structocr 1.1.6

The official Python SDK for StructOCR API - Passport, ID card, Driver License OCR, Invoice, VIN and Container OCR.

StructOCR Python SDK

The official Python client for StructOCR.

StructOCR is a powerful API tailored for developers to extract structured data from identity documents with high accuracy. This SDK helps you integrate Passport OCR, National ID OCR, Driver License OCR, Invoice OCR, VIN OCR, and Container OCR into your Python applications in minutes.

👉 Get your Free API Key here

---

🚀 What's New in 1.1.6

We've massively expanded our logistics and finance capabilities! The SDK now natively supports:

• Container OCR: Accurately parse shipping container numbers from images.
• VIN OCR: Read Vehicle Identification Numbers from windshields or chassis.
• Invoice OCR: Automatically extract invoice numbers, currencies, merchants, and customers.

Check out the Quick Start below to see how easy it is to use them!

---

Features

• Passport OCR API: Instantly extract MRZ, name, DOB, and expiry date from passports of 200+ countries.
• National ID OCR: Support for ID cards with automatic field mapping.
• Driver License OCR: Extract vehicle class, license number, and personal details.
• Invoice OCR: Extract invoice number, currency, merchant, customer.
• VIN OCR: Extract VIN (Vehicle Identification Number) from windshield or engine bay images.
• Container OCR: Extract shipping container numbers accurately from images.
• Secure & Fast: Enterprise-grade encryption and sub-second response times.

Installation

Install the package via pip:

pip install structocr

Quick Start

1. Initialize the Client

from structocr import StructOCR

# Initialize with your API Key
client = StructOCR(api_key="sk_live_xxxxxxxx")

2. Scan a Passport (Passport OCR)

# Pass the path to the passport image file
result = client.scan_passport('./docs/passport_sample.jpg')

print(f"Name: {result['data']['name']}")
print(f"Passport Number: {result['data']['document_number']}")

3. Scan a National ID, Driver License, Invoice, VIN, or Container

# National ID OCR
id_data = client.scan_national_id('./docs/id_card.png')

# Driver License OCR
license_data = client.scan_driver_license('./docs/license.jpg')

# Invoice OCR
invoice_data = client.scan_invoice('./docs/invoice.jpg')

# VIN OCR
vin_data = client.scan_vin('./docs/vin.jpg')

# Container OCR
container_data = client.scan_container('./docs/container.jpg')

Documentation

For full API documentation, response examples, and error codes, please visit the StructOCR Developer Docs.

Requirements

• Python 3.6+
• requests library

License

MIT License. See LICENSE for details.