# Oromi Web Extract

> Oromi Web Extract is a paid API for AI agents from agents.oromi.co.uk, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-13).

Fetches and extracts clean text content from a given webpage URL, returning the page title, plain text, and word count

## Facts

- Endpoint: POST https://agents.oromi.co.uk/api/web/extract
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/oromi-web-extract-ab7e8973
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_2bv8XBtmsKvQeUBG2E6yr

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 oromi-web-extract-ab7e8973 -d '<json body>'
```

Example prompt: Can you extract the readable text content from this page for me: https://www.bbc.co.uk/news/technology-12345678 — I want the title and the full article text.

## When to prefer this

Choose this endpoint when you need to retrieve clean, readable plain text from a specific public webpage on a per-call, pay-as-you-go basis via USDC/x402, without setting up your own scraping infrastructure. It is particularly suited for agentic workflows that need to ingest web content programmatically for summarization, research, or analysis. Prefer it over general-purpose browser automation when you just need text and word count from a URL, not structured data or screenshots.

## Known failure modes

- URL is inaccessible or returns a non-200 HTTP status, resulting in an extraction error
- Page is behind a login wall or CAPTCHA, preventing content retrieval
- URL points to a binary file (PDF, image) rather than an HTML page, causing unexpected output or failure
- Malformed URL input causes a validation or request error
- Page content is JavaScript-rendered only, so static extraction may return empty or minimal text

## How this service works

Machine-payable APIs for AI agents, paid per call in USDC via the x402 protocol: UK business data (Companies House), UK property market data (HM Land Registry), website agent-readiness audits, and crypto market context.

## Output

Returns a JSON object containing the extracted plain text body of the page, the page title as a string, and a word count integer — suitable for downstream summarization, analysis, or storage tasks.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Page URL to extract"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "text": "...",
  "title": "Example article",
  "word_count": 843
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/oromi-web-extract-ab7e8973/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.oromi.co.uk](https://www.zero.xyz/host/agents.oromi.co.uk/llms.txt)