jamesturk/scrapeghost

👻 Experimental library for scraping websites using OpenAI's GPT API.

52
/ 100
Established

This tool helped developers extract specific data from websites using AI. You would define the structure of the information you needed (like a list of product names and prices), feed it a webpage, and it would output that data in a clean, structured format. It was built for programmers who wanted to leverage large language models for web scraping tasks.

1,444 stars.

Use this if you are a developer looking for an experimental way to extract structured data from web pages using an LLM, and are comfortable with potentially high API costs.

Not ideal if you are looking for a maintained, cost-effective, or non-developer-centric solution for web scraping.

web-scraping data-extraction developer-tool AI-powered-scraping
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

1,444

Forks

88

Language

Python

License

Last pushed

Jan 14, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/jamesturk/scrapeghost"

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