README.md

RAG Docs

A Python application for crawling and scraping documentation using Firecrawl API.

Features

• Crawls websites and follows child links
• Converts scraped content to markdown format
• Saves documentation files with sanitized filenames
• Handles duplicate filenames automatically

Requirements

• Python 3.x
• Firecrawl API key

Installation

pip install firecrawl-py

Usage

1. Set your Firecrawl API key (recommended: use environment variables)
2. Update the url and max_pages variables in firecrawlbasics.py
3. Run the script:

python firecrawlbasics.py

Configuration

The script can be configured by modifying variables in firecrawlbasics.py:

• url: The starting URL to crawl
• max_pages: Maximum number of pages to crawl
• output_folder: Folder to save markdown files
• include_paths: Path filters for crawling
• exclude_paths: Paths to exclude from crawling

Security Note

⚠️ Important: Move your Firecrawl API key to an environment variable instead of hardcoding it in the script.

License

[Add your license here]