# Web Index / Hub Page Text Extractor

> Web Index / Hub Page Text Extractor is a paid API for AI agents from api.qocgpiywhm.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-15).

Extracts readable text content from homepage or hub-style URLs, falling back to an alternative extraction profile if the primary yields no main content.

## Facts

- Endpoint: POST https://api.qocgpiywhm.com/api/v1/tools/clean_web_index?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/web-index-hub-page-text-extractor-8be3431d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_rneba_KY9cPkr_uI6GJXG

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 web-index-hub-page-text-extractor-8be3431d -d '<json body>'
```

Example prompt: Can you grab the main readable text from the homepage at https://example.com — I want to see what their site is actually about, not just links or metadata.

## When to prefer this

Choose this endpoint when the target URL is a homepage, portal, directory, or hub page — not a single article or blog post. It is distinct from the single-article extractor (which targets individual content pages) and the link extractor (which returns structured link lists). The built-in fallback profile makes it more robust for ambiguous hub pages than calling a single-mode extractor.

## Known failure modes

- URL is unreachable or returns a non-200 HTTP status — no content returned
- Page is entirely JavaScript-rendered with no static text — extraction yields empty or minimal result
- Both the primary and fallback extraction profiles find no main content — empty response
- Invalid or malformed URL input — request rejected
- Rate limit or payment failure — request blocked

## How this service works

Use to extract readable text from a homepage or hub URL. Not a single-article extract (Web Content Cleaner) and not a structured link list (Link Extractor). If the requested extract has no main content, the other profile is tried once in the same request.

## Output

Returns cleaned, human-readable text extracted from the homepage or hub URL. If the primary extraction profile finds no main content, a secondary profile is automatically tried within the same request, maximizing the chance of returning useful text.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/web-index-hub-page-text-extractor-8be3431d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.qocgpiywhm.com](https://www.zero.xyz/host/api.qocgpiywhm.com/llms.txt)