Show HN: Docs-to-Markdown – Convert Documentation URLs into Markdown

2 points

a year ago

Hey HN! I built *docs-to-markdown*, a CLI tool that automatically crawls a website’s documentation and converts it into organized Markdown files—handy for quickly feeding docs into LLMs.

*Key Features:* - *Flexible Conversion:* Grab docs as one single file or multiple files reflecting the site’s structure. - *LLM-Optimized:* Includes an optional GPT-4 filtering step for cleaning up the text. - *Easy Setup:* `pip install docs-to-markdown`, then run a single command.

*Quick Example:* ```bash pip install docs-to-markdown

docs-to-markdown https://example.com/docs --doc_name example_doc # Generates a folder 'example_doc' with one or more Markdown files ```

For filtering with GPT-4, just add `--llm-filtering` (requires an OpenAI key).

*Repo & More Info:* [GitHub – fdagostino/docs-to-markdown](https://github.com/fdagostino/docs-to-markdown)

I’d love any feedback! Let me know what you think, or open an issue if you find any bugs or have feature requests.