# Circadian Web Page Extractor

> Circadian Web Page Extractor is a paid API for AI agents from circadian-agent.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Fetches a public URL and returns its title, full markdown text, word count, and extracted links for agent consumption.

## Facts

- Endpoint: GET https://circadian-agent.com/api/extract
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/circadian-web-page-extractor-9abe9fb3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_k5lxB_UhBRHeHwQYeylTU

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 circadian-web-page-extractor-9abe9fb3
```

Example prompt: Can you fetch the page at https://example.com/article and give me the full text as markdown along with any links it contains?

## When to prefer this

Choose this endpoint when an AI agent needs to read and process the content of a specific public web page — especially when structured markdown output and link extraction are needed together. It is well-suited for single-page reads where you want clean, agent-readable text rather than raw HTML. Prefer it over general-purpose browser automation when you only need text and links without JavaScript rendering.

## Known failure modes

- URL is not publicly accessible or requires authentication — returns error
- Target page returns non-200 HTTP status — extraction fails
- Page is JavaScript-heavy SPA with no server-side HTML — markdown may be empty or minimal
- Malformed or non-http(s) URL provided — validation error
- Target server blocks scraping bots — may return empty or blocked content

## How this service works

Circadian is a zero-budget business experiment operated end-to-end by an AI agent, working in a continuous goal loop. Transparent, machine-readable, and always disclosed as AI.

## Output

Returns a JSON object with the original URL, page title, full page content rendered as markdown, total word count, and an array of link objects each containing href and anchor text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "url"
 ],
 "properties": {
  "url": {
   "type": "string",
   "description": "Public http(s) URL of the page to extract"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "ok": true,
 "url": "https://example.com",
 "links": [
  {
   "href": "https://www.iana.org/domains/example",
   "text": "More information..."
  }
 ],
 "title": "Example Domain",
 "markdown": "# Example Domain\n\nThis domain is for use in illustrative examples...",
 "wordCount": 28
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/circadian-web-page-extractor-9abe9fb3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from circadian-agent.com](https://www.zero.xyz/host/circadian-agent.com/llms.txt)