# NOVA URL to JSON Extractor

> NOVA URL to JSON Extractor is a paid API for AI agents from nova-demand-worker.vercel.app, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-11).

Fetches a public webpage URL and returns its structured content as JSON, including text, links, title, headings, canonical URL, and meta description.

## Facts

- Endpoint: POST https://nova-demand-worker.vercel.app/x402/url-to-json?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/nova-url-to-json-extractor-9a273953
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_uo6xUaFbEZ_k9jv514dbI

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 nova-url-to-json-extractor-9a273953 -d '<json body>'
```

Example prompt: Fetch the page at https://techcrunch.com/2024/01/15/openai-news/ and give me the full text, title, and all the links on that page.

## When to prefer this

Choose this endpoint when you need to quickly extract structured content (text, links, headings, metadata) from a single public webpage at low cost ($0.01 USDC per call) and want a clean JSON response without setting up your own scraping infrastructure. It is ideal for agent workflows that need to read and process live web content on demand, especially when payment is handled via x402 on Base with USDC.

## Known failure modes

- URL is not publicly accessible or requires authentication — returns an error or empty content
- URL points to a non-HTML resource (PDF, image, etc.) — structured fields may be empty or missing
- Webpage blocks bot/programmatic access — content may be incomplete or missing
- Invalid or malformed URL input — returns a validation error
- Target server is slow or down — request may time out

## How this service works

Machine-facing pay-per-call utility services using x402 on Base with USDC.

## Output

A JSON object containing the page's extracted plain text, an array of all hyperlinks found, the page title, an array of headings, the canonical URL, and the meta description tag — all derived from the live fetched version of the provided URL.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public HTTP or HTTPS webpage URL to extract."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/page",
  "text": "Example page text",
  "links": [
   "https://example.com/other"
  ],
  "title": "Example",
  "headings": [
   "Example"
  ],
  "canonical": "https://example.com/page",
  "description": "Example page"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/nova-url-to-json-extractor-9a273953/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from nova-demand-worker.vercel.app](https://www.zero.xyz/host/nova-demand-worker.vercel.app/llms.txt)