authentication for secure access.
+- ⚙️ **Full Browser Control**: Modify headers, cookies, user agents, and more for tailored crawling setups.
+- 🌍 **Multi-Browser Support**: Compatible with Chromium, Firefox, and WebKit.
+
+</details>
+
+<details>
+<summary>🔎 <strong>Crawling & Scraping</strong></summary>
+
+- 🖼️ **Media Support**: Extract images, audio, videos, and responsive image formats like `srcset` and `picture`.
+- 🚀 **Dynamic Crawling**: Execute JS and wait for async or sync for dynamic content extraction.
+- 📸 **Screenshots**: Capture page screenshots during crawling for debugging or analysis.
+- 📂 **Raw Data Crawling**: Directly process raw HTML (`raw:`) or local files (`file://`).
+- 🔗 **Comprehensive Link Extraction**: Extracts internal, external links, and embedded iframe content.
+- 🛠️ **Customizable Hooks**: Define hooks at every step to customize crawling behavior.
+- 💾 **Caching**: Cache data for improved speed and to avoid redundant fetches.
+- 📄 **Metadata Extraction**: Retrieve structured metadata from web pages.
+- 📡 **IFrame Content Extraction**: Seamless extraction from embedded iframe content.
+
+</details>
+
+<details>
+<summary>🚀 <strong>Deployment</strong></summary>
+
+- 🐳 **Dockerized Setup**: Optimized Docker image with API server for easy deployment.
+- 🔄 **API Gateway**: One-click deployment with secure token authentication for API-based workflows.
+- 🌐 **Scalable Architecture**: Designed for mass-scale production and optimized server performance.
+- ⚙️ **DigitalOcean Deployment**: Ready-to-deploy configurations for DigitalOcean and similar platforms.
+
+</details>
+
+<details>
+<summary>🎯 <strong>Additional Features</strong></summary>
+
+- 🕶️ **Stealth Mode**: Avoid bot detection by mimicking real users.
+- 🏷️ **Tag-Based Content Extraction**: Refine crawling based on custom tags, headers, or metadata.
+- 🔗 **Link Analysis**: Extract and analyze all links for detailed data exploration.
+- 🛡️ **Error Handling**: Robust error management for seamless execution.
+- 🔐 **CORS & Static Serving**: Supports filesystem-based caching and cross-origin requests.
+- 📖 **Clear Documentation**: Simplified and updated guides for onboarding and advanced usage.
+- 🙌 **Community Recognition**: Acknowledges contributors and pull requests for transparency.
+
+</details>
 
-- 🚀 **Blazing Fast Scraping**: Significantly improved scraping speed.  
-- 📥 **Download Manager**: Integrated file crawling, downloading, and tracking within `CrawlResult`.  
-- 📝 **Markdown Strategy**: Flexible system for custom markdown generation and formats.  
-- 🔗 **LLM-Friendly Citations**: Auto-converts links to numbered citations with reference lists.  
-- 🔎 **Markdown Filter**: BM25-based content extraction for cleaner, relevant markdown.  
-- 🖼️ **Image Extraction**: Supports `srcset`, `picture`, and responsive image formats.  
-- 🗂️ **Local/Raw HTML**: Crawl `file://` paths and raw HTML (`raw:`) directly.  
-- 🤖 **Browser Control**: Custom browser setups with stealth integration to bypass bots.  
-- ☁️ **API & Cache Boost**: CORS, static serving, and enhanced filesystem-based caching.  
-- 🐳 **API Gateway**: Run as an API service with secure token authentication.  
-- 🛠️ **Database Upgrades**: Optimized for larger content sets with faster caching.  
-- 🐛 **Bug Fixes**: Resolved browser context issues, memory leaks, and improved error handling.
 
 
 ## Try it Now!
@@ -65,11 +157,12 @@ Crawl4AI simplifies asynchronous web crawling and data extraction, making it acc
 
 Crawl4AI offers flexible installation options to suit various use cases. You can install it as a Python package or use Docker.
 
-### Using pip 🐍
+<details>
+<summary>🐍 <strong>Using pip</strong></summary>
 
 Choose the installation option that best fits your needs:
 
-#### Basic Installation
+### Basic Installation
 
 For basic web crawling and scraping tasks:
 
@@ -79,7 +172,7 @@ pip install crawl4ai
 
 By default, this will install the asynchronous version of Crawl4AI, using Playwright for web crawling.
 
-👉 Note: When you install Crawl4AI, the setup script should automatically install and set up Playwright. However, if you encounter any Playwright-related errors, you can manually install it using one of these methods:
+👉 **Note**: When you install Crawl4AI, the setup script should automatically install and set up Playwright. However, if you encounter any Playwright-related errors, you can manually install it using one of these methods:
 
 1. Through the command line:
 
@@ -95,15 +188,19 @@ By default, this will install the asynchronous version of Crawl4AI, using Playwr
 
 This second method has proven to be more reliable in some cases.
 
