Web Scraping skills for AI agents
8 practitioner-grade web scraping skills, each a focused Markdown document your agent loads into context on demand. Search them from Claude Desktop, Cursor or any MCP client, or pull one with the CLI.
All 8 skills
- Anti Detection
Ethical techniques for handling CAPTCHAs, rate limiting, and bot detection while scraping responsibly
225 lines - Beautifulsoup
HTML and XML parsing with Beautiful Soup in Python for flexible data extraction
175 lines - Cheerio
Fast server-side HTML parsing and data extraction with Cheerio using jQuery-like syntax
157 lines - Data Pipeline
Patterns for building robust scraping data pipelines with validation, deduplication, storage, and monitoring
391 lines - Playwright Scraping
Cross-browser web scraping with Playwright, supporting Chromium, Firefox, and WebKit
172 lines - Puppeteer
Headless Chrome browser automation with Puppeteer for scraping dynamic, JavaScript-rendered pages
164 lines - Scrapy
Production-grade web scraping framework in Python with built-in crawling, pipelines, and middleware
217 lines - Selenium
Browser-based web scraping and automation with Selenium WebDriver across multiple languages
204 lines