🌐 Structured Data Extractor

Point at any URL and define a JSON schema — SparkForge will fetch the page and use Claude Haiku to extract exactly the data fields you specified. Perfect for price monitoring, lead generation, product data extraction, and any scenario where you need structured data from unstructured web content.

Request Body

Parameter	Type	Required	Description	Default
`url`	string	required	URL to fetch and extract data from	—
`schema`	object	required	Field definitions: { fieldName: 'string' \| 'number' \| 'boolean' \| 'array' \| 'object' }	—
`instructions`	string	optional	Optional extraction hints for the AI (e.g. 'extract the main product price')	—

Response Fields

Field	Type	Description
`data`	object	Extracted data matching your schema
`url`	string	URL that was fetched
`extractedAt`	string	ISO 8601 timestamp of extraction

Code Examples

cURL

bash

curl -X POST https://sparkforge.sh/api/extract \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-token>" \
  -d '{
    "url": "https://example.com/product/widget-pro",
    "schema": {
      "name": "string",
      "price": "number",
      "description": "string",
      "in_stock": "boolean"
    },
    "instructions": "Extract main product information from the page"
  }'

Python

python

import requests

response = requests.post(
    "https://sparkforge.sh/api/extract",
    headers={"Content-Type": "application/json", "X-PAYMENT": "<token>"},
    json={
        "url": "https://example.com/product/widget-pro",
        "schema": {
            "name": "string",
            "price": "number",
            "description": "string",
            "in_stock": "boolean"
        },
        "instructions": "Extract the main product details"
    }
)

data = response.json()["data"]
print(f"{data['name']}: ${data['price']} ({'In Stock' if data['in_stock'] else 'Out of Stock'})")

TypeScript / Node.js

typescript

const res = await fetch402("https://sparkforge.sh/api/extract", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    url: "https://example.com/product/widget-pro",
    schema: {
      name: "string",
      price: "number",
      description: "string",
      in_stock: "boolean",
    },
    instructions: "Extract the main product details",
  }),
});

const { data, extractedAt } = await res.json();
console.log(data.name, data.price, data.in_stock);

Example Response

json

{
  "data": {
    "name": "ACME Widget Pro",
    "price": 29.99,
    "description": "A high-quality widget for all your professional needs. Durable, lightweight, and built to last.",
    "in_stock": true
  },
  "url": "https://example.com/product/widget-pro",
  "extractedAt": "2026-02-28T16:00:00.000Z"
}

💳 Payment via x402

This endpoint costs $0.03 per call, paid in USDC on Base, Polygon, or Solana. Use the @x402/fetch library to handle payments automatically, or implement the x402 handshake manually.

bash

# Free demo mode (no payment)
curl https://sparkforge.sh/api/extract?demo=true

# Or try via MCP (Claude Desktop, Cursor, Windsurf)
# Add to mcp config: { "url": "https://sparkforge.sh/api/mcp" }

←

AI Smart Summarizer

Crypto News Summarizer

→