edge-browser_skill

Overview

This skill controls the Microsoft Edge browser to fetch web pages and extract rendered content. It uses a real browser session to handle JavaScript, dynamic loading, and sites with basic bot defenses. Use it when standard HTTP fetchers fail or when an Edge-specific environment is required.

How this skill works

The skill launches an Edge/Chromium browser via Playwright, navigates to the target URL, waits for network and JavaScript activity, and extracts the full HTML, page title, and plain text. It supports configurable wait times and output to a JSON file. If Edge is not available, it falls back to Chromium automatically.

When to use it

• You need JavaScript-rendered content that simple HTTP requests cannot obtain.
• Target site applies anti-scraping measures that block non-browser user agents.
• A user explicitly requests browsing with Microsoft Edge instead of Chrome.
• Standard web fetch tools fail due to bot detection or session requirements.
• You want a reliable archive of page HTML, title, and extracted text.

Best practices

• Install Playwright and the required browser binaries before running the skill.
• Use the --wait option for pages with lazy-loaded or delayed content.
• Respect site terms of service and robots.txt when scraping content.
• Limit request frequency and consider using proxies if rate-limited.
• Save outputs to files for later analysis and reproducibility.

Example use cases

• Fetch a news article that requires client-side rendering and save the HTML and text.
• Access a product page with dynamic pricing that standard scrapers miss.
• Archive a web page for backup or auditing, including rendered DOM and title.
• Work around bot-blocking heuristics by using a full Edge browser session.
• Automate retrieval of pages behind mild anti-bot checks where headers alone fail.