Israel Teudat Zehut OCR API with Python

Working with the Teudat Zehut (identity card)

The biometric Teudat Zehut prints Hebrew and Arabic text with the nine-digit identity number. Re-keying these values is slow, and generic OCR still leaves your team to map each text fragment to the right field.

Structured Extraction for Your Backend

The National ID OCR API returns the identity number, names, dates, and address when they are printed on the submitted side of the card. Test it with the free ID card scanner.

Common Integration Scenarios

• Customer onboarding: Pre-fill identity fields from the Teudat Zehut (identity card) before the customer confirms them.
• Account operations: Reduce manual transcription when staff enter identity data.
• Document review: Store normalized output next to your own review decision.

Israel Teudat Zehut OCR API with Python

The official Python SDK reads a local file and calls /v1/national-id from your backend.

Prerequisite: `pip install structocr`; set the server-side `STRUCTOCR_API_KEY` environment variable.

Prefer another stack? Open the Node.js SDK + Express integration.

import os
from structocr import StructOCR

client = StructOCR(os.environ["STRUCTOCR_API_KEY"])
result = client.scan_national_id("id-card.jpg")

if result.get("success"):
    data = result["data"]
    print(data.get("document_number"))
    print(data.get("given_names"), data.get("surname"))
else:
    print(result.get("error"))

JSON Response Example

Fictional values showing the normalized shape for a readable Teudat Zehut (identity card); unavailable fields are null.

{
  "success": true,
  "data": {
    "type": "national_id",
    "country_code": "ISR",
    "document_number": "000000000",
    "personal_number": null,
    "surname": "DOE",
    "given_names": "ALEX",
    "sex": null,
    "date_of_birth": "1990-01-01",
    "place_of_birth": null,
    "date_of_issue": null,
    "date_of_expiry": null,
    "issuing_authority": null,
    "address": null,
    "additional_fields": {}
  }
}