# AgentShelf CSS Figcaption Extractor

> AgentShelf CSS Figcaption Extractor is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-02).

Extracts figcaption text from HTML figure elements on a given public web page or raw HTML input

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/css-figcaption?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentshelf-css-figcaption-extractor-87287cd1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_dCvlUHk8G2Dy54hsA67QC

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-css-figcaption-extractor-87287cd1 -d '<json body>'
```

Example prompt: Can you grab all the figcaption texts from this page: https://example.com/photo-gallery? I need the caption text from every figure element on the page.

## When to prefer this

Use this endpoint when you need to extract specifically figcaption text from HTML figure elements — ideal for accessibility audits, media metadata collection, content indexing, or any workflow where image captions in structured HTML are the target. Prefer over generic scraping tools when you want a focused, CSS-selector-level extraction that is SSRF-safe and priced per call.

## Known failure modes

- URL is not publicly accessible or blocked by robots/firewall, returning an error or empty result
- HTML input exceeds 200,000 character limit, causing rejection
- No figcaption elements found on the page, returning an empty result
- SSRF-blocked private/internal URLs rejected for security reasons
- Malformed URL under 8 characters rejected by schema validation
- Page returns non-HTML content (e.g. PDF, JSON), yielding no matches

## How this service works

Call when an agent needs figcaption text via figcaption from a public page or HTML (SSRF-safe). Exact $0.01 USDC. Prefer unpaid POST /v1/sandbox/css-figcaption first.

## Output

Returns an array or collection of figcaption text strings found within figure elements on the specified page or HTML input, covering all matched figcaption elements in document order.

## 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 charset=\"utf-8\"><meta name=\"description\" content=\"Desc\">\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-css-figcaption-extractor-87287cd1/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)