-#### Installation with Synchronous Version
+---
 
-If you need the synchronous version using Selenium:
+### Installation with Synchronous Version
+
+The sync version is deprecated and will be removed in future versions. If you need the synchronous version using Selenium:
 
 ```bash
 pip install crawl4ai[sync]
 ```
 
-#### Development Installation
+---
+
+### Development Installation
 
 For contributors who plan to modify the source code:
 
@@ -112,7 +209,9 @@ git clone https://github.com/unclecode/crawl4ai.git
 cd crawl4ai
 pip install -e .                    # Basic installation in editable mode
 ```
+
 Install optional features:
+
 ```bash
 pip install -e ".[torch]"           # With PyTorch features
 pip install -e ".[transformer]"     # With Transformer features
@@ -121,7 +220,10 @@ pip install -e ".[sync]"            # With synchronous crawling (Selenium)
 pip install -e ".[all]"             # Install all optional features
 ```
 
-## One-Click Deployment 🚀
+</details>
+
+<details>
+<summary>🚀 <strong>One-Click Deployment</strong></summary>
 
 Deploy your own instance of Crawl4AI with one click:
 
@@ -132,14 +234,19 @@ Deploy your own instance of Crawl4AI with one click:
 The deploy will:
 - Set up a Docker container with Crawl4AI
 - Configure Playwright and all dependencies
-- Start the FastAPI server on port 11235
+- Start the FastAPI server on port `11235`
 - Set up health checks and auto-deployment
 
-### Using Docker 🐳
+</details>
+
+<details>
+<summary>🐳 <strong>Using Docker</strong></summary>
 
 Crawl4AI is available as Docker images for easy deployment. You can either pull directly from Docker Hub (recommended) or build from the repository.
 
-#### Option 1: Docker Hub (Recommended)
+---
+
+### Option 1: Docker Hub (Recommended)
 
 ```bash
 # Pull and run from Docker Hub (choose one):
@@ -157,7 +264,9 @@ docker run --platform linux/arm64 -p 11235:11235 unclecode/crawl4ai:basic
 docker run --shm-size=2gb -p 11235:11235 unclecode/crawl4ai:basic
 ```
 
-#### Option 2: Build from Repository
+---
+
+### Option 2: Build from Repository
 
 ```bash
 # Clone the repository
@@ -179,7 +288,12 @@ docker build -t crawl4ai:local \
 docker run -p 11235:11235 crawl4ai:local
 ```
 
-Quick test (works for both options):
+---
+
+### Quick Test
+
+Run a quick test (works for both Docker options):
+
 ```python
 import requests
 
@@ -196,143 +310,134 @@ result = requests.get(f"http://localhost:11235/task/{task_id}")
 
 For advanced configuration, environment variables, and usage examples, see our [Docker Deployment Guide](https://crawl4ai.com/mkdocs/basic/docker-deployment/).
 
+</details>
 
-## Quick Start 🚀
+
+## 🔬 Advanced Usage Examples 🔬
+
+You can check the project structure in the directory [https://github.com/unclecode/crawl4ai/docs/examples](docs/examples). Over there, you can find a variety of examples; here, some popular examples are shared.
+
+<details>
+<summary>📝 <strong>Heuristic Markdown Generation with Clean and Fit Markdown</strong></summary>
 
 ```python
 import asyncio
-from crawl4ai import AsyncWebCrawler
+from crawl4ai import AsyncWebCrawler, CacheMode
+from crawl4ai.content_filter_strategy import BM25ContentFilter
+from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
 
 async def main():
-    async with AsyncWebCrawler(verbose=True) as crawler:
-        result = await crawler.arun(url="https://www.nbcnews.com/business")
-        print(result.markdown)
-
-if __name__ == "__main__":
-    asyncio.run(main())
-```
-
-## Advanced Usage 🔬
-
-### Executing JavaScript and Using CSS Selectors
-
-```python
-import asyncio
-from crawl4ai import AsyncWebCrawler
-
-async def main():
-    async with AsyncWebCrawler(verbose=True) as crawler:
-        js_code = ["const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();"]
+    async with AsyncWebCrawler(
+        headless=True,  
+        verbose=True,
+    ) as crawler:
         result = await crawler.arun(
-            url="https://www.nbcnews.com/business",
-            js_code=js_code,
-            css_selector=".wide-tease-item__description",
-            bypass_cache=True
+            url="https://docs.micronaut.io/4.7.6/guide/",
+            cache_mode=CacheMode.ENABLED,
+            markdown_generator=DefaultMarkdownGenerator(
+                content_filter=BM25ContentFilter(user_query=None, bm25_threshold=1.0)
+            ),
         )
-        print(result.extracted_content)
+        print(len(result.markdown))
+        print(len(result.fit_markdown))
+        print(len(result.markdown_v2.fit_markdown))
 
 if __name__ == "__main__":
     asyncio.run(main())
 ```
 
