# Schema Extraction from URL

> Schema Extraction from URL is a paid API for AI agents from x240.jvnclk88.workers.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-29).

Fetches a public URL and extracts specific named fields from the page content, returning a structured JSON object

## Facts

- Endpoint: POST https://x240.jvnclk88.workers.dev/extract?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/schema-extraction-from-url-724d780f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_cWQCc4-ZBYAcTFzBMdjJ9

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 schema-extraction-from-url-724d780f -d '<json body>'
```

Example prompt: Go to https://www.example.com/product/123 and extract the price, title, and availability as a JSON object for me.

## When to prefer this

Use this endpoint when you know exactly which named fields you want from a page and need them as structured JSON, rather than raw text or all metadata. It is ideal for targeted data extraction (e.g. price, title, author) without post-processing. Prefer it over the product-page or metadata endpoints when you need custom field names beyond their fixed schemas, and over the batch scrape endpoint when you need clean, typed values for specific fields from a single URL.

## Known failure modes

- URL is not publicly accessible or returns a non-200 status — extraction fails with an error
- Page content is JavaScript-rendered and the relevant fields are not present in the initial HTML — fields may be null
- More than 20 fields requested — request rejected
- Field names are too ambiguous to match page content — returns null values for unmatched fields
- URL is malformed or not http/https — request rejected with validation error

## How this service works

Schema extraction - send a URL and the fields you want (for example price, title) and get a JSON object back

## Output

A JSON object whose keys are the field names you specified and whose values are the corresponding data found on the page. If a field cannot be found, it may be null or omitted. The response reflects the content of the live page at the time of the request.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public http or https URL to fetch"
  },
  "fields": {
   "oneOf": [
    {
     "type": "array",
     "items": {
      "type": "string"
     },
     "maxItems": 20
    },
    {
     "type": "object",
     "additionalProperties": {
      "type": "string"
     }
    }
   ],
   "description": "Field names to extract (array of strings, or object of name to description), up to 20"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/schema-extraction-from-url-724d780f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x240.jvnclk88.workers.dev](https://www.zero.xyz/host/x240.jvnclk88.workers.dev/llms.txt)