Merge branch 'sameer'

Author: ANGELOANTU7

.DS_Store

@@ -0,0 +1,69 @@
+import os
+from fastapi import APIRouter
+from pdf2image import convert_from_path
+from google.cloud import vision
+
+# Create an instance of APIRouter
+router = APIRouter()
+
+def pdf_to_images(pdf_path, output_folder):
+    
+    # Convert PDF pages to images
+    images = convert_from_path(pdf_path)
+
+    # Create the output folder if it doesn't exist
+    if not os.path.exists(output_folder):
+        os.makedirs(output_folder)
+
+    # Save each image in the specified output folder
+    image_paths = []
+    for i, image in enumerate(images):
+        image_path = os.path.join(output_folder, f'page_{i+1}.jpeg')
+        image.save(image_path, 'JPEG')
+        image_paths.append(image_path)
+    noImg = i+1     
+    return image_paths,noImg
+
+@router.get("/NotesToText")
+def NotesToText_handler():
+    substring_to_remove = "Scanned by CamScanner"
+    for i in range(4):
+        print(f"converting module-{i+1}....")
+        pdf_path = f'Local_Storage/notes_pdf/module_{i+1}.pdf'
+        output_folder = f'images/Notes_images/module_{i+1}'
+        
+        # Convert the PDF to images and save them in the output folder
+        image_paths, noImg = pdf_to_images(pdf_path, output_folder)
+        print(noImg)
+        
+        os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = 'Files/client_file_vision.json'
+        client = vision.ImageAnnotatorClient()
+
+        # [START vision_python_migration_text_detection]
+        image_contents = " "
+
+        for j in range(noImg):
+            image_path = f'images/Notes_images/Module_{i+1}/page_{j+1}.jpeg'   
+            with open(image_path, 'rb') as image_file:
+                content = image_file.read()
+                image = vision.Image(content=content)
+                response = client.text_detection(image=image)
+                texts = response.text_annotations[0]
+                text = str(texts.description)
+                image_contents += text.replace(substring_to_remove, "")
+
+
+        output_file = f"Local_Storage/notes_txt/module_{i+1}.txt"
+    #    Write the text content to the output file
+        with open(output_file, "w") as file:
+            file.write(image_contents)
+            print(f"module-{i+1} completed")
+              
+        if response.error.message:
+            raise Exception(
+            '{}\nFor more info on error messages, check: '
+            'https://cloud.google.com/apis/design/errors'.format(
+                response.error.message))
+
+
+

Backend/NotesToText.py

@@ -0,0 +1,13 @@
+{
+  "type": "service_account",
+  "project_id": "notes2text",
+  "private_key_id": "2fed7b9ef897663b69d3d0acf6194e99461a3506",
+  "private_key": "-----BEGIN PRIVATE KEY-----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\nAbdXeljWTGv1qc8rIZ4KS5vr\n-----END PRIVATE KEY-----\n",
+  "client_email": "[email protected]",
+  "client_id": "105405504203772246599",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/image2text%40notes2text.iam.gserviceaccount.com",
+  "universe_domain": "googleapis.com"
+}