# BlindOracle Clean Web Extract

> BlindOracle Clean Web Extract is a paid API for AI agents from api.craigmbrown.com, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-15).

Extracts clean main content from a single URL using Firecrawl, wrapped in a BlindOracle trust envelope with SHA-256 hash and scan verdict

## Facts

- Endpoint: POST https://api.craigmbrown.com/v1/services/data.web-extract
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/blindoracle-clean-web-extract-a6b1686e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_0GP9447IZxrk8LF0tO5On

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 blindoracle-clean-web-extract-a6b1686e -d '<json body>'
```

Example prompt: Pull the main content from https://example.com/article and give me the clean text — I also want the content hash and scan verdict so I can verify what was retrieved.

## When to prefer this

Choose this endpoint when you need both clean main-content extraction and a cryptographic trust envelope (SHA-256 hash + scan verdict) for a single URL. Prefer it over raw scrapers when content integrity verification matters — e.g. for due diligence pipelines, agent fact-checking, or any workflow where you need to prove what content was retrieved and that it passed a malware/safety scan.

## Known failure modes

- Invalid or unreachable URL returns an error status
- Paywalled or login-gated pages may return incomplete or no content
- Dynamically rendered JavaScript-heavy pages may yield partial content
- Network timeouts on slow-loading pages
- Blocked requests if the target site has anti-scraping protections

## How this service works

Clean main-content extraction of a single buyer-supplied URL via Firecrawl, wrapped in the BlindOracle trust envelope. Thin extraction tool; no data inventory held.

## Output

A JSON response containing the extracted page content, a BlindOracle trust envelope (with content_sha256, content_scanned flag, scan_verdict, source, and powered_by fields), and a deliverable_type field. The trust envelope allows downstream consumers to verify content integrity and provenance.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string"
  },
  "only_main_content": {
   "type": "boolean"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "schema": {
  "type": "object",
  "properties": {
   "status": {
    "type": "string"
   },
   "bo_trust": {
    "type": "object"
   },
   "deliverable_type": {
    "type": "string"
   }
  }
 },
 "example": {
  "deliverable_type": "..."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/blindoracle-clean-web-extract-a6b1686e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.craigmbrown.com](https://www.zero.xyz/host/api.craigmbrown.com/llms.txt)