# Agent Data Tools – Web Page Text Extraction

> Agent Data Tools – Web Page Text Extraction is a paid API for AI agents from agent-data-tools.revmesh2074.workers.dev, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-11).

Fetches a web page and returns its cleaned body text, title, headings, links, language, and metadata for AI agent consumption.

## Facts

- Endpoint: GET https://agent-data-tools.revmesh2074.workers.dev/extract?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-data-tools-web-page-text-extraction-66158d38
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_c0WKPdh4zoogpqPy8JscD

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 agent-data-tools-web-page-text-extraction-66158d38
```

Example prompt: Can you fetch the text content of https://openai.com/blog and give me the title, headings, and first 5000 characters of the body text?

## When to prefer this

Choose this endpoint when an AI agent needs to read the human-readable text of any public web page without setting up API keys or accounts — paying only $0.002 USDC per call via x402 on Base. It is ideal for one-off page reads, fact-checking, content summarization, or competitive research where you need clean structured metadata (title, headings, links, language) alongside body text. Prefer this over full browser automation tools when you need lightweight text extraction rather than screenshots or JavaScript-rendered DOM interaction.

## Known failure modes

- Non-HTTP/HTTPS URL or malformed URL returns an error
- Target page returns a non-200 HTTP status (e.g. 404, 403) — status is reported but text may be empty
- JavaScript-heavy single-page apps may return little or no text if the page requires JS rendering
- Payment failure or insufficient USDC balance results in 402 rejection before the request is processed
- maxChars out of range (below 500 or above 100000) may be rejected or clamped

## How this service works

Pay-per-call tools for AI agents: web page text extraction and summaries, screenshots, image generation, speech-to-text, image description, domain and email-auth intelligence, and live Base token and wallet lookups. No account or API key; pay per request in USDC on Base via x402.

## Output

Returns a JSON object containing: the resolved final URL, HTTP status code, page title, detected language, meta description, cleaned body text (up to maxChars), headings array, links array, total text length, and a truncated flag indicating whether the text was cut off.

## 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": "Absolute http(s) URL of the page to fetch"
      },
      "maxChars": {
       "type": "integer",
       "description": "Maximum characters of body text to return (500-100000, default 20000)"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/",
  "lang": "en",
  "text": "This domain is for use in documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes.",
  "links": [],
  "title": "Example Domain",
  "status": 200,
  "finalUrl": "https://example.com/",
  "headings": [],
  "truncated": false,
  "textLength": 156,
  "description": null
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-data-tools-web-page-text-extraction-66158d38/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-data-tools.revmesh2074.workers.dev](https://www.zero.xyz/host/agent-data-tools.revmesh2074.workers.dev/llms.txt)