# Agent Souk Web Page Fetcher

> Agent Souk Web Page Fetcher is a paid API for AI agents from api.agentsouk.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Fetches and extracts the text content, links, title, and metadata from any public web URL

## Facts

- Endpoint: POST https://api.agentsouk.dev/v1/x402/lst_01M1XYP3M9411Q18YT0MDB3V6S
- 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/agent-souk-web-page-fetcher-f717d449
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_aJ28DYc14zC90oSEbwHC3

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 agent-souk-web-page-fetcher-f717d449 -d '<json body>'
```

Example prompt: Fetch the full text content and links from https://news.ycombinator.com, up to 50000 characters, so I can read what's on the page.

## When to prefer this

Use this endpoint when an AI agent needs to read, extract, or summarize the textual content of a public webpage as part of an autonomous workflow — especially when paying per-call via USDC x402 micropayments suits the use case. Prefer this over browser automation tools when JavaScript rendering is not required and plain text extraction is sufficient.

## Known failure modes

- URL is not publicly accessible or requires authentication — HTTP 403/401 returned
- URL resolves to a non-HTML resource (PDF, binary) — content_type may differ and text extraction may be empty
- Page has heavy JavaScript rendering — text may be incomplete as server-side fetch cannot execute JS
- max_chars too low — text will be clipped and clipped field will be true
- Network timeout or DNS failure — fetch error returned
- Invalid URL format — schema validation error before request is made

## How this service works

Fetch a web page and extract clean text, title, description and links

## Output

A JSON object containing the extracted page title, plain-text body (clipped to max_chars if needed), array of hyperlinks (href + anchor text), detected language, meta description, final URL after redirects, number of redirects, HTTP status code, content type, fetch timestamp, character count, and word count.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "description": "Public http(s) URL"
  },
  "max_chars": {
   "type": "integer",
   "default": 20000,
   "maximum": 200000,
   "minimum": 100
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/",
  "lang": null,
  "text": "Example Domain\n\nThis domain is for use in illustrative examples in documents. ...",
  "links": [
   {
    "href": "https://www.iana.org/domains/example",
    "text": "More information..."
   }
  ],
  "title": "Example Domain",
  "clipped": false,
  "final_url": "https://example.com/",
  "redirects": 0,
  "fetched_at": "2026-09-07T12:00:00.000Z",
  "text_chars": 170,
  "word_count": 28,
  "description": null,
  "http_status": 200,
  "total_chars": 170,
  "content_type": "text/html; charset=utf-8"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-souk-web-page-fetcher-f717d449/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.agentsouk.dev](https://www.zero.xyz/host/api.agentsouk.dev/llms.txt)