dlmw/julius_baer_onboarding
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add Account OCR

Browse Source
This commit is contained in:
robinrolle
2025-04-12 09:11:25 +02:00
parent d64bf40d46
commit 2328be999f
1 changed files with 26 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
poc_ocr.py
View File

@ -5,6 +5,9 @@ from PIL import Image
import pytesseract import pytesseract
import io import io
import xml.etree.ElementTree as ET import xml.etree.ElementTree as ET
import base64
import io
import pymupdf
from pathlib import Path from pathlib import Path
# === Configuration API === # === Configuration API ===
@ -23,6 +26,8 @@ payload = {
response = requests.post(api_url, headers=headers, json=payload) response = requests.post(api_url, headers=headers, json=payload)
response_data = response.json() response_data = response.json()
print(response_data)
# === Traitement du passeport === # === Traitement du passeport ===
passport_b64 = response_data["client_data"]["passport"] passport_b64 = response_data["client_data"]["passport"]
image_bytes = base64.b64decode(passport_b64) image_bytes = base64.b64decode(passport_b64)
@ -84,4 +89,24 @@ if document_path in zip_file.namelist():
else: else:
print(full_text) print(full_text)
else: else:
print("Le fichier 'word/document.xml' est introuvable dans le profil.") print("Le fichier 'word/document.xml' est introuvable dans le profil.")
# === Traitement du fichier account (PDF) avec PyMuPDF ===
print("\n=== Texte extrait depuis le fichier ACCOUNT (via PyMuPDF) ===\n")
import base64
from pdf2image import convert_from_bytes
import pytesseract
# Décode ton PDF base64
account_b64 = response_data["client_data"].get("account")
pdf_bytes = base64.b64decode(account_b64)
# Convertit chaque page en image
images = convert_from_bytes(pdf_bytes)
# Applique OCR avec pytesseract
for i, image in enumerate(images):
text = pytesseract.image_to_string(image, lang="eng")
print(f"--- Page {i + 1} ---")
print(text)