# AgentShelf JSON-LD Course Extractor

> AgentShelf JSON-LD Course Extractor is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.009/call, status unknown (last checked 2026-10-02).

Extracts JSON-LD @type Course structured data from a public webpage URL or raw HTML, SSRF-safe, for $0.009 USDC per call.

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/profile-jsonld-course?utm_source=zero.xyz
- Price: $0.009/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentshelf-json-ld-course-extractor-412ba0ff
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_oOBxdihLboPbhpUT1mlmo

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-json-ld-course-extractor-412ba0ff -d '<json body>'
```

Example prompt: Can you pull the JSON-LD Course structured data from this page: https://www.coursera.org/learn/machine-learning — I want the course name, description, and provider details from the schema markup.

## When to prefer this

Use this endpoint when you need to extract schema.org Course structured data specifically from a public webpage or HTML blob, and you want an SSRF-safe, paid extraction service. Prefer the free sandbox endpoint POST /v1/sandbox/profile-jsonld-course first; fall back to this paid endpoint when the sandbox is unavailable or rate-limited. Choose this over general-purpose scrapers when you specifically need the JSON-LD Course type and want structured, typed output rather than raw HTML or unstructured text.

## Known failure modes

- URL is unreachable or returns non-2xx HTTP status
- Page contains no JSON-LD @type Course markup — returns empty result
- HTML exceeds 200,000 character limit
- URL is blocked due to SSRF safety rules (private/internal addresses)
- Malformed HTML that cannot be parsed
- Both url and html fields absent or too short

## How this service works

Call when an agent needs JSON-LD @type Course extracted from a public page or HTML (SSRF-safe). Exact $0.009 USDC. Prefer unpaid POST /v1/sandbox/profile-jsonld-course first.

## Output

Returns the extracted JSON-LD @type Course object(s) from the page, containing fields such as name, description, provider, url, courseCode, hasCourseInstance, and other schema.org Course properties found in the page's structured data markup.

## 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-json-ld-course-extractor-412ba0ff/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)