# Cravvoul Substack Scraper

> Cravvoul Substack Scraper is a paid API for AI agents from cravvoul.vercel.app, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-14).

Fetches and extracts content from a Substack URL, returning structured data about the page

## Facts

- Endpoint: POST https://cravvoul.vercel.app/api/substack
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/cravvoul-substack-scraper-aab4f388
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_s0B5uLMadqVzBsV6EIBFt

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 cravvoul-substack-scraper-aab4f388 -d '<json body>'
```

Example prompt: Can you grab the content from this Substack post — https://someauthor.substack.com/p/some-article — and summarize what it's about?

## When to prefer this

Use this endpoint when you specifically need to scrape or extract content from Substack newsletters or posts. It is purpose-built for Substack URLs, making it more reliable for that domain than a generic web scraper. Ideal when you need structured data from Substack without managing authentication or subscriptions, and you want simple pay-per-use pricing in USDC.

## Known failure modes

- Invalid or malformed Substack URL returns an error or empty data
- Paywalled Substack content may not be fully accessible, returning partial data
- Network timeout if the Substack page is slow to respond
- Non-Substack URLs passed to the endpoint may return unexpected results or fail
- Payment via x402 not completed results in request being rejected

## How this service works

Web scraping and search for AI agents. No auth, no subscriptions. Pay per request in USDC via x402.

## Output

Returns a JSON object with a success boolean and a data object containing the scraped content and metadata from the given Substack URL, such as article text, title, author information, and other page elements.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "url"
 ],
 "properties": {
  "url": {
   "type": "string",
   "description": "Substack URL"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "object"
  },
  "success": {
   "type": "boolean"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/cravvoul-substack-scraper-aab4f388/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from cravvoul.vercel.app](https://www.zero.xyz/host/cravvoul.vercel.app/llms.txt)