github.com · Software & Apps
Rare Pick

llm-scraper

Visit site
llm-scraper

About

llm-scraper is a Python library designed for extracting structured data from web pages using large language models (LLMs). It allows developers to define a schema for the desired data, and the library then leverages LLMs to parse and extract information from HTML content according to that schema.

This tool is intended for software developers, data scientists, and researchers who need to automate web data extraction tasks, particularly from websites with complex or inconsistent structures where traditional scraping methods might be challenging. It simplifies the process of transforming unstructured web content into usable, structured data.

His flagship open-source project (~6.9k stars): turn any webpage into structured data with LLMs, built on Playwright, Zod and the Vercel AI SDK.· Mish Ushakov

More from Mish Ushakov

See all
Rare Picke2b.dev
E2B

E2B

Rare Picke2b.dev
Fragments by E2B

Fragments by E2B

Softwareclaude.com
Claude Code

Claude Code

Softwarecursor.com
Cursor

Cursor

Rare Pickstepci.com
Step CI

Step CI

Rare Pickgarph.dev
garph

garph

More in Software & Apps

See all
Rare Pick
PitchDeck

PitchDeck

Rare Pickmysql.com
MySQL

MySQL

Rare Pickjan.ai
Jan

Jan

Rare Picknikke-en.com
NIKKE: Goddess of Victory

NIKKE: Goddess of Victory

Softwarecarrd.co
Carrd

Carrd

Rare Pickbing.com
Bing Webmaster Tools

Bing Webmaster Tools