Data-Extraction Packages

Model Context Protocol server to work with AgentQL

JavaScript implementation of Lusail, a domain-specific language for extracting structured data from HTML

TOML front-matter parser and combiner. Minimal and perfect

YAML front-matter parser and combiner. Minimal and perfect

JSON front-matter parser and combiner. Minimal and perfect

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

easy-csv-parser simplifies CSV data parsing in Node.js. Fetch, extract headers, and convert CSV files from URLs to JavaScript objects and JSON effortlessly. Ideal fordevelopers, data analysis, automation, and more.

Convierte un objeto de tabla Excel a JSON.

A flexible and powerful library designed to extract and transform data from HTML documents using user-defined schemas

A module written in TypeScript that provides a utility to extract data from an OFX file in Node.js and Browser

This is a simple Javscript library that converts a JSON object to a CSV file.

Official TypeScript SDK for Parsera.org API - Extract structured data from any webpage

A lightweight package to scrape and extract metadata for npm packages.

A lightweight library for scraping public social media profiles, providing profile information such as usernames, pictures, and more.

A nodejs tool for scraping Google Reviews using Puppeteer.

Utilities for extracting financial data from various economic calendar websites

Extractor de datos de tiendas Shopify usando API

Tavily搜索 MCP 服务是一个兼容Model Context Protocol (MCP)协议的高级网络搜索工具，允许AI模型如Claude直接访问互联网上的实时信息。该服务提供两个核心工具：tavily-search用于智能网络搜索，支持按新闻、特定域名筛选；以及tavily-extract用于从网页中提取关键内容。作为专业的搜索解决方案，Tavily MCP 服务支持多种MCP客户端包括Cursor、Cline和Claude Desktop，帮助AI模型获取最新、最相关的网络信息，大幅提升其回答

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