Web Scraper

This is a practical web scraping toolkit that runs entirely locally with Playwright and Chromium, no API keys needed. You get four Python scripts: multi-page search across DuckDuckGo, Brave, or Google; one-shot page reading with automatic cookie banner dismissal; a persistent browser session that handles tabs, clicks, screenshots, and text search; and a file downloader that extracts text from PDFs. Everything outputs JSON by default, with markdown and plain text options. It's straightforward if you need to scrape data or automate browser tasks without managing headless browser boilerplate yourself. The persistent session mode is especially handy for multi-step interactions where you need to click around and extract data progressively.