All open source
Open SourceScraping27k

ScrapeGraphAI

LLM-powered scraper that builds graph pipelines from a plain prompt.

ScrapeGraphAI is a Python web scraping library that uses LLMs and a graph-based pipeline to extract structured data from websites based on natural-language prompts. Instead of writing CSS or XPath selectors, users describe what data they want and the library builds the extraction logic. It is notable for combining LLM reasoning with scraping to produce schema-conforming output.

Repository

ScrapeGraphAI/Scrapegraph-ai

Language

Python

What you'd build with it

  • Extracting structured data from pages by describing the desired fields in plain language
  • Building scrapers that adapt to varied page layouts without hand-written selectors
  • Producing JSON/schema-conforming output directly for downstream pipelines

Tags

ai-scrapergraphllm