A Python tool to scrape website content for LLM context.
pip install doc-scraperThis tool uses crawl4ai which relies on Playwright. After installing the package, you need to install the browser binaries:
playwright installOr if you are using the crawl4ai CLI directly:
crawl4ai-doctordoc-scraper <url>Example:
doc-scraper https://docs.reducto.ai/Follow the interactive prompts to configure the output directory and other settings.