Python scraper based on AI
ScrapeGraphAI is a Python library that uses language models and graph-based pipelines to extract requested information from websites and local documents. Developers use it to build scrapers for sources such as HTML, XML, JSON, and Markdown files. The catalogue includes an instruction for working with the library.
Latest release v2.3.1 · 6 Oct 2026
1 file for Codex and OpenCode: Scrapegraph-ai AGENTS.md — 1,314 tokens loaded in every session.
AGENTS.md A 1,314 tok These files are ScrapeGraphAI/Scrapegraph-ai's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.