Developers wanting to extract structured data from websites and documents using natural language prompts.

ScrapeGraphAI is a Python library that uses LLMs and graph based pipelines to scrape and extract information from web pages and local documents.

Used as a Python library, with scraping pipelines like SmartScraperGraph and SearchGraph run locally or integrated into LangChain and n8n.

Released around 2024 and actively maintained with regular commits as of 2026.

Lets users describe what data they want in plain language instead of writing brittle CSS or XPath selectors.

Depends on an LLM provider such as OpenAI, Groq, Gemini, or a local Ollama model to drive extraction.

Open source under MIT; runs locally as a library but sends page content to whichever LLM provider is configured, which may be a third party API.