Web-scraping Packages

MCP server for JinaAI reader

A module for downloading TikTok videos by the URL

Plugin for browser actions and web scraping

A powerful NestJS HTML parsing service with XPath and CSS selector support, proxy configuration, random user agents, and rich response metadata including headers and status codes

Web data extraction can be effectively performed using CSS selectors.

Pure MCP Server for Jina.AI Advanced web scraping

High-performance, configurable, batch-generating User-Agent spoofing library. Supports multiple browsers, devices, and returns detailed meta information. Perfect for web scraping, automated testing, proxy pools and more.

A simple yet powerful module to retrieve organic search results and much more from Google.

IMDb scraper for extracting movie reviews from IMDb pages.

movietorrent scraper for extracting movie news from all pages.

A typescript wrapper around cURL-impersonate.

A minimal TypeScript library for fetching and parsing Google Scholar pages.

Odysseus is a web scraping library built on top of Playwright, designed to handle dynamic web pages and CAPTCHA challenges with ease.

Browser Native client SDK for web scraping and content extraction API

Intelligent web scraping with AI Q&A, PDF support and multi-level fallback system - 11x faster than traditional scrapers

🔍 MCP 服务器，可让您使用内置缓存搜索和访问 Svelte 文档。

MCP client for MCPRelay proxy service - provides web access for AI agents

DeepSearch MCP Server with Brave Search API and Puppeteer content extraction

Model Context Protocol (MCP) server that integrates AgentQL data extraction capabilities.

Model Context Protocol (MCP) server for pure.md, the markdown delivery network for LLMs