-### Using a Proxy
+</details>
+
+<details>
+<summary>🖥️ <strong>Executing JavaScript & Extract Structured Data without LLMs</strong></summary>
 
 ```python
 import asyncio
-from crawl4ai import AsyncWebCrawler
-
-async def main():
-    async with AsyncWebCrawler(verbose=True, proxy="http://127.0.0.1:7890") as crawler:
-        result = await crawler.arun(
-            url="https://www.nbcnews.com/business",
-            bypass_cache=True
-        )
-        print(result.markdown)
-
-if __name__ == "__main__":
-    asyncio.run(main())
-```
-
-### Extracting Structured Data without LLM
-
-The `JsonCssExtractionStrategy` allows for precise extraction of structured data from web pages using CSS selectors.
-
-```python
-import asyncio
-import json
-from crawl4ai import AsyncWebCrawler
+from crawl4ai import AsyncWebCrawler, CacheMode
 from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+import json
 
-async def extract_news_teasers():
+async def main():
     schema = {
-        "name": "News Teaser Extractor",
-        "baseSelector": ".wide-tease-item__wrapper",
-        "fields": [
-            {
-                "name": "category",
-                "selector": ".unibrow span[data-testid='unibrow-text']",
-                "type": "text",
-            },
-            {
-                "name": "headline",
-                "selector": ".wide-tease-item__headline",
-                "type": "text",
-            },
-            {
-                "name": "summary",
-                "selector": ".wide-tease-item__description",
-                "type": "text",
-            },
-            {
-                "name": "time",
-                "selector": "[data-testid='wide-tease-date']",
-                "type": "text",
-            },
-            {
-                "name": "image",
-                "type": "nested",
-                "selector": "picture.teasePicture img",
-                "fields": [
-                    {"name": "src", "type": "attribute", "attribute": "src"},
-                    {"name": "alt", "type": "attribute", "attribute": "alt"},
-                ],
-            },
-            {
-                "name": "link",
-                "selector": "a[href]",
-                "type": "attribute",
-                "attribute": "href",
-            },
-        ],
-    }
+    "name": "KidoCode Courses",
+    "baseSelector": "section.charge-methodology .w-tab-content > div",
+    "fields": [
+        {
+            "name": "section_title",
+            "selector": "h3.heading-50",
+            "type": "text",
+        },
+        {
+            "name": "section_description",
+            "selector": ".charge-content",
+            "type": "text",
+        },
+        {
+            "name": "course_name",
+            "selector": ".text-block-93",
+            "type": "text",
+        },
+        {
+            "name": "course_description",
+            "selector": ".course-content-text",
+            "type": "text",
+        },
+        {
+            "name": "course_icon",
+            "selector": ".image-92",
+            "type": "attribute",
+            "attribute": "src"
+        }
+    ]
+}
 
     extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)
 
-    async with AsyncWebCrawler(verbose=True) as crawler:
+    async with AsyncWebCrawler(
+        headless=False,
+        verbose=True
+    ) as crawler:
+        
+        # Create the JavaScript that handles clicking multiple times
+        js_click_tabs = """
+        (async () => {
+            const tabs = document.querySelectorAll("section.charge-methodology .tabs-menu-3 > div");
+            
+            for(let tab of tabs) {
+                // scroll to the tab
+                tab.scrollIntoView();
+                tab.click();
+                // Wait for content to load and animations to complete
+                await new Promise(r => setTimeout(r, 500));
+            }
+        })();
+        """     
+
         result = await crawler.arun(
-            url="https://www.nbcnews.com/business",
-            extraction_strategy=extraction_strategy,
-            bypass_cache=True,
+            url="https://www.kidocode.com/degrees/technology",
+            extraction_strategy=JsonCssExtractionStrategy(schema, verbose=True),
+            js_code=[js_click_tabs],
+            cache_mode=CacheMode.BYPASS
         )
 
-        assert result.success, "Failed to crawl the page"
+        companies = json.loads(result.extracted_content)
+        print(f"Successfully extracted {len(companies)} companies")
+        print(json.dumps(companies[0], indent=2))
 
-        news_teasers = json.loads(result.extracted_content)
-        print(f"Successfully extracted {len(news_teasers)} news teasers")
-        print(json.dumps(news_teasers[0], indent=2))
 
 if __name__ == "__main__":
-    asyncio.run(extract_news_teasers())
+    asyncio.run(main())
 ```
 
-For more advanced usage examples, check out our [Examples](https://crawl4ai.com/mkdocs/extraction/css-advanced/) section in the documentation.
+</details>
 
-### Extracting Structured Data with OpenAI
+<details>
+<summary>📚 <strong>Extracting Structured Data with LLMs</strong></summary>
 
 ```python
 import os
 import asyncio
-from crawl4ai import AsyncWebCrawler
+from crawl4ai import AsyncWebCrawler, CacheMode
 from crawl4ai.extraction_strategy import LLMExtractionStrategy
 from pydantic import BaseModel, Field
 
@@ -347,6 +452,8 @@ async def main():
             url='https://openai.com/api/pricing/',
             word_count_threshold=1,
             extraction_strategy=LLMExtractionStrategy(
+                # Here you can use any provider that Litellm library supports, for instance: ollama/qwen2
+                # provider="ollama/qwen2", api_token="no-token", 
                 provider="openai/gpt-4o", api_token=os.getenv('OPENAI_API_KEY'), 
                 schema=OpenAIModelFee.schema(),
                 extraction_type="schema",
@@ -354,7 +461,7 @@ async def main():
                 Do not miss any models in the entire content. One extracted model JSON format should look like this: 
                 {"model_name": "GPT-4", "input_fee": "US$10.00 / 1M tokens", "output_fee": "US$30.00 / 1M tokens"}."""
             ),            
-            bypass_cache=True,
+            cache_mode=CacheMode.BYPASS,
         )
         print(result.extracted_content)
 
@@ -362,143 +469,98 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
-### Session Management and Dynamic Content Crawling
+</details>
 
-Crawl4AI excels at handling complex scenarios, such as crawling multiple pages with dynamic content loaded via JavaScript. Here's an example of crawling GitHub commits across multiple pages:
+<details>
+<summary>🤖 <strong>Using You own Browswer with Custome User Profile</strong></summary>
 
 ```python
-import asyncio
-import re
-from bs4 import BeautifulSoup
+import os, sys
+from pathlib import Path
+import asyncio, time
 from crawl4ai import AsyncWebCrawler
 
-async def crawl_typescript_commits():
-    first_commit = ""
-    async def on_execution_started(page):
-        nonlocal first_commit 
-        try:
-            while True:
-                await page.wait_for_selector('li.Box-sc-g0xbh4-0 h4')
-                commit = await page.query_selector('li.Box-sc-g0xbh4-0 h4')
-                commit = await commit.evaluate('(element) => element.textContent')
-                commit = re.sub(r'\s+', '', commit)
-                if commit and commit != first_commit:
-                    first_commit = commit
-                    break
-                await asyncio.sleep(0.5)
-        except Exception as e:
-            print(f"Warning: New content didn't appear after JavaScript execution: {e}")
+async def test_news_crawl():
+    # Create a persistent user data directory
+    user_data_dir = os.path.join(Path.home(), ".crawl4ai", "browser_profile")
+    os.makedirs(user_data_dir, exist_ok=True)
 
