Structured Page Extraction

Pull data from a page into the JSON schema you define. The page is rendered, then AI maps its content to your fields.

Pay by wallet (x402) AI-generated structured-scrape

Example

Input

{
  "url": "https://example.com",
  "schema": {
    "type": "object",
    "properties": {
      "name": {
        "type": "string"
      },
      "email": {
        "type": "string"
      }
    }
  }
}

Answer

{
  "url": "https://example.com",
  "data": {
    "name": null,
    "email": null
  }
}

Inputs

Field	Type	Required	What it is
`url`	string	Yes	URL to scrape
`schema`	object	Yes	JSON schema describing the data to extract

Output fields

How reliably each field appears in a successful answer.

Field	Type	Appears
`url`	string	Always (present in every successful answer)
`data`	object	Always (present in every successful answer)

How to call it

The same tool through each route. MCP clients reach it through Strale’s server at https://api.strale.io/mcp; the call below is what the agent sends.

# Needs an API key. max_price_cents caps what this call may cost.
curl -X POST https://api.strale.io/v1/do \
  -H "Authorization: Bearer $STRALE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "capability_slug": "structured-scrape",
    "inputs": {
      "url": "https://example.com",
      "schema": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string"
          },
          "email": {
            "type": "string"
          }
        }
      }
    },
    "max_price_cents": 20
  }'

{
  "tool": "strale_execute",
  "arguments": {
    "slug": "structured-scrape",
    "inputs": {
      "url": "https://example.com",
      "schema": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string"
          },
          "email": {
            "type": "string"
          }
        }
      }
    },
    "max_price_cents": 20
  }
}

import { Strale } from "straleio";

const strale = new Strale({ apiKey: process.env.STRALE_API_KEY! });
const result = await strale.do({
  capability_slug: "structured-scrape",
  inputs: {
    "url": "https://example.com",
    "schema": {
      "type": "object",
      "properties": {
        "name": {
          "type": "string"
        },
        "email": {
          "type": "string"
        }
      }
    }
  },
  max_price_cents: 20,
});

import os
from straleio import Strale, DoRequest

strale = Strale(api_key=os.environ["STRALE_API_KEY"])
result = strale.do(DoRequest(
    capability_slug="structured-scrape",
    inputs={
        "url": "https://example.com",
        "schema": {
            "type": "object",
            "properties": {
                "name": {
                    "type": "string",
                },
                "email": {
                    "type": "string",
                },
            },
        },
    },
    max_price_cents=20,
))

# No account. The first request answers 402 with the price in USDC;
# an x402 client pays it from your wallet and repeats the request.
curl -i -X POST https://api.strale.io/x402/v2/structured-scrape \
  -H 'Content-Type: application/json' \
  -d '{
    "url": "https://example.com",
    "schema": {
      "type": "object",
      "properties": {
        "name": {
          "type": "string"
        },
        "email": {
          "type": "string"
        }
      }
    }
  }'

Limitations

Dynamic class names can require selector changes
Requires CSS selectors for extraction — sites with dynamically generated class names (CSS-in-JS) may need adjusted selectors
What to do instead: Use data attributes or semantic HTML tags as selectors instead of class names for sites using CSS-in-JS