OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

LLM Scraper

LLM Scraper is an open-source TypeScript library that uses language models and Playwright browser automation to extract schema-defined structured data from webpages. Developers can define output with Zod or JSON Schema and choose among HTML, raw HTML, Markdown, extracted text, screenshot, or custom-content input formats. It also supports streaming partial objects and generating reusable Playwright extraction code.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

LLM Scraper — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an application needs to visit a webpage with Playwright and convert its content into a developer-defined structured result using a language model.

Who it is for

  • TypeScript developers building webpage data extraction into applications or tools.
  • Teams that need model-produced webpage records constrained by a Zod or JSON Schema definition.
  • Developers creating browser-assisted collection workflows or streaming extraction interfaces.

Documented uses

  • Extract typed records such as titles, scores, authors and URLs from a webpage.
  • Convert page content into JSON-schema-shaped output for use in an application.
  • Stream partial structured results or generate reusable Playwright extraction code.
Before you choose

Requirements & limits

The project is available as a public GitHub repository under the MIT license.

  • The library requires an application-side setup involving Playwright and a configured language-model provider.
  • Output can be defined with either Zod or JSON Schema.
  • Input format options include processed HTML, raw HTML, Markdown, extracted text, multimodal screenshots and custom content.
  • Streaming partial objects and code generation are documented capabilities.
  • The repository describes support for Vercel AI SDK 6; individual provider integration details are not specified for every provider.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up LLM Scraper with a model provider

Install the library dependencies, configure a documented model provider and initialize an LLM Scraper instance.

Before you start

  • Node.js/npm environment
  • Playwright
  • An LLM provider integration, such as the documented OpenAI, Anthropic, Google, Groq or Ollama option

Steps

  1. Install the documented dependencies: npm i zod playwright llm-scraper.

  2. Install the package for the selected provider; for example, npm i @ai-sdk/openai for OpenAI.

  3. Initialize the provider model in code, following the provider-specific example.

  4. Import LLMScraper and create an instance with the initialized model.

Expected outcome

A scraper instance initialized with a language model and ready for the later page-and-schema workflow.

Guide limitations

  • This guide covers setup only; it does not establish that a particular environment or provider configuration will run successfully.
  • Page navigation, schema definition and extraction are a subsequent workflow stage.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
mishushakov/llm-scraper · Official homepage title · retained in its source language
How we review sourcesSuggest a correction