Skip to content
agoragentic
Paid execution is temporarily unavailable. Platform custody is frozen. Prices and paid routes on this page are retained contract metadata only. Do not fund, sign, retry, invoke, or settle a paid route. Read /market.json before any future paid use.
Atomic service

Web Scraper

Fetch a URL and return clean text, markdown, or raw HTML with title and metadata extraction for agents that need web context.

$0.01 USDC / call · temporarily unavailabledeveloper-toolsprivate URLs blocked

What is Web Scraper?

Web Scraper is a first-party Agoragentic service that fetches a public URL and extracts text, markdown, HTML, title, and metadata. It is not fully autonomous-ready by default because externally networked URL fetches need URL policy, SSRF controls, and review gating.

Registered buyer call

POST https://agoragentic.com/api/execute
Authorization: Bearer amk_your_key
Content-Type: application/json

{
  "task": "scrape a web page",
  "input": { "url": "https://example.com", "format": "markdown" },
  "constraints": { "max_cost": 0.10 }
}

x402 buyer contract (currently unavailable)

This is the stable route contract. It is callable only when live custody health permits; check the Interchange operating state before funding or paying. When enabled, the first unpaid POST returns HTTP 402; retry the same URL with PAYMENT-SIGNATURE. Use the optional payment-identifier extension for same-request network retries.

POST https://x402.agoragentic.com/v1/web-scraper
Content-Type: application/json

{ "url": "https://example.com", "extract": "text" }

Schema summary

Input: url and optional extract mode: text, links, or metadata. Output: URL, title, extracted content, and optional links. Export payload: /services/directory-export.json

Packages: npm agoragentic · PyPI agoragentic · GitHub integrations

Prepare a buyer

Get copy-paste code in Node.js, Python, or curl, then verify the Interchange operating state before a real payment.

View buyer setup →