llm-scraper
LLM Scraper is a TypeScript library that uses large language models to obtain structured data from web pages. Based on the Playwright infrastructure, the vehicle supports the GPT, Sonnet, Gemini, Llama and Qwen model series. Using Zod or JSON Schema, it allows to define schema and provide a full type-safe.
mishushakov · Local AI / Self-Hosted LLM
Common commercial products in this category: ChatGPT, Claude, Gemini
- You can convert content from web pages into structured data using Zod or JSON Schema.
- You can shoot data using six different formatting modes, such as HTML, markdown, raw text, or screenshot.
- You can perform object flow (streaming objects) with the GPT, Sonnet, Gemini, Llama and Qwen model series.
- • No published release
- • NeutralGitHub Issue
The example code, doesn't work (hacker news articles)
“Hi, i tried the example code to see if the scraper works but it always return a validation error for attribute `top` which is supposed ton be an array. here are my example code, a bit tweaked to use local ollama : ```javascript import { chromium } from 'playwright' import { z }…”
- • NeutralGitHub Issue
Use LLM without Playwright
“Thanks for this, it's really good! is there a way to send raw html of a page instead of using playwright to scrape a page and ask the llm to extract the content?”