GH Repository · mishushakov
llm-scraper
Turn any webpage into structured data using LLMs
- stars
- 6,932
- 30-day movement
- starts with the next reading
- Related entries
- 60
- Connections
- 1
typescriptnodeagent-frameworkTypeScriptaillmbrowsergptlangchainopenaiscraperpuppeteerbrowser-automationplaywrightllamaartificial-intelligencegpt-4
llm-scraper is a TypeScript library that uses LLMs to turn webpage content into structured data. It builds on browser automation tools like Playwright and Puppeteer and works with LLM providers such as OpenAI and local Llama models.
Use it when you need to extract structured information from web pages without writing brittle per-site scraping rules.
Use it to
- Extract structured data from webpages via LLMs
- Automate browser scraping with Playwright or Puppeteer
- Combine scraping with LangChain workflows
- Run extraction against OpenAI or Llama models
For Developers building LLM-based scraping or data extraction pipelines
- Role
- agent-framework
- Language
- TypeScript
- Licence
- MIT
- Forks
- 454
- Open issues
- 3
- Last push
- 2026-09-10
topicsweb-scrapingllmbrowser-automationplaywrightopenaitypescript