# AgentRXI Web Page Data Extractor

> AgentRXI Web Page Data Extractor is a paid API for AI agents from agentrxi.com, paid per call via x402, $0.009/call, status unknown (last checked 2026-10-15).

Renders any public URL with a headless browser and uses an LLM to extract structured JSON fields defined by a schema or plain-English prompt.

## Facts

- Endpoint: GET https://agentrxi.com/v1/extract?utm_source=zero.xyz
- Price: $0.009/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentrxi-web-page-data-extractor-4adb5402
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_LI3lp7Hb7RujL0rjYBiip

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 agentrxi-web-page-data-extractor-4adb5402
```

Example prompt: Can you go to https://news.ycombinator.com and extract the top 10 story titles and their URLs as structured JSON? Use a schema with fields 'title' and 'url'.

## When to prefer this

Choose this endpoint when you need structured JSON from a real website, especially pages that use JavaScript rendering (SPAs, React, Vue) where simple HTTP fetch-and-parse fails. It is ideal when you have a clear schema of fields to extract or can describe them in plain English. Prefer it over raw HTML fetchers when you need LLM interpretation to map messy page content into clean structured data.

## Known failure modes

- URL is behind a login wall or CAPTCHA — returns empty or partial fields
- Schema fields don't match any content on the page — returns nulls
- Dynamic content that loads only after user interaction (infinite scroll, click events) may not be captured
- Malformed or unparseable JSON schema input — returns an error
- Rate-limiting or blocking by the target site — may return incomplete data
- Invalid or unreachable URL — returns an HTTP error

## How this service works

Extract structured JSON from any web page. Give a URL plus a JSON schema or a plain-English prompt describing the fields you want; a headless browser renders the page and an LLM fills the schema. Also callable as GET with the same fields as query parameters.

## Output

A structured JSON object whose keys match the provided schema or plain-English prompt fields, populated with values extracted from the rendered web page. If a field is not found, it may be null or absent. The response reflects the fully rendered DOM, including JavaScript-generated content.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string"
      },
      "prompt": {
       "type": "string",
       "description": "Alternative to schema: describe what to extract"
      },
      "schema": {
       "type": "string",
       "description": "JSON schema of the fields to extract; JSON"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentrxi-web-page-data-extractor-4adb5402/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentrxi.com](https://www.zero.xyz/host/agentrxi.com/llms.txt)