Update app.py

app.py

@@ -131,7 +131,7 @@ def clean_ocr_text(text):
     cleaned_text = '\n'.join([line.strip() for line in cleaned_text.splitlines() if len(line.strip()) > 2])
     return cleaned_text
 
-def get_information_from_video_using_OCR(video_path, interval=1):
+def get_information_from_video_using_OCR(video_path, interval=2):
     """Extract text from video frames using OCR and return the combined text content."""
     cap = cv2.VideoCapture(video_path)
     fps = int(cap.get(cv2.CAP_PROP_FPS))
@@ -147,12 +147,17 @@ def get_information_from_video_using_OCR(video_path, interval=1):
             break
 
         if frame_count % frame_interval == 0:
-            preprocessed_frame = preprocess_frame(frame)
+            timestamp = frame_count / fps  # Calculate timestamp in seconds
+            