obeone/crawler-to-md

Convert web content to Markdown & JSON files to fuel your GPTs !

46
/ 100
Emerging

This tool helps you gather information from websites by converting their content into structured Markdown and JSON files. You input a list of website addresses or a starting URL, and it produces ready-to-use files that capture the text and metadata from those pages. It's designed for anyone who needs to collect web content for AI model training, data analysis, or building custom GPTs.

Available on PyPI.

Use this if you need to quickly and easily collect web page content into a structured format for AI training, analysis, or uploading to GPT models.

Not ideal if you need a sophisticated web automation tool for complex interactions, form filling, or bypassing advanced anti-scraping measures.

web-content-collection ai-data-preparation knowledge-base-building content-curation custom-gpt-data
No License
Maintenance 6 / 25
Adoption 7 / 25
Maturity 17 / 25
Community 16 / 25

How are scores calculated?

Stars

26

Forks

6

Language

Python

License

Last pushed

Nov 19, 2025

Commits (30d)

0

Dependencies

11

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/obeone/crawler-to-md"

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