Browser Automation & Web Scraping

0•

Automates headless browser interactions, dynamic web scraping, full-page screenshots, and form submissions using Playwright.

The Browser Automation skill equips Claude Code with robust browser control and web extraction capabilities powered by Playwright across Python and Node.js. It allows developers to capture full-page screenshots, execute automated login sequences, extract data from client-rendered single-page applications, and generate PDFs from web documents. Designed to bypass the limitations of static HTTP fetch tools, it provides production-ready guidance on handling dynamic JavaScript rendering, infinite scroll feeds, and network idle states while enforcing clean browser lifecycle management.

主要功能

01Dynamic web scraping for client-side rendered JavaScript pages
02Infinite scroll handling and programmatic page evaluation
03Automated form interaction and multi-step login flows
04Headless PDF document generation with print formatting
05Full-page and custom-viewport website screenshot capture
060 GitHub stars

使用场景

01Automating multi-step authentication and automated form submissions
02Capturing full-page screenshots and PDF exports of live web applications
03Scraping dynamic SPA content that standard HTTP requests cannot render