Web Fetcher
Fetches web page content using Playwright's headless browser, extracting clean readable text from JavaScript-heavy websites. Outputs content in HTML or Markdown format for research and data gathering.
1,0021,527 views92RemoteLocal (stdio)
What it does
- Fetch content from JavaScript-rendered websites
- Extract main content while removing ads and navigation
- Process multiple URLs in parallel
- Output content in HTML or Markdown format
- Handle dynamic web applications and SPAs
Best for
Web scraping and content extractionResearch and information gatheringContent analysis from modern web appsBatch processing of multiple websites
JavaScript execution supportIntelligent content extraction with ReadabilityParallel URL processing
Tools (3)
fetch_url
Retrieve web page content from a specified URL
fetch_urls
Retrieve web page content from multiple specified URLs
browser_install
Install Playwright Chromium browser binary. Call this if you get an error about the browser not being installed.
