whereismyai
LLM Scraper
LLM Scraper is a TypeScript library that extracts structured data from any webpage using large language models.
LLM Scraper is a TypeScript library that allows you to extract structured data from any webpage using large language models. It is built on the Playwright framework and supports defining schemas with Zod or JSON Schema to ensure full type-safety. The tool supports multiple model series including GPT, Sonnet, Gemini, Llama, and Qwen, with integrations for OpenAI, Anthropic, Google, Groq, and Ollama. It offers six formatting modes: html, rawhtml, markdown, text, image, and custom. Additional capabilities include streaming objects and code-generation to produce reusable Playwright scripts.
LLM Scraper at a glance
Key features
- Extracts structured data using LLMs
- Supports GPT, Sonnet, Gemini, Llama, and Qwen models
- Defines schemas with Zod or JSON Schema
- Provides full type-safety with TypeScript
- Uses the Playwright framework
- Streams partial objects
- Generates reusable Playwright scripts
- Includes six formatting modes for content loading
Use it for
- Extracting top stories from HackerNews
- Scraping webpage contents according to a schema
- Streaming partial structured data objects
Alternatives to LLM Scraper
- AnyCrawl — Provides clean, structured, and LLM-ready data from any website.
- Scrape Anything by Context.dev — Extracts clean Markdown, HTML, and structured data with built-in proxies and JS rendering.
- ScrapeGraphAI — Extracts structured data via natural language prompts with no selectors or proxies.
- LLM CLI — It enables command-line interaction with remote APIs and local machine models.
- Markdownee — Extracts main web content cleanly using Trafilatura Core and Crawlee.
- Huntsman — It runs fast and light on a single Go binary and container without Redis or Playwright.
- Pagesift — Extracts web data with high memory efficiency and speed for AI agents.
- Crawlee — Handles blocking, crawling, proxies, and browsers for JavaScript and Python.
- Crawl4AI — Turns any URL into clean Markdown or typed JSON for AI models.
- Firecrawl — Provides direct web data access for AI agents with open source flexibility.
- Jina — It provides reliable reader and search APIs optimized for LLMs and RAG systems.
- jurl — Extracts exact page content without rewriting or hallucinating answers.
All LLM Scraper alternatives