Data Extraction
651AI tools in the Data Extraction category
pentestic-playwright-mcp
opakgraham
Enhanced Playwright MCP Server with 40+ browser automation tools
opensteer
timjang3
Open-source browser automation SDK and CLI that lets AI agents build complex scrapers directly in your codebase.
@iflow-mcp/browserless-mcp
chatflowdev
Model Context Protocol server for Browserless.io browser automation
kick.com-api
bankkroll
An advanced kick.com API wrapper that allows via CLI or directly via API
@cbayel/web-browser
cbayel
MCP server for browser automation and web scraping
terminal-scrapearange
wolfram77
Terminal interface implementation for ranged web scraping.
braid-video-downloader
potatocorn3r
A powerful TypeScript library for downloading videos from web pages, including M3U8/HLS streams, with browser automation and intelligent stream detection
...morefree-proxy-nodejs
tuanle1028
> Free proxy nodejs is a lightweight Node.js NPM package designed to simplify the process of obtaining a list of proxies from https://spys.one. This package offers a convenient and customizable way to retrieve proxy data for your web scraping, security, o
...morebrowserd
subpopular
Browser automation SDK with visual streaming and remote control
dom-parser
ershov-konst
Fast dom parser based on regexps
@iflow-mcp/telegram-mcp-server
chatflowdev
MCP server for scraping Telegram public channels and groups
crawl-server
imike3049
Efficient SEO-focused server for Wasm-generated pages
@dmsdc-ai/aigentry-dustcraw
duckyoung_kim
Airborne signal absorber — collects floating public data (RSS/API/web) and feeds aigentry-brain
camofox-browser
redf0x1
Anti-detection browser server for AI agents — REST API wrapping Camoufox engine with OpenClaw plugin support
open-web-unlocker
GitHub Actions
Fetch public web pages through a configurable fetch/browser pipeline and parse them into structured JSON or clean markdown.
...more@crawl-me-maybe/sitemap
autopsyaardvark
A generic sitemap generation Vite plugin. Outputs sitemap.xml and robots.txt files after build. **This does not scan your directory for outputted routes, that approach only works for fully static sites. ISR and SSR are offlimits, hence I made this.**
...more@4ier/neo
4ier
Turn any website into an AI-callable API. Passive traffic capture, API schema generation, and execution.
apex-scraper
semo_dev
A stealth web scraper for crawling websites and extracting clean text content with page and word limits.
@monibrand/se-scraper
sviande
A module using puppeteer to scrape several search engines such as Google, Bing and Duckduckgo
almuten-scraper
oliver797
A tool for scraping and calculating almuten (planetary dignity) in astrology