-    async with AsyncWebCrawler(verbose=True) as crawler:
-        crawler.crawler_strategy.set_hook('on_execution_started', on_execution_started)
-
-        url = "https://github.com/microsoft/TypeScript/commits/main"
-        session_id = "typescript_commits_session"
-        all_commits = []
-
-        js_next_page = """
-        const button = document.querySelector('a[data-testid="pagination-next-button"]');
-        if (button) button.click();
-        """
-
-        for page in range(3):  # Crawl 3 pages
-            result = await crawler.arun(
-                url=url,
-                session_id=session_id,
-                css_selector="li.Box-sc-g0xbh4-0",
-                js=js_next_page if page > 0 else None,
-                bypass_cache=True,
-                js_only=page > 0
-            )
-
-            assert result.success, f"Failed to crawl page {page + 1}"
-
-            soup = BeautifulSoup(result.cleaned_html, 'html.parser')
-            commits = soup.select("li")
-            all_commits.extend(commits)
-
-            print(f"Page {page + 1}: Found {len(commits)} commits")
-
-        await crawler.crawler_strategy.kill_session(session_id)
-        print(f"Successfully crawled {len(all_commits)} commits across 3 pages")
-
-if __name__ == "__main__":
-    asyncio.run(crawl_typescript_commits())
+    async with AsyncWebCrawler(
+        verbose=True,
+        headless=True,
+        user_data_dir=user_data_dir,
+        use_persistent_context=True,
+        headers={
+            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
+            "Accept-Language": "en-US,en;q=0.5",
+            "Accept-Encoding": "gzip, deflate, br",
+            "DNT": "1",
+            "Connection": "keep-alive",
+            "Upgrade-Insecure-Requests": "1",
+            "Sec-Fetch-Dest": "document",
+            "Sec-Fetch-Mode": "navigate",
+            "Sec-Fetch-Site": "none",
+            "Sec-Fetch-User": "?1",
+            "Cache-Control": "max-age=0",
+        }
+    ) as crawler:
+        url = "ADDRESS_OF_A_CHALLENGING_WEBSITE"
+        
+        result = await crawler.arun(
+            url,
+            cache_mode=CacheMode.BYPASS,
+            magic=True,
+        )
+        
+        print(f"Successfully crawled {url}")
+        print(f"Content length: {len(result.markdown)}")
 ```
 
-This example demonstrates Crawl4AI's ability to handle complex scenarios where content is loaded asynchronously. It crawls multiple pages of GitHub commits, executing JavaScript to load new content and using custom hooks to ensure data is loaded before proceeding.
-
-For more advanced usage examples, check out our [Examples](https://crawl4ai.com/mkdocs/tutorial/episode_12_Session-Based_Crawling_for_Dynamic_Websites/) section in the documentation.
 </details>
 
 
-## Speed Comparison 🚀
+## ✨ Recent Updates   
 
-Crawl4AI is designed with speed as a primary focus. Our goal is to provide the fastest possible response with high-quality data extraction, minimizing abstractions between the data and the user.
+- 🚀 **Improved ManagedBrowser Configuration**: Dynamic host and port support for more flexible browser management.  
+- 📝 **Enhanced Markdown Generation**: New generator class for better formatting and customization.  
+- ⚡ **Fast HTML Formatting**: Significantly optimized HTML formatting in the web crawler.  
+- 🛠️ **Utility & Sanitization Upgrades**: Improved sanitization and expanded utility functions for streamlined workflows.  
+- 👥 **Acknowledgments**: Added contributor details and pull request acknowledgments for better transparency.  
 
-We've conducted a speed comparison between Crawl4AI and Firecrawl, a paid service. The results demonstrate Crawl4AI's superior performance:
 
-```bash
-Firecrawl:
-Time taken: 7.02 seconds
-Content length: 42074 characters
-Images found: 49
-
-Crawl4AI (simple crawl):
-Time taken: 1.60 seconds
-Content length: 18238 characters
-Images found: 49
-
-Crawl4AI (with JavaScript execution):
-Time taken: 4.64 seconds
-Content length: 40869 characters
-Images found: 89
-```
-
-As you can see, Crawl4AI outperforms Firecrawl significantly:
-
-- Simple crawl: Crawl4AI is over 4 times faster than Firecrawl.
-- With JavaScript execution: Even when executing JavaScript to load more content (doubling the number of images found), Crawl4AI is still faster than Firecrawl's simple crawl.
-
-You can find the full comparison code in our repository at `docs/examples/crawl4ai_vs_firecrawl.py`.
-
-## Documentation 📚
+## 📖 Documentation & Roadmap 
 
 For detailed documentation, including installation instructions, advanced features, and API reference, visit our [Documentation Website](https://crawl4ai.com/mkdocs/).
 
-## Crawl4AI Roadmap 🗺️
+Moreover to check our development plans and upcoming features, check out our [Roadmap](https://github.com/unclecode/crawl4ai/blob/main/ROADMAP.md).
 
-For detailed information on our development plans and upcoming features, check out our [Roadmap](https://github.com/unclecode/crawl4ai/blob/main/ROADMAP.md).
+<details>
+<summary>📈 <strong>Development TODOs</strong></summary>
 
-### Advanced Crawling Systems 🔧
 - [x] 0. Graph Crawler: Smart website traversal using graph search algorithms for comprehensive nested page extraction
 - [ ] 1. Question-Based Crawler: Natural language driven web discovery and content extraction
 - [ ] 2. Knowledge-Optimal Crawler: Smart crawling that maximizes knowledge while minimizing data extraction
 - [ ] 3. Agentic Crawler: Autonomous system for complex multi-step crawling operations
-
-### Specialized Features 🛠️
 - [ ] 4. Automated Schema Generator: Convert natural language to extraction schemas
 - [ ] 5. Domain-Specific Scrapers: Pre-configured extractors for common platforms (academic, e-commerce)
