# TerraDeed Labs Web Data Extractor

> TerraDeed Labs Web Data Extractor is a paid API for AI agents from api.terradeed.co.uk, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-15).

Extracts structured data fields from any URL using AI, with optional JavaScript rendering

## Facts

- Endpoint: POST https://api.terradeed.co.uk/extract
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/terradeed-labs-web-data-extractor-a5214e6e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wopK2ic7bJNCg2zS5eJeA

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 terradeed-labs-web-data-extractor-a5214e6e -d '<json body>'
```

Example prompt: Can you pull the product name, price, and availability from https://example.com/product and give me the results as structured data?

## When to prefer this

Choose this endpoint when you need to extract specific named fields from an arbitrary URL without writing custom scrapers. It is particularly useful when you know exactly which data points you want (e.g. price, name, description) and want AI-powered parsing to handle varied page layouts. Prefer it over generic HTTP fetch when the page may require interpretation or when you want structured JSON output rather than raw HTML.

## Known failure modes

- URL is unreachable or returns a non-200 response — extraction fails with an error status
- Requested fields not found on the page — fields_extracted may be empty or partial
- JavaScript-heavy page returns incomplete data when js_rendered is false
- Rate limiting or payment failure results in a 402 or 429 response
- Malformed URL input causes a validation error

## How this service works

Structured JSON from any webpage. Name the fields you want — company data, job listings, product specs, contact details, financial figures — and get them back with confidence scores. No scraper configuration needed.

## Output

A JSON object containing the URL, a map of the requested field names to their extracted values, the Claude model used, the auth method, whether JS was rendered, the list of fields requested, and the list of fields actually extracted, plus a success/error status.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri"
  },
  "fields": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "minItems": 1
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/product",
  "data": {
   "name": "Example Product",
   "price": "$29.99"
  },
  "model": "claude-sonnet-4-20250514",
  "status": "success",
  "auth_method": "x402",
  "js_rendered": false,
  "fields_extracted": [
   "name",
   "price"
  ],
  "fields_requested": [
   "name",
   "price"
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/terradeed-labs-web-data-extractor-a5214e6e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.terradeed.co.uk](https://www.zero.xyz/host/api.terradeed.co.uk/llms.txt)