Extract schema-shaped JSON from JavaScript-rendered pages with llm-scraper
Open a rendered page, describe the fields you want, and return structured data without hand-maintaining brittle selectors.
Prerequisites
Node.js, Playwright-compatible browser runtime, llm-scraper package, supported LLM provider credentials, target URLs
Installation
Use the upstream install or setup path that matches your environment:
- npm i zod playwright llm-scraper
- npm i @ai-sdk/openai
- npm i @ai-sdk/anthropic
- npm i @ai-sdk/google
Basic usage or getting-started notes:
Install the required dependencies from npm:
Initialize your LLM:
OpenAI
Extracted from upstream docs: https://raw.githubusercontent.com/mishushakov/llm-scraper/HEAD/README.md