 - [ ] 6. Web Embedding Index: Semantic search infrastructure for crawled content
-
-### Development Tools 🔨
 - [ ] 7. Interactive Playground: Web UI for testing, comparing strategies with AI assistance
 - [ ] 8. Performance Monitor: Real-time insights into crawler operations
 - [ ] 9. Cloud Integration: One-click deployment solutions across cloud providers
-
-### Community & Growth 🌱
 - [ ] 10. Sponsorship Program: Structured support system with tiered benefits
 - [ ] 11. Educational Content: "How to Crawl" video series and interactive tutorials
 
-## Contributing 🤝
+</details>
+
+## 🤝 Contributing 
 
 We welcome contributions from the open-source community. Check out our [contribution guidelines](https://github.com/unclecode/crawl4ai/blob/main/CONTRIBUTING.md) for more information.
 
-## License 📄
+## 📄 License 
 
 Crawl4AI is released under the [Apache 2.0 License](https://github.com/unclecode/crawl4ai/blob/main/LICENSE).
 
-## Contact 📧
+## 📧 Contact 
 
 For questions, suggestions, or feedback, feel free to reach out:
 
@@ -508,32 +570,32 @@ For questions, suggestions, or feedback, feel free to reach out:
 
 Happy Crawling! 🕸️🚀
 
+## 🗾 Mission
 
-# Mission
+Our mission is to unlock the value of personal and enterprise data by transforming digital footprints into structured, tradeable assets. Crawl4AI empowers individuals and organizations with open-source tools to extract and structure data, fostering a shared data economy.  
 
-Our mission is to unlock the untapped potential of personal and enterprise data in the digital age. In today's world, individuals and organizations generate vast amounts of valuable digital footprints, yet this data remains largely uncapitalized as a true asset. 
+We envision a future where AI is powered by real human knowledge, ensuring data creators directly benefit from their contributions. By democratizing data and enabling ethical sharing, we are laying the foundation for authentic AI advancement.
 
-Our open-source solution empowers developers and innovators to build tools for data extraction and structuring, laying the foundation for a new era of data ownership. By transforming personal and enterprise data into structured, tradeable assets, we're creating opportunities for individuals to capitalize on their digital footprints and for organizations to unlock the value of their collective knowledge.
+<details>
+<summary>🔑 <strong>Key Opportunities</strong></summary>
+ 
+- **Data Capitalization**: Transform digital footprints into measurable, valuable assets.  
+- **Authentic AI Data**: Provide AI systems with real human insights.  
+- **Shared Economy**: Create a fair data marketplace that benefits data creators.  
 
-This democratization of data represents the first step toward a shared data economy, where willing participation in data sharing drives AI advancement while ensuring the benefits flow back to data creators. Through this approach, we're building a future where AI development is powered by authentic human knowledge rather than synthetic alternatives.
+</details>
 
-![Mission Diagram](./docs/assets/pitch-dark.svg)
+<details>
+<summary>🚀 <strong>Development Pathway</strong></summary>
 
-For a detailed exploration of our vision, opportunities, and pathway forward, please see our [full mission statement](./MISSION.md).
+1. **Open-Source Tools**: Community-driven platforms for transparent data extraction.  
+2. **Digital Asset Structuring**: Tools to organize and value digital knowledge.  
+3. **Ethical Data Marketplace**: A secure, fair platform for exchanging structured data.  
 
-## Key Opportunities
+For more details, see our [full mission statement](./MISSION.md).
+</details>
 
-- **Data Capitalization**: Transform digital footprints into valuable assets that can appear on personal and enterprise balance sheets
-- **Authentic Data**: Unlock the vast reservoir of real human insights and knowledge for AI advancement
-- **Shared Economy**: Create new value streams where data creators directly benefit from their contributions
 
-## Development Pathway
-
-1. **Open-Source Foundation**: Building transparent, community-driven data extraction tools
-2. **Data Capitalization Platform**: Creating tools to structure and value digital assets
-3. **Shared Data Marketplace**: Establishing an economic platform for ethical data exchange
-
-For a detailed exploration of our vision, challenges, and solutions, please see our [full mission statement](./MISSION.md).
 
 
 ## Star History

crawl4ai/__version__.py

@@ -1,2 +1,2 @@
 # crawl4ai/_version.py
-__version__ = "0.3.743"
+__version__ = "0.3.745"

crawl4ai/async_crawler_strategy.py

@@ -15,7 +15,7 @@ import hashlib
 import json
 import uuid
 from .models import AsyncCrawlResponse
-
+from .utils import create_box_message
 from playwright_stealth import StealthConfig, stealth_async
 
 stealth_config = StealthConfig(
@@ -321,10 +321,10 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                         "--disable-infobars",
                         "--window-position=0,0",
                         "--ignore-certificate-errors",
-                        "--ignore-certificate-errors-spki-list",
+                        "--ignore-certificate-errors-spki-list"
                     ]
                 }
-
+                
                 # Add channel if specified (try Chrome first)
                 if self.chrome_channel:
                     browser_args["channel"] = self.chrome_channel
@@ -765,12 +765,15 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                 await self.execute_hook('before_goto', page, context = context)
                 
 
-                response = await page.goto(
-                    url,
-                    # wait_until=kwargs.get("wait_until", ["domcontentloaded", "networkidle"]),
