← all repositories

scraperai/scraperai

AI-powered web scraping tool that uses LLMs to extract data and generate reusable scraping configurations.

414 stars HTML Data Tooling
scraperai
Not currently ranked — collecting fresh signals.
star history

ScraperAI is an open-source web scraping tool that leverages Large Language Models like ChatGPT to extract structured data from web pages. It provides automatic detection of page types, XPATHs, pagination patterns, and generates reusable scraping recipes. The tool supports custom LLMs through LangChain integration and can work with Selenium for dynamic content.

Frequently asked

What is scraperai/scraperai?
AI-powered web scraping tool that uses LLMs to extract data and generate reusable scraping configurations.
Is scraperai open source?
Yes — scraperai/scraperai is open source, released under the GPL-3.0 license.
What language is scraperai written in?
scraperai/scraperai is primarily written in HTML.
How popular is scraperai?
scraperai/scraperai has 414 stars on GitHub.
Where can I find scraperai?
scraperai/scraperai is on GitHub at https://github.com/scraperai/scraperai.

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.