yoloshii

Ultimate Scraper Skill — Data skill for Claude Code

Data community

Multi-tier web scraper with intelligent tier escalation, anti-bot bypass, CAPTCHA solving, and AI-powered data extraction.

How to install Ultimate Scraper Skill

This entry records only its repository, not the path inside it, so there is no exact command to give. Open yoloshii/ultimate-scraper-skill and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Ultimate Scraper Skill does

Multi-tier web scraper with intelligent tier escalation, anti-bot bypass, CAPTCHA solving, and AI-powered data extraction. 6 tiers (static → HTTP → stealth browser → anti-detect → AI → visual), CloakBrowser/Camoufox stealth, per-domain rate limiting, fingerprint persistence, and agent-first deployment.

Alternatives in Data

Claude Code Usage Monitor — by Maciek-roboblog - A real-time terminal-based tool for monitoring Claude Code token usage 7k ★
LLM Redteam — LLM red-team corpus runner — fires categorized prompt-injection / jailbreak / system-prompt-leak / data-exfil 4.5k ★
MCP Server Chart — 🤖 A visualization mcp & skills contains 25+ visual charts using @antvis 4k ★

README

ultimate-scraper

Multi-tier web scraper with intelligent tier escalation, anti-bot bypass, CAPTCHA solving, and AI-powered data extraction.

Features

6 scraping tiers with automatic escalation (static → HTTP → stealth browser → anti-detect → AI → visual)
CloakBrowser (C++ patched Chromium) and Camoufox (C++ anti-detect Firefox) for stealth
CAPTCHA solving via CapSolver (AI) and 2Captcha (human workers)
AI extraction with 3-tier LLM routing (local → z.ai → Claude Haiku)
Per-domain rate limiting with sliding window
Fingerprint persistence (consistent identity per domain)
Proxy support with geo-targeting and timezone/locale correlation
Tracker blocking via CDP network interception
Shadow DOM piercing for web components
WebMCP extraction for Chrome 147+ structured tool discovery
Batch processing with checkpointing and streaming output
Session persistence with cookie/state management

Quick Start

# Install core + all tiers
pip install httpx beautifulsoup4 lxml html2text pyyaml python-dotenv
pip install chompjs extruct              # Tier 0: static extraction
pip install curl_cffi                     # Tier 1: TLS spoofing
pip install scrapling cloakbrowser        # Tier 2: stealth browser
pip install 'camoufox[geoip]' && python -m camoufox fetch  # Tier 3: anti-detect (~780MB)
pip install crawl4ai                      # Tier 4: AI extraction

# Basic scrape
python scripts/scrape.py "https://example.com"

# With AI extraction
python scripts/scrape.py "https://example.com" \
  -e "Extract all product names and prices" -o json

# Protected sites (stealth browser + US proxy)
python scripts/scrape.py "https://example.com" -m stealth -g us