# spipe Content Extractor

> spipe Content Extractor is a paid API for AI agents from spip37.vercel.app, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-16).

Extracts and returns the content of one or more URLs in specified output formats, with configurable per-page crawl timeout

## Facts

- Endpoint: POST https://spip37.vercel.app/contents
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/spipe-content-extractor-29dfce28
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_TVLEVlf7gPeMkRhWbX7Ud

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 spipe-content-extractor-29dfce28 -d '<json body>'
```

Example prompt: Can you extract the full text content from these three URLs for me: https://example.com/article1, https://example.com/article2, and https://example.com/article3 — use markdown format and set a 30-second timeout per page?

## When to prefer this

Choose this endpoint when you need to extract readable content from one or more URLs at once, especially for AI research, summarization, or knowledge-base ingestion workflows. It supports configurable timeouts and output formats, making it well-suited for pipelines that need clean text or markdown from arbitrary web pages. Prefer it over browser automation tools when you need a lightweight, pay-per-call API without managing infrastructure.

## Known failure modes

- URL unreachable or returns non-200 status — content may be missing or empty for that entry
- Crawl timeout exceeded for a slow-loading page — partial or no content returned
- Invalid URL format in the urls array — request may fail or that URL may be skipped
- Paywalled or JavaScript-heavy pages may yield incomplete content
- Payment failure via x402 protocol — request blocked before processing

## How this service works

Web search, content extraction, and research APIs for AI agents. x402 on Base.

## Output

Returns a JSON object containing the extracted content from each requested URL, formatted according to the specified output formats (e.g. markdown, plain text). Each entry corresponds to one of the submitted URLs.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "urls"
 ],
 "properties": {
  "urls": {
   "type": "array",
   "description": "URLs to extract"
  },
  "formats": {
   "type": "array",
   "description": "Output formats"
  },
  "crawl_timeout": {
   "type": "integer",
   "description": "Timeout per page (1-60s)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/spipe-content-extractor-29dfce28/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from spip37.vercel.app](https://www.zero.xyz/host/spip37.vercel.app/llms.txt)