Invoice Extraction

Extract vendor information, line items, totals, and dates from invoices. Parse handles a wide range of invoice formats including PDFs, scanned images, and multi-page documents.

Invoice Schema

Define a schema that captures the key fields from an invoice:

{
  "name": "invoice",
  "description": "Extract data from invoices",
  "fields": [
    { "name": "vendor_name", "type": "string", "description": "Company name of the vendor" },
    { "name": "vendor_address", "type": "string", "description": "Address of the vendor" },
    { "name": "invoice_number", "type": "string", "description": "Invoice reference number" },
    { "name": "date", "type": "date", "description": "Invoice issue date" },
    { "name": "due_date", "type": "date", "description": "Payment due date" },
    { "name": "line_items", "type": "array", "description": "List of billed items", "items": {
      "type": "object",
      "fields": [
        { "name": "description", "type": "string" },
        { "name": "quantity", "type": "number" },
        { "name": "unit_price", "type": "number" },
        { "name": "amount", "type": "number" }
      ]
    }},
    { "name": "subtotal", "type": "number", "description": "Subtotal before tax" },
    { "name": "tax", "type": "number", "description": "Tax amount" },
    { "name": "total", "type": "number", "description": "Total amount due" },
    { "name": "currency", "type": "string", "description": "Currency code (e.g. USD, EUR)" }
  ]
}

Code Examples

cURL

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

Python

import requests

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

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

data = response.json()
print(f"Vendor: {data['data']['vendor_name']}")
print(f"Total: {data['data']['currency']} {data['data']['total']}")

for item in data["data"]["line_items"]:
    print(f"  - {item['description']}: {item['amount']}")

Node.js

const fs = require("fs");

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

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(`Vendor: ${data.vendor_name}`);
console.log(`Total: ${data.currency} ${data.total}`);

data.line_items.forEach((item) => {
  console.log(`  - ${item.description}: ${item.amount}`);
});

Sample Output

{
  "success": true,
  "id": "ext_inv_001",
  "data": {
    "vendor_name": "TechSupply Inc.",
    "vendor_address": "123 Business Ave, Suite 400, San Francisco, CA 94105",
    "invoice_number": "INV-2024-0847",
    "date": "2024-01-15",
    "due_date": "2024-02-14",
    "line_items": [
      {
        "description": "Cloud Hosting - Standard Plan",
        "quantity": 1,
        "unit_price": 299.00,
        "amount": 299.00
      },
      {
        "description": "SSL Certificate - Wildcard",
        "quantity": 2,
        "unit_price": 49.99,
        "amount": 99.98
      },
      {
        "description": "Technical Support - Premium",
        "quantity": 1,
        "unit_price": 150.00,
        "amount": 150.00
      }
    ],
    "subtotal": 548.98,
    "tax": 49.41,
    "total": 598.39,
    "currency": "USD"
  },
  "pages_used": 1,
  "confidence": 0.97
}

Tips for Invoice Extraction

Multi-page invoices are supported — all pages are processed and data is combined automatically
Currency is detected automatically; add a currency field to your schema to capture it explicitly
Use the array type for line items to handle invoices with varying numbers of items
For scanned invoices, ensure the image is at least 150 DPI for best results