scrape

name	scrape
description	Scrape a single web page through UpRock's global device network and return clean, LLM-ready markdown. Use when the user gives a URL and wants its content, or asks to "scrape", "fetch", "read", or "extract" a page. Handles JavaScript rendering, anti-bot, and per-country geo placement.

UpRock: Scrape a page

Fetch a single URL through UpRock's distributed network of real browsers and return clean markdown.

How to do it

1. Call the uprock MCP tool crawl_fetch with:

   • url: the target URL (required).
   • method: default CRAWL_FULL_PAGE (real browser + JavaScript). Only use GET when the user says the page is a static HTML page or a raw API/JSON endpoint and speed matters.
   • country: set only if the user wants the page as seen from a specific place (e.g. localized pricing, geo-restricted content, cookie banners). Prefer meta-regions (NA, EU, APAC, LATAM, MEA); use a country code (US, DE, JP, …) only when exact country placement is required.
   • device_type: mobile or desktop only if requested.
   • retries: leave default (2) for reliability; set 0 for a single fast attempt.

2. crawl_fetch returns a summary plus content.markdown.resource and content.html.resource (and sometimes screenshots.viewport) as crawl:// resource URIs — not the full text inline.

3. If the user needs the full page text (to extract data, read tables, quote sections), call resource_fetch with the crawl://…/markdown URI. Prefer markdown over HTML — it is far more compact. Use the …/html URI only when the user needs raw markup structure, and …/viewport for the screenshot.

4. Present the markdown to the user. If they asked for structured data (specific fields, a table, JSON), extract it from the fetched markdown yourself and return it in the requested shape.

Notes

• crawl_fetch already renders JavaScript and handles anti-bot — do not fall back to the built-in WebFetch.
• For many URLs at once, call crawl_fetch for each (they run independently); for following links across a site, use /uprock:crawl instead.
• If a fetch fails, retry once with a different country/meta-region before reporting failure.