Update app.py

app.py

@@ -1,33 +1,152 @@
-from simple_salesforce import Salesforce
-import requests
+
+
 import os
+import cv2
+from google.oauth2 import service_account
+from googleapiclient.discovery import build
+from googleapiclient.http import MediaIoBaseDownload, MediaFileUpload
+import io
+import time
+from PIL import Image
+
+# Load Google Drive API credentials
+SCOPES = ['https://www.googleapis.com/auth/drive']
+SERVICE_ACCOUNT_FILE = r'C:\Users\Ajaya\Downloads\salesforce-api-439514-d6b432a2e20e.json'  # Use raw string to avoid Unicode escape issues
+credentials = service_account.Credentials.from_service_account_file(SERVICE_ACCOUNT_FILE, scopes=SCOPES)
+drive_service = build('drive', 'v3', credentials=credentials)
+
+# Folder IDs
+aadhar_folder_id = '1jXklVbxTni1gnduuKgJ7zI6zVks6s0LP'
+cphotos_folder_id = '1JVJMtHuIHxZyxAekT6ZQFkEWePOimIlX'
+suspects_folder_id = '1LJE5aw_g5Jvqd5cLZ7UiJ8LyR36JkBKP'
+
+def list_files_in_folder(folder_id):
+    print(f"Listing files in folder ID: {folder_id}")
+    query = f"'{folder_id}' in parents and trashed=false"
+    try:
+        results = drive_service.files().list(q=query, pageSize=1000, fields="files(id, name, mimeType, owners, parents)").execute()
+        files = results.get('files', [])
+        if not files:
+            print(f"No files found in folder ID: {folder_id}. Ensure that the folder has files and the service account has access.")
+        else:
+            print(f"Found {len(files)} files in folder ID: {folder_id}.")
+            for file in files:
+                print(f"Found file: Name={file['name']}, ID={file['id']}, Type={file['mimeType']}, Owner={file['owners'][0]['displayName']}, Parent Folder ID={file['parents']}")
+        return files
+    except Exception as e:
+        print(f"Error listing files in folder ID: {folder_id} - {e}")
+        return []
+
+def download_file(file_id, file_name):
+    print(f"Attempting to download file: {file_name} (ID: {file_id})")
+    # Add extension if missing (assuming files are images)
+    if not file_name.lower().endswith(('.jpg', '.jpeg', '.png')):
+        file_name += ".jpg"
+    try:
+        request = drive_service.files().get_media(fileId=file_id)
+        file_io = io.BytesIO()
+        downloader = MediaIoBaseDownload(file_io, request)
+        done = False
+        while not done:
+            _, done = downloader.next_chunk()
+        file_io.seek(0)
+        with open(file_name, 'wb') as f:
+            f.write(file_io.read())
+        print(f"Successfully downloaded file: {file_name}")
+        return file_name
+    except Exception as e:
+        print(f"Error downloading file ID: {file_id} - {e}")
+        return None
+
+def verify_and_fix_image(image_path):
+    try:
+        with Image.open(image_path) as img:
+            img.verify()  # Verify if the image is corrupt
+        # Reopen and save to ensure it's clean
+        with Image.open(image_path) as img:
+            img.save(image_path)
+        print(f"Image verified and cleaned: {image_path}")
+        return True
+    except Exception as e:
+        print(f"Image verification failed for {image_path}. Error: {e}")
+        return False
+
+def upload_file(file_path, folder_id):
+    print(f"Uploading file: {file_path} to folder ID: {folder_id}")
+    file_metadata = {'name': os.path.basename(file_path), 'parents': [folder_id]}
+    media = MediaFileUpload(file_path, resumable=True)
+    try:
+        file = drive_service.files().create(body=file_metadata, media_body=media, fields='id').execute()
+        print(f"Uploaded file ID: {file.get('id')}")
+        return file.get('id')
+    except Exception as e:
+        print(f"Error uploading file {file_path} to folder ID: {folder_id} - {e}")
+        return None
+
+def detect_face(image_path):
+    print(f"Detecting faces in image: {image_path}")
+    face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error reading image: {image_path}. The file may not be a valid image.")
+        return False
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5)
+    face_detected = len(faces) > 0
+    print(f"Faces detected: {face_detected} in image: {image_path}")
+    return face_detected
+
+def process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id):
+    print("Starting processing of images...")
+    aadhar_files = list_files_in_folder(aadhar_folder_id)
+    cphotos_files = list_files_in_folder(cphotos_folder_id)
+
+    aadhar_faces = []
+    for file in aadhar_files:
+        print(f"Processing Aadhar file: {file['name']}")
+        file_path = download_file(file['id'], file['name'])
+        if file_path and verify_and_fix_image(file_path) and detect_face(file_path):
+            img = cv2.imread(file_path)
+            gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+            face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
+            faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5)
+            if len(faces) > 0:
+                aadhar_faces.append((file['name'], faces, img))
+
+    for file in cphotos_files:
+        print(f"Processing CCTV file: {file['name']}")
+        file_path = download_file(file['id'], file['name'])
+        if not file_path or not verify_and_fix_image(file_path):
+            continue
+        matched = False
+        if detect_face(file_path):
+            img_c = cv2.imread(file_path)
+            gray_c = cv2.cvtColor(img_c, cv2.COLOR_BGR2GRAY)
+            face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
+            faces_c = face_cascade.detectMultiScale(gray_c, scaleFactor=1.1, minNeighbors=5)
+            if len(faces_c) > 0:
+                for aadhar_name, aadhar_face_regions, aadhar_img in aadhar_faces:
+                    for (x, y, w, h) in aadhar_face_regions:
+                        aadhar_face = aadhar_img[y:y+h, x:x+w]
+                        for (xc, yc, wc, hc) in faces_c:
+                            cctv_face = img_c[yc:yc+hc, xc:xc+wc]
+                            if aadhar_face.shape == cctv_face.shape and not (cv2.subtract(aadhar_face, cctv_face).any()):
+                                matched = True
+                                print(f"Match found for file: {file['name']} with Aadhar file: {aadhar_name}")
+                                break
+                    if matched:
+                        break
+        if not matched:
+            upload_file(file_path, suspects_folder_id)
+            print(f"Unmatched image uploaded: {file['name']}")
+    print("Processing of images completed.")
+
+def main():
+    start_time = time.time()
+    print("Script started...")
+    process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id)
+    end_time = time.time()
+    print(f"Script completed in {end_time - start_time:.2f} seconds.")
 
