Llm-Scraper

Visit Tool

llm-scraper is a TypeScript library that extracts structured data from any webpage using LLMs. It supports various models and allows schema definition with Zod or JSON Schema for type-safe data extraction.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is llm-scraper?

llm-scraper is a powerful TypeScript library designed to transform unstructured web content into structured data using Large Language Models (LLMs). It offers broad compatibility, supporting popular LLM series such as GPT, Sonnet, Gemini, Llama, and Qwen. Developers can define data schemas using either Zod or JSON Schema, ensuring full type-safety within TypeScript projects. Built on the Playwright framework, llm-scraper facilitates robust browser automation and supports streaming objects for real-time data processing. It also includes code-generation capabilities and offers six distinct formatting modes, including HTML, raw HTML, Markdown, text, image screenshots, and custom content loading, providing flexibility for diverse scraping needs.

Best used for

Ideal for developers who need to programmatically extract structured data from websites, automate content collection for analysis, and integrate LLM-powered scraping into their applications. Especially valuable for those requiring type-safe data definitions and flexible content formatting options.

Common actions

scrape web data

extract structured information

automate web content

integrate LLMs for scraping

"AI Agents"github copilotautomated workflowface swappinglow-code/no-codedeepfakecollaborationworkflowsopen-source

Capabilities

Key features

Extract structured data
Supports multiple LLMs
Zod/JSON Schema support
Playwright framework
Streaming objects
Code-generation
6 formatting modes

Target Audience

developerdata scientist

Integrations

openaianthropicgooglegroqollama

Pricing & Plans

Open Source

Free

FAQs

Which LLM models does llm-scraper support?

llm-scraper supports a wide range of LLM models, including those from the GPT, Sonnet, Gemini, Llama, and Qwen series. It integrates with popular AI SDKs like OpenAI, Anthropic, Google, and Groq, as well as Ollama for local models.

How does llm-scraper ensure type-safety for extracted data?

llm-scraper ensures full type-safety by allowing users to define data schemas using either Zod or JSON Schema. This integration with TypeScript helps developers maintain data integrity and predictability when working with scraped content.

Can llm-scraper generate code for Playwright scripts?

Yes, llm-scraper can generate reusable Playwright scripts. Using its `generate` function, you can create code that scrapes content according to a defined schema, which can then be executed directly on a page to retrieve structured data.

Trending

Subcategories trending in Data & Analytics

Business Intelligence Predictive Analytics Data Labeling & Annotation Real-Time Analytics Market Research Data Cleaning & Prep

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce