# tolca.tonbot.ca URL Extractor

> tolca.tonbot.ca URL Extractor is a paid API for AI agents from tolca.tonbot.ca, paid per call via x402, $0.03/call, status unknown (last checked 2026-10-12).

Fetches any public URL (HTML, PDF, or JSON) and returns structured data as clean JSON matching a caller-defined schema in a single call.

## Facts

- Endpoint: POST https://tolca.tonbot.ca/v1/extract-url?utm_source=zero.xyz
- Price: $0.03/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tolca-tonbot-ca-url-extractor-99f33f96
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_WqgyF1S_pWb-kxdTyvlON

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 tolca-tonbot-ca-url-extractor-99f33f96 -d '<json body>'
```

Example prompt: Fetch https://en.wikipedia.org/wiki/Montreal and extract the following fields as JSON: population (number), founded_year (number), official_languages (list of strings), and mayor (string).

## When to prefer this

Choose this endpoint when you need to extract specific named fields from a public webpage, PDF, or JSON URL without writing custom parsing or scraping code. It is ideal when you have a clear schema of what you want and need clean, structured JSON output in a single API call. Prefer it over generic scraping tools when you want schema-driven extraction with no post-processing.

## Known failure modes

- URL is not publicly accessible or returns a non-200 status — extraction fails with an error
- PDF or HTML content exceeds max_chars limit (60,000) — content may be truncated or rejected
- Schema fields cannot be found in the page content — returned values may be null or missing
- URL points to dynamically rendered JavaScript content that cannot be fetched server-side
- Malformed URL or unsupported content type returns an error

## How this service works

Pay-per-call services for AI agents over x402 (USDC on Base).

## Output

Returns a JSON object containing the extracted fields matching the caller-provided schema, along with the page title and source URL. The data keys correspond exactly to the field names defined in the input schema.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "example": "https://en.wikipedia.org/wiki/Montreal",
   "description": "Public http(s) URL: HTML page, PDF or JSON"
  },
  "schema": {
   "type": "object",
   "description": "Field name -> type or description of what to extract"
  },
  "max_chars": {
   "type": "integer",
   "default": 30000,
   "maximum": 60000,
   "minimum": 1000
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {
   "title": "Example post",
   "author": "Jane Doe",
   "key_points": [
    "..."
   ],
   "published_date": "2026-01-15"
  },
  "kind": "html",
  "title": "Example post",
  "source": "https://example.com/blog/post"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tolca-tonbot-ca-url-extractor-99f33f96/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from tolca.tonbot.ca](https://www.zero.xyz/host/tolca.tonbot.ca/llms.txt)