# Sitesy Page Reader

> Sitesy Page Reader is a paid API for AI agents from api.sitesy.ca, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-31).

Fetches a web page and returns its clean, readable plain text content along with extracted metadata

## Facts

- Endpoint: GET https://api.sitesy.ca/v1/page-reader?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-31
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sitesy-page-reader-e52d1a13
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_o1JhTfK3EGXGzEwfHDRzO

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 sitesy-page-reader-e52d1a13
```

Example prompt: Can you pull the readable text and metadata from this page for me: https://example.com/some-article — I want just the clean content, no HTML noise.

## When to prefer this

Choose this endpoint when you need clean, readable text from a single web page and want HTML stripped away automatically. It is ideal for feeding article or documentation content into an LLM, summarization pipeline, or RAG system. Prefer it over raw HTTP fetch when you need human-readable output without parsing HTML yourself. Use it instead of the sibling page-metadata endpoint when you want body content rather than just meta tags.

## Known failure modes

- URL is unreachable or returns non-2xx status — endpoint may return error or empty content
- Page is JavaScript-rendered and content is not available in static HTML — extracted text may be incomplete or missing
- URL points to a PDF or binary file rather than an HTML page — extraction may fail or return garbled content
- Rate limiting or bot-blocking by the target site — page may return empty or blocked content
- Malformed or missing URL parameter — endpoint returns validation error

## How this service works

Clean readable text and metadata extracted from one web page

## Output

Returns cleaned, human-readable plain text extracted from the target web page, stripping HTML tags, navigation, ads, and boilerplate, along with page metadata such as title and description. The response is structured for easy downstream consumption by language models or text processing pipelines.

## 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",
       "description": "A web page address"
      }
     }
    }
   },
   "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/sitesy-page-reader-e52d1a13/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.sitesy.ca](https://www.zero.xyz/host/api.sitesy.ca/llms.txt)