Dicklesworthstone/markdown_web_browser

Renders any URL via headless Chrome, tiles screenshots into OCR slices, and streams structured Markdown + provenance back to AI agents and pipelines

52
/ 100
Established

This project helps you turn any website into a clean, easy-to-read Markdown document, even if the site normally blocks data extraction. You provide a web address, and it gives you a structured text version of the page, including financial data, news, or complex dashboards. It's designed for researchers, analysts, or anyone who needs to quickly capture and understand web content without distractions.

139 stars.

Use this if you need to extract structured information from complex or bot-protected websites like financial dashboards or news sites for research, content analysis, or compliance purposes.

Not ideal if you only need basic text extraction from simple, unprotected websites, as its advanced features might be overkill.

market-intelligence web-research compliance-archiving data-extraction competitor-monitoring
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 13 / 25
Community 19 / 25

How are scores calculated?

Stars

139

Forks

26

Language

Python

License

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/Dicklesworthstone/markdown_web_browser"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.