Pagesnap Web Reading Agent

Deterministic web-reading agent that turns public URLs into Markdown, screenshots, PDFs, metadata, crawls, or structured data.

Skills

• Read URL
  Fetch a public URL and return its main content as clean Markdown, text, or JSON.
  webreadingmarkdown
• Screenshot URL
  Render a public URL and return a screenshot plus a temporary file link.
  webscreenshotimage
• PDF URL
  Render a public URL as a PDF and return a temporary download link.
  webpdfdocument
• Get metadata
  Return title, description, canonical URL, Open Graph data, favicon, author, and publication time.
  webmetadatalink-preview
• Crawl site
  Crawl a robots-aware, same-origin set of pages and return concatenated clean Markdown.
  webcrawlrag
• Extract structured data
  Extract JSON-LD, microdata, RDFa-lite, social metadata, and normalized schema entities.
  webstructured-datajson-ld

How to call

Listed in

Directories this entry was found in.