-                    wait_until=kwargs.get("wait_until", "domcontentloaded"),
-                    timeout=kwargs.get("page_timeout", 60000)
-                )
+                try:
+                    response = await page.goto(
+                        url,
+                        # wait_until=kwargs.get("wait_until", ["domcontentloaded", "networkidle"]),
+                        wait_until=kwargs.get("wait_until", "domcontentloaded"),
+                        timeout=kwargs.get("page_timeout", 60000),
+                    )
+                except Error as e:
+                    raise RuntimeError(f"Failed on navigating ACS-GOTO :\n{str(e)}")
                 
                 # response = await page.goto("about:blank")
                 # await page.evaluate(f"window.location.href = '{url}'")

crawl4ai/async_webcrawler.py

@@ -26,8 +26,10 @@ from .utils import (
     sanitize_input_encode,
     InvalidCSSSelectorError,
     format_html,
-    fast_format_html
+    fast_format_html,
+    create_box_message
 )
+
 from urllib.parse import urlparse
 import random
 from .__version__ import __version__ as crawl4ai_version
@@ -326,15 +328,15 @@ class AsyncWebCrawler:
             if not hasattr(e, "msg"):
                 e.msg = str(e)
             # print(f"{Fore.RED}{self.tag_format('ERROR')} {self.log_icons['ERROR']} Failed to crawl {cache_context.display_url[:URL_LOG_SHORTEN_LENGTH]}... | {e.msg}{Style.RESET_ALL}")
+            
             self.logger.error_status(
                 url=cache_context.display_url,
-                error=e.msg,
+                error=create_box_message(e.msg, type = "error"),
                 tag="ERROR"
             )            
             return CrawlResult(
                 url=url, 
                 html="", 
-                markdown=f"[ERROR] 🚫 arun(): Failed to crawl {cache_context.display_url}, error: {e.msg}", 
                 success=False, 
                 error_message=e.msg
             )

crawl4ai/utils.py

@@ -17,7 +17,8 @@ from requests.exceptions import InvalidSchema
 import hashlib
 from typing import Optional, Tuple, Dict, Any
 import xxhash
-
+from colorama import Fore, Style, init
+import textwrap
 
 from .html2text import HTML2Text
 class CustomHTML2Text(HTML2Text):
@@ -103,12 +104,67 @@ class CustomHTML2Text(HTML2Text):
             self.preserved_content.append(data)
             return
         super().handle_data(data, entity_char)
-
-
-
 class InvalidCSSSelectorError(Exception):
     pass
 
+
+def create_box_message(
+   message: str, 
+   type: str = "info", 
+   width: int = 80, 
+   add_newlines: bool = True,
+   double_line: bool = False
+) -> str:
+   init()
+   
+   # Define border and text colors for different types
+   styles = {
+       "warning": (Fore.YELLOW, Fore.LIGHTYELLOW_EX, "⚠"),
+       "info": (Fore.BLUE, Fore.LIGHTBLUE_EX, "ℹ"), 
+       "success": (Fore.GREEN, Fore.LIGHTGREEN_EX, "✓"),
+       "error": (Fore.RED, Fore.LIGHTRED_EX, "×"),
+   }
+   
+   border_color, text_color, prefix = styles.get(type.lower(), styles["info"])
+   
+   # Define box characters based on line style
+   box_chars = {
+       "single": ("─", "│", "┌", "┐", "└", "┘"),
+       "double": ("═", "║", "╔", "╗", "╚", "╝")
+   }
+   line_style = "double" if double_line else "single"
+   h_line, v_line, tl, tr, bl, br = box_chars[line_style]
+   
+   # Process lines with lighter text color
+   formatted_lines = []
+   raw_lines = message.split('\n')
+   
+   if raw_lines:
+       first_line = f"{prefix} {raw_lines[0].strip()}"
+       wrapped_first = textwrap.fill(first_line, width=width-4)
+       formatted_lines.extend(wrapped_first.split('\n'))
+       
+       for line in raw_lines[1:]:
+           if line.strip():
+               wrapped = textwrap.fill(f"  {line.strip()}", width=width-4)
+               formatted_lines.extend(wrapped.split('\n'))
+           else:
+               formatted_lines.append("")
+   
+   # Create the box with colored borders and lighter text
+   horizontal_line = h_line * (width - 1)
+   box = [
+       f"{border_color}{tl}{horizontal_line}{tr}",
+       *[f"{border_color}{v_line}{text_color} {line:<{width-2}}{border_color}{v_line}" for line in formatted_lines],
+       f"{border_color}{bl}{horizontal_line}{br}{Style.RESET_ALL}"
+   ]
+   
+   result = "\n".join(box)
+   if add_newlines:
+       result = f"\n{result}\n"
+   
+   return result
+
 def calculate_semaphore_count():
     cpu_count = os.cpu_count()
     memory_gb = get_system_memory() / (1024 ** 3)  # Convert to GB

docs/examples/quickstart_async.py

@@ -13,7 +13,9 @@ import re
 from typing import Dict, List
 from bs4 import BeautifulSoup
 from pydantic import BaseModel, Field
-from crawl4ai import AsyncWebCrawler
+from crawl4ai import AsyncWebCrawler, CacheMode
+from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
+from crawl4ai.content_filter_strategy import BM25ContentFilter
 from crawl4ai.extraction_strategy import (
     JsonCssExtractionStrategy,
     LLMExtractionStrategy,
@@ -51,7 +53,7 @@ async def simple_example_with_running_js_code():
             url="https://www.nbcnews.com/business",
             js_code=js_code,
             # wait_for=wait_for,
-            bypass_cache=True,
+            cache_mode=CacheMode.BYPASS,
         )
         print(result.markdown[:500])  # Print first 500 characters
 
@@ -61,7 +63,7 @@ async def simple_example_with_css_selector():
         result = await crawler.arun(
             url="https://www.nbcnews.com/business",
             css_selector=".wide-tease-item__description",
-            bypass_cache=True,
+            cache_mode=CacheMode.BYPASS,
         )
         print(result.markdown[:500])  # Print first 500 characters
 
@@ -132,7 +134,7 @@ async def extract_structured_data_using_llm(provider: str, api_token: str = None
