# Pocket Network Structured Web Extraction

> Pocket Network Structured Web Extraction is a paid API for AI agents from agent.pocket.network, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-01).

Fetches a web page and returns structured metadata fields, headings, JSON-LD, and a text excerpt, with optional regex or schema-based field extraction.

## Facts

- Endpoint: POST https://agent.pocket.network/v1/structured-web-extraction?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-01
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pocket-network-structured-web-extraction-68027012
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_WuxszkNsrZlXuIwpmD4UU

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 pocket-network-structured-web-extraction-68027012 -d '<json body>'
```

Example prompt: Can you fetch the page at https://example.com/article and pull out the title, author, published date, and a text excerpt from it?

## When to prefer this

Choose this endpoint when you need fast, structured metadata extraction from a public web page without executing JavaScript, and you want to pay per call in USDC with no account or API key setup. It is ideal for one-off or agent-driven scraping tasks where you need standard fields like title, author, OpenGraph, and JSON-LD plus optional custom regex extraction. Prefer alternatives if the target page requires JavaScript rendering, authentication, or full-page crawling beyond a single URL.

## Known failure modes

- URL is unreachable or returns a non-200 status — extraction fails with an error
- JavaScript-rendered content is not returned since JS is not executed
- Paywalled or login-gated pages return only visible pre-auth HTML
- Regex patterns in optional schema that don't match return empty custom fields
- Malformed URL input results in a validation error
- Cache may return slightly stale data up to 10 minutes old

## How this service works

Fetch a web page and return structured data: standard fields (title, description, language, h1, OpenGraph, author, published), headings, JSON-LD and a text excerpt. Optional schema picks named fields or applies regexes to the HTML. POST /v1/url with {url}. JavaScript is not executed; pages are cached for 10 minutes. Pay per request in USDC; no account, no API key.

## Output

Returns a structured JSON object containing standard fields (title, description, language, h1, OpenGraph metadata, author, published date), a list of headings, any JSON-LD blocks found on the page, a plain-text excerpt, and any custom fields defined by the optional schema parameter. Pages are cached for 10 minutes.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "The page URL (http or https)."
  },
  "schema": {
   "description": "Optional: a list of field names, a JSON Schema, or {fields: {name: regex}}."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pocket-network-structured-web-extraction-68027012/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent.pocket.network](https://www.zero.xyz/host/agent.pocket.network/llms.txt)