# mishushakov/llm-scraper

Turn any webpage into structured data using LLMs

Repository: https://github.com/mishushakov/llm-scraper
Canonical: https://ross.abutalabs.com/products/llm-scraper
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, browser, gpt, langchain, llm, openai, scraper, browser-automation, playwright, puppeteer, llama, artificial-intelligence, gpt-4
Last push: 2026-08-02T02:49:24+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 35, longevity 61
- inputs: {"age_days": 865, "days_push": 31, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6915, forks 453 (observed 2026-08-28T04:09:51.348805+00:00)

## What it is
A TypeScript library that turns any webpage into structured data using LLMs, built on Playwright and the Vercel AI SDK. It supports multiple LLM providers, Zod/JSON Schema definitions, streaming, and several page formatting modes including HTML, markdown, text, and screenshots.

## Use cases
- extract structured data from webpages with an LLM
- scrape product listings into typed JSON objects
- parse news headlines from a site using GPT-4o
- convert HTML pages to markdown or text for LLM input
- generate scraping code from a schema
- stream structured extraction results from a live page

## When to choose
- you need schema-validated structured extraction from web pages
- you want type-safe scraping with Zod schemas in TypeScript
- you need multi-modal extraction including page screenshots
- you want to swap between OpenAI, Anthropic, Google, Groq, or Ollama providers

## When to avoid
- you need high-volume scraping without LLM API costs
- you only need simple static HTML parsing without AI
- your project is not in the Node.js/TypeScript ecosystem
- you need a no-code scraping service with a UI

## Facets
- artifact type: library
- maturity: active
- function: web-scraping, llm-inference, parser, rag
- domain: artificial-intelligence, large-language-models, crawlers, web-development, developer-tools
- platform: cross-platform
- tags: playwright, puppeteer, zod, vercel-ai-sdk, structured-extraction, browser-automation, schema-validation, nodejs, typescript

## Member repositories
- mishushakov/llm-scraper (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:51.348805+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:41:27.553285+00:00, confidence not recorded.
  - readme: https://github.com/mishushakov/llm-scraper (fetched 2026-08-28T04:09:51.348805+00:00, sha 77b6bd03c255)
  - registry_npm: https://registry.npmjs.org/llm-scraper (fetched 2026-08-29T08:37:31.427806+00:00, sha 4845c19280d9)
- Data as of 2026-08-30T08:39:29.467469+00:00.