-# Salesforce credentials
-sf = Salesforce(username='alwaysajay411@gmail.com', 
-                password='Anusha@310819', 
-                security_token='GsGDq6g2ft5klfVfD53NFG4kA',
-                domain='login')
-
-# Query Salesforce custom object for image file details
-query = "SELECT Id, Name, ContentDocumentId FROM CustomerData__c"
-response = sf.query(query)
-records = response['records']
-
-# Create a folder to save images locally if it doesn't exis
-local_folder = 'salesforce_images'
-if not os.path.exists(local_folder):
-    os.makedirs(local_folder)
-# Iterate through records and download images
-for record in records:
-    file_id = record['ContentDocumentId']
-    file_details = sf.ContentDocument.get(file_id)
-    file_name = file_details['Title'] + '.' + file_details['FileExtension']
-    file_url = f'/services/data/v50.0/sobjects/ContentVersion/{file_id}/VersionData'
-    
-    # Download file content
-    file_response = requests.get(sf.base_url + file_url, headers={'Authorization': 'Bearer ' + sf.session_id})
-    
-    # Save the image file locally
-    with open(os.path.join(local_folder, file_name), 'wb') as f:
-        f.write(file_response.content)
-        print(f'Downloaded {file_name}')
+if __name__ == "__main__":
+    main()