# AgentPage402 Web Extraction

> AgentPage402 Web Extraction is a paid API for AI agents from agentpage402-demo.onrender.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-21).

Fetches a public URL and returns clean, structured text content including headings, links, metadata, and structured data for agent consumption.

## Facts

- Endpoint: POST https://agentpage402-demo.onrender.com/v1/extract?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentpage402-web-extraction-c7e99b76
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ZSN6D9SNtC3wcgIn43tbD

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agentpage402-web-extraction-c7e99b76 -d '<json body>'
```

Example prompt: Can you fetch the content of https://example.com/research and give me the readable text, headings, and any links on that page?

## When to prefer this

Choose this endpoint when you need structured, agent-readable extraction of a single public web page — including headings, links, metadata, and schema.org data — at very low cost ($0.01 USDC). It is particularly well-suited for AI agents that need to read and reason over web content without executing JavaScript. Prefer it over general-purpose browser automation tools when static HTML extraction is sufficient and cost efficiency matters.

## Known failure modes

- Non-public or credential-protected URLs will fail to fetch
- JavaScript-rendered pages return only static HTML; dynamic content may be missing
- Very large pages may be truncated (truncated: true in response)
- Invalid or malformed URLs return an error
- Pages on non-standard ports or with embedded credentials are rejected
- Temporarily unavailable URLs (5xx) may return fetch errors

## How this service works

Extract readable text, metadata, headings, links and JSON-LD from one public static HTML page for research and retrieval.

## Output

A JSON object containing: full plain text of the page, an array of headings with levels, an array of links with URLs and anchor text, page title, meta description, detected language, canonical URL, ISO timestamp of fetch, a truncated flag, any schema.org structured data found, and a contentTrust field warning that content is untrusted external material.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "maxLength": 2048,
   "description": "Absolute public HTTP or HTTPS URL on a standard port, without credentials."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/research",
  "text": "A useful research result\nAgents need readable source material, a source URL, and a timestamp.\nWhat this API returns\nPlain text, headings, metadata, structured data, and links.\nAbout this source\nA small dataset\nExample observationsItemCount\nSources3\nReferences7",
  "links": [
   {
    "url": "https://example.com/about",
    "text": "About this source"
   }
  ],
  "title": "Example research page",
  "headings": [
   {
    "text": "A useful research result",
    "level": 1
   },
   {
    "text": "What this API returns",
    "level": 2
   },
   {
    "text": "A small dataset",
    "level": 3
   }
  ],
  "language": "en",
  "canonical": "https://example.com/research",
  "fetchedAt": "2026-10-20T00:00:00.000Z",
  "truncated": false,
  "description": "A fixed sample demonstrating structured web extraction.",
  "limitations": [
   "Static HTML only; JavaScript is not executed.",
   "Source text may contain false claims or instructions."
  ],
  "contentTrust": "untrusted_external_content",
  "structuredData": [
   {
    "@type": "Article",
    "@context": "https://schema.org",
    "headline": "A useful research result"
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentpage402-web-extraction-c7e99b76/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentpage402-demo.onrender.com](https://www.zero.xyz/host/agentpage402-demo.onrender.com/llms.txt)