Receipt Parsing

Extract store information, line items, totals, and payment details from receipts. Parse works with printed receipts, digital receipts, and photographed thermal paper.

Receipt Schema

Define a schema that captures the key fields from a receipt:

{
  "name": "receipt",
  "description": "Extract data from receipts",
  "fields": [
    { "name": "store_name", "type": "string", "description": "Name of the store or business" },
    { "name": "store_address", "type": "string", "description": "Store location or address" },
    { "name": "date", "type": "date", "description": "Date of purchase" },
    { "name": "items", "type": "array", "description": "List of purchased items", "items": {
      "type": "object",
      "fields": [
        { "name": "name", "type": "string" },
        { "name": "quantity", "type": "number" },
        { "name": "price", "type": "number" }
      ]
    }},
    { "name": "subtotal", "type": "number", "description": "Subtotal before tax" },
    { "name": "tax", "type": "number", "description": "Tax amount" },
    { "name": "total", "type": "number", "description": "Total amount paid" },
    { "name": "payment_method", "type": "string", "description": "Payment method used (e.g. Cash, Visa, Mastercard)" }
  ]
}

Code Examples

cURL

curl -X POST https://api.parse.conversiontools.io/v1/extract \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@receipt.jpg" \
  -F "schema=receipt"

Python

import requests

headers = {
    "Authorization": "Bearer YOUR_API_KEY"
}

with open("receipt.jpg", "rb") as f:
    response = requests.post(
        "https://api.parse.conversiontools.io/v1/extract",
        headers=headers,
        files={"file": f},
        data={"schema": "receipt"}
    )

data = response.json()
print(f"Store: {data['data']['store_name']}")
print(f"Total: {data['data']['total']}")
print(f"Paid with: {data['data']['payment_method']}")

for item in data["data"]["items"]:
    print(f"  - {item['name']}: {item['price']}")

Node.js

const fs = require("fs");

const form = new FormData();
form.append("file", fs.createReadStream("receipt.jpg"));
form.append("schema", "receipt");

const response = await fetch("https://api.parse.conversiontools.io/v1/extract", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
  },
  body: form,
});

const { data } = await response.json();
console.log(`Store: ${data.store_name}`);
console.log(`Total: ${data.total}`);
console.log(`Paid with: ${data.payment_method}`);

data.items.forEach((item) => {
  console.log(`  - ${item.name}: ${item.price}`);
});

Sample Output

{
  "success": true,
  "id": "ext_rcp_001",
  "data": {
    "store_name": "Fresh Market Grocery",
    "store_address": "456 Oak Street, Portland, OR 97201",
    "date": "2024-01-20",
    "items": [
      {
        "name": "Organic Bananas",
        "quantity": 1,
        "price": 2.49
      },
      {
        "name": "Whole Wheat Bread",
        "quantity": 1,
        "price": 4.99
      },
      {
        "name": "Almond Milk 64oz",
        "quantity": 2,
        "price": 7.98
      },
      {
        "name": "Free Range Eggs (12ct)",
        "quantity": 1,
        "price": 5.49
      }
    ],
    "subtotal": 20.95,
    "tax": 1.68,
    "total": 22.63,
    "payment_method": "Visa ending in 4242"
  },
  "pages_used": 1,
  "confidence": 0.94
}

Tips for Receipt Parsing

Thermal paper receipts fade over time — scan or photograph them promptly for best results
For photographed receipts, ensure even lighting and avoid shadows for best accuracy
Handwritten receipts are supported but may have lower confidence scores
JPEG and PNG image formats are both supported — use PNG for higher quality scans