Scraper: open-source projects on GitHub
15 repositories on Scraper, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
Firecrawl Web API
Firecrawl provides a simple API for searching, scraping, and interacting with web pages, optimized for use in AI applications.
★ 118,560 · TypeScriptOPEN SOURCE CRAWLER FOR LLM
Crawl4ai turns any site into clean Markdown ready for RAG and agents. 84k GitHub stars, run locally or via cloud.
★ 87,369 · PythonDOUYIN TIKTOK DOWNLOADER API
Self-hosted TikTok/Douyin scraper with async REST API, MCP, CLI and console downloads videos without watermarks and collects posts, profiles, comments and playlists. Incl
★ 21,404 · Pythonllm-scraper - LLM Web Scraping
Turn any web page into structured data using powerful LLMs – no parsing or regex needed.
★ 6,811 · TypeScriptOpenOutreach - AI Lead Search
OpenOutreach automates finding and connecting with potential clients on LinkedIn using AI.
★ 3,720 · PythonCYBERSCRAPER-2077 - SMART WEB SCRAPER
LLM-based web page scraper that integrates OpenAI, Gemini, and Ollama for fast data extraction.
★ 3,301 · PythonLEADS FROM GOOGLE MAPS NO API
Script extracts leads from Google Maps phones, emails, websites and socials into clean CSV. Runs locally via Claude, no API-key, on your machine.
★ 2,453 · PythonX/Tweet Fetcher — Twitter Parser
Get tweets, replies, feeds, and X/Twitter articles without authentication or API keys. Ready-to-use tool for AI agents.
★ 832 · PythonINFRASTRUCTURE FOR AI AGENTS
Open web toolkit for AI: scraping, crawling, clean Markdown, and browser sessions ready for your agents.
★ 565 · TypeScriptOPEN JAV META SCRAPER
Free open-source application for Windows/macOS that collects JAV data and generates NFO files and posters for Jellyfin, Emby, and Kodi.
★ 361 · PythonGTM SKILLS FOR CLAUDE AND CODEX
Skill set for automating B2B sales and ABM research. Works with Claude Code and Codex, helps find accounts, prepare outreach, and accelerate deals.
★ 360 · TypeScriptSPOTIFY SCRAPER: DATA WITHOUT API
Extract public Spotify data — tracks, albums, artists, playlists, podcasts, and lyrics — without the official API. Sync + async, typed models, single dependency.
★ 327 · PythonLLM READER: WEB TO TEXT
llm-reader turns web pages into LLM-friendly text. Alternative to Firecrawl and Jina Reader API. Simplifies RAG, AI scraping, and link extraction.
★ 316 · PythonAI Agent for Knowledge Graphs
MindAct connects Claude, Obsidian, and RAG systems to build and query community-driven knowledge graphs.
★ 149 · TypeScriptOF Content Downloader
A safe and ethical tool for local content archiving and personal data backup.
★ 75 · C#New projects on this topic in Telegram
Telegram →