                 {"model_name": "GPT-4", "input_fee": "US$10.00 / 1M tokens", "output_fee": "US$30.00 / 1M tokens"}.""",
                 extra_args=extra_args
             ),
-            bypass_cache=True,
+            cache_mode=CacheMode.BYPASS,
         )
         print(result.extracted_content)
 
@@ -166,7 +168,7 @@ async def extract_structured_data_using_css_extractor():
         result = await crawler.arun(
             url="https://www.coinbase.com/explore",
             extraction_strategy=extraction_strategy,
-            bypass_cache=True,
+            cache_mode=CacheMode.BYPASS,
         )
 
         assert result.success, "Failed to crawl the page"
@@ -213,7 +215,7 @@ async def crawl_dynamic_content_pages_method_1():
                 session_id=session_id,
                 css_selector="li.Box-sc-g0xbh4-0",
                 js=js_next_page if page > 0 else None,
-                bypass_cache=True,
+                cache_mode=CacheMode.BYPASS,
                 js_only=page > 0,
                 headless=False,
             )
@@ -282,7 +284,7 @@ async def crawl_dynamic_content_pages_method_2():
                 extraction_strategy=extraction_strategy,
                 js_code=js_next_page_and_wait if page > 0 else None,
                 js_only=page > 0,
-                bypass_cache=True,
+                cache_mode=CacheMode.BYPASS,
                 headless=False,
             )
 
@@ -343,7 +345,7 @@ async def crawl_dynamic_content_pages_method_3():
                 js_code=js_next_page if page > 0 else None,
                 wait_for=wait_for if page > 0 else None,
                 js_only=page > 0,
-                bypass_cache=True,
+                cache_mode=CacheMode.BYPASS,
                 headless=False,
             )
 
@@ -384,7 +386,7 @@ async def crawl_with_user_simultion():
         url = "YOUR-URL-HERE"
         result = await crawler.arun(
             url=url,            
-            bypass_cache=True,
+            cache_mode=CacheMode.BYPASS,
             magic = True, # Automatically detects and removes overlays, popups, and other elements that block content
             # simulate_user = True,# Causes a series of random mouse movements and clicks to simulate user interaction
             # override_navigator = True # Overrides the navigator object to make it look like a real user
@@ -408,7 +410,7 @@ async def speed_comparison():
     params={'formats': ['markdown', 'html']}
     )
     end = time.time()
-    print("Firecrawl (simulated):")
+    print("Firecrawl:")
     print(f"Time taken: {end - start:.2f} seconds")
     print(f"Content length: {len(scrape_status['markdown'])} characters")
     print(f"Images found: {scrape_status['markdown'].count('cldnry.s-nbcnews.com')}")
@@ -420,7 +422,7 @@ async def speed_comparison():
         result = await crawler.arun(
             url="https://www.nbcnews.com/business",
             word_count_threshold=0,
-            bypass_cache=True,
+            cache_mode=CacheMode.BYPASS,
             verbose=False,
         )
         end = time.time()
@@ -430,6 +432,25 @@ async def speed_comparison():
         print(f"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}")
         print()
 
+        # Crawl4AI with advanced content filtering
+        start = time.time()
+        result = await crawler.arun(
+            url="https://www.nbcnews.com/business",
+            word_count_threshold=0,
+            markdown_generator=DefaultMarkdownGenerator(
+                content_filter=BM25ContentFilter(user_query=None, bm25_threshold=1.0)
+            ),
+            cache_mode=CacheMode.BYPASS,
+            verbose=False,
+        )
+        end = time.time()
+        print("Crawl4AI (Markdown Plus):")
+        print(f"Time taken: {end - start:.2f} seconds")
+        print(f"Content length: {len(result.markdown_v2.raw_markdown)} characters")
+        print(f"Fit Markdown: {len(result.markdown_v2.fit_markdown)} characters")
+        print(f"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}")
+        print()
+
         # Crawl4AI with JavaScript execution
         start = time.time()
         result = await crawler.arun(
@@ -438,13 +459,17 @@ async def speed_comparison():
                 "const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();"
             ],
             word_count_threshold=0,
-            bypass_cache=True,
+            cache_mode=CacheMode.BYPASS,
+            markdown_generator=DefaultMarkdownGenerator(
+                content_filter=BM25ContentFilter(user_query=None, bm25_threshold=1.0)
+            ),
             verbose=False,
         )
         end = time.time()
         print("Crawl4AI (with JavaScript execution):")
         print(f"Time taken: {end - start:.2f} seconds")
         print(f"Content length: {len(result.markdown)} characters")
+        print(f"Fit Markdown: {len(result.markdown_v2.fit_markdown)} characters")
         print(f"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}")
 
     print("\nNote on Speed Comparison:")
@@ -483,7 +508,7 @@ async def generate_knowledge_graph():
         url = "https://paulgraham.com/love.html"
         result = await crawler.arun(
             url=url,
-            bypass_cache=True,
+            cache_mode=CacheMode.BYPASS,
             extraction_strategy=extraction_strategy,
             # magic=True
         )
@@ -496,7 +521,7 @@ async def fit_markdown_remove_overlay():
         url = "https://janineintheworld.com/places-to-visit-in-central-mexico"
         result = await crawler.arun(
             url=url,
-            bypass_cache=True,
+            cache_mode=CacheMode.BYPASS,
             word_count_threshold = 10,
             remove_overlay_elements=True,
             screenshot = True
