# AgentShelf XPath Caption Extractor

> AgentShelf XPath Caption Extractor is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-02).

Extracts caption text from a public webpage or raw HTML using XPath targeting of caption elements, with SSRF protection.

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/xpath-caption?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentshelf-xpath-caption-extractor-52cd3ffa
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_odtkVdQekftzPYml5rpzm

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 agentshelf-xpath-caption-extractor-52cd3ffa -d '<json body>'
```

Example prompt: Can you extract the caption text from this article page at https://example.com/article — I need whatever text is in the caption element on that page.

## When to prefer this

Use this endpoint when you need to extract caption text specifically (figcaption, caption elements) from a public webpage or raw HTML and want SSRF-safe fetching built in. Prefer the free sandbox endpoint /v1/sandbox/xpath-caption first if available to avoid the $0.002 USDC cost. Choose this over general HTML scrapers when you specifically need XPath-targeted caption extraction without running your own browser or parser.

## Known failure modes

- No caption element found on the page — returns empty or null result
- SSRF-blocked URL (private IP ranges, localhost) — request rejected for security
- URL is not publicly accessible or returns non-200 status — fetch failure
- HTML input exceeds 200,000 character limit — payload too large error
- Malformed HTML that cannot be parsed by XPath — parse error
- URL string shorter than 8 characters or longer than 2048 characters — validation error

## How this service works

Call when an agent needs text of //caption via //caption from a public page or HTML (SSRF-safe). Exact $0.002 USDC. Prefer unpaid POST /v1/sandbox/xpath-caption first.

## Output

Returns the extracted caption text from the specified public webpage URL or provided HTML, targeted via XPath on caption-type elements. The response contains the plain text content of the matched caption node(s).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "maxLength": 2048,
   "minLength": 8,
   "description": "Public page to fetch. The selector or profile is fixed by the SKU. Provide url or html."
  },
  "html": {
   "type": "string",
   "examples": [
    "<!doctype html><html lang=\"en\"><head><title>Hello</title>\n<meta name=\"description\" content=\"Desc\"><meta property=\"og:title\" content=\"OG\">\n<link rel=\"canonical\" href=\"https://example.com/\"><link rel=\"icon\" href=\"/favicon.ico\">\n</head><body><h1>Hello</h1><a href=\"https://example.com/a\">A</a></body></html>"
   ],
   "maxLength": 200000,
   "minLength": 1,
   "description": "HTML to extract from locally. Provide html or url. When both are set, html is used."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentshelf-xpath-caption-extractor-52cd3ffa/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentshelf.syntexa.ch](https://www.zero.xyz/host/agentshelf.syntexa.ch/llms.txt)