Scrapegraph-ai

Python scraper based on AI

★ 31,491 stars, verified 2026-10-02Category: Search / Scraping / Data InfraGitHub repository ↗

Python scraper based on AI

Search engines, scrapers, and data infrastructure for AI pipelines.

Key features

Good for

Stack & tags

PythonLangChainLlamaIndexMCPPyPIai-crawlerai-scrapingai-searchcrawlerdata-extractionfirecrawl-alternativelarge-language-modelllm

Quick start

pip install scrapegraphai

From the project README on GitHub.

Similar open-source projects

yt-dlp

★ 194,511

The video downloader — essential for creators and researchers, top-tier star count

Search / Scraping / Data InfraGitHub ↗

Firecrawl

★ 186,985

Turn the web into LLM-ready data — AI crawler/search API, self-hostable

Search / Scraping / Data InfraGitHub ↗