@@ -517,10 +542,10 @@ async def main():
     await extract_structured_data_using_css_extractor()
 
     # LLM extraction examples
-    await extract_structured_data_using_llm()
-    await extract_structured_data_using_llm("huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct", os.getenv("HUGGINGFACE_API_KEY"))
+    # await extract_structured_data_using_llm()
+    # await extract_structured_data_using_llm("huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct", os.getenv("HUGGINGFACE_API_KEY"))
+    # await extract_structured_data_using_llm("ollama/llama3.2")    
     await extract_structured_data_using_llm("openai/gpt-4o", os.getenv("OPENAI_API_KEY"))
-    await extract_structured_data_using_llm("ollama/llama3.2")    
 
     # You always can pass custom headers to the extraction strategy
     custom_headers = {

requirements.txt

@@ -1,16 +1,16 @@
 aiosqlite~=0.20
 html2text~=2024.2
 lxml~=5.3
-litellm~=1.48
+litellm>=1.53.1
 numpy>=1.26.0,<3
 pillow~=10.4
-playwright>=1.47,<1.48
+playwright>=1.49.0
 python-dotenv~=1.0
 requests~=2.26
 beautifulsoup4~=4.12
-tf-playwright-stealth~=1.0
+tf-playwright-stealth>=1.1.0
 xxhash~=3.4
 rank-bm25~=0.2
-aiofiles~=24.0
+aiofiles>=24.1.0
 colorama~=0.4
 snowballstemmer~=2.2

setup.py

@@ -9,10 +9,17 @@ import asyncio
 
 # Create the .crawl4ai folder in the user's home directory if it doesn't exist
 # If the folder already exists, remove the cache folder
-crawl4ai_folder = os.getenv("CRAWL4_AI_BASE_DIRECTORY", Path.home()) / ".crawl4ai"
+base_dir = os.getenv("CRAWL4_AI_BASE_DIRECTORY")
+crawl4ai_folder = Path(base_dir) if base_dir else Path.home()
+crawl4ai_folder = crawl4ai_folder / ".crawl4ai"
 cache_folder = crawl4ai_folder / "cache"
-content_folders = ['html_content', 'cleaned_html', 'markdown_content', 
-                  'extracted_content', 'screenshots']
+content_folders = [
+    "html_content",
+    "cleaned_html",
+    "markdown_content",
+    "extracted_content",
+    "screenshots",
+]
 
 # Clean up old cache if exists
 if cache_folder.exists():
@@ -28,7 +35,7 @@ for folder in content_folders:
 __location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
 with open(os.path.join(__location__, "requirements.txt")) as f:
     requirements = f.read().splitlines()
-    
+
 with open("crawl4ai/__version__.py") as f:
     for line in f:
         if line.startswith("__version__"):
@@ -37,11 +44,12 @@ with open("crawl4ai/__version__.py") as f:
 
 # Define requirements
 default_requirements = requirements
-torch_requirements = ["torch", "nltk",  "scikit-learn"]
+torch_requirements = ["torch", "nltk", "scikit-learn"]
 transformer_requirements = ["transformers", "tokenizers"]
-cosine_similarity_requirements = ["torch", "transformers", "nltk" ]
+cosine_similarity_requirements = ["torch", "transformers", "nltk"]
 sync_requirements = ["selenium"]
 
+
 def install_playwright():
     print("Installing Playwright browsers...")
     try:
@@ -49,16 +57,22 @@ def install_playwright():
         print("Playwright installation completed successfully.")
     except subprocess.CalledProcessError as e:
         print(f"Error during Playwright installation: {e}")
-        print("Please run 'python -m playwright install' manually after the installation.")
+        print(
+            "Please run 'python -m playwright install' manually after the installation."
+        )
     except Exception as e:
         print(f"Unexpected error during Playwright installation: {e}")
-        print("Please run 'python -m playwright install' manually after the installation.")
+        print(
+            "Please run 'python -m playwright install' manually after the installation."
+        )
+
 
 def run_migration():
     """Initialize database during installation"""
     try:
         print("Starting database initialization...")
         from crawl4ai.async_database import async_db_manager
+
         asyncio.run(async_db_manager.initialize())
         print("Database initialization completed successfully.")
     except ImportError:
@@ -67,12 +81,14 @@ def run_migration():
         print(f"Warning: Database initialization failed: {e}")
         print("Database will be initialized on first use")
 
+
 class PostInstallCommand(install):
     def run(self):
         install.run(self)
         install_playwright()
         # run_migration()
 
+
 setup(
     name="Crawl4AI",
     version=version,
@@ -84,18 +100,23 @@ setup(
     author_email="unclecode@kidocode.com",
     license="MIT",
     packages=find_packages(),
-    install_requires=default_requirements + ["playwright", "aiofiles"],  # Added aiofiles
+    install_requires=default_requirements
+    + ["playwright", "aiofiles"],  # Added aiofiles
     extras_require={
         "torch": torch_requirements,
         "transformer": transformer_requirements,
         "cosine": cosine_similarity_requirements,
         "sync": sync_requirements,
-        "all": default_requirements + torch_requirements + transformer_requirements + cosine_similarity_requirements + sync_requirements,
+        "all": default_requirements
+        + torch_requirements
+        + transformer_requirements
+        + cosine_similarity_requirements
+        + sync_requirements,
     },
     entry_points={
-        'console_scripts': [
-            'crawl4ai-download-models=crawl4ai.model_loader:main',
-            'crawl4ai-migrate=crawl4ai.migrations:main',  # Added migration command
+        "console_scripts": [
+            "crawl4ai-download-models=crawl4ai.model_loader:main",
+            "crawl4ai-migrate=crawl4ai.migrations:main",  # Added migration command
         ],
     },
     classifiers=[
@@ -110,6 +131,6 @@ setup(
     ],
     python_requires=">=3.7",
     cmdclass={
-        'install': PostInstallCommand,
+        "install": PostInstallCommand,
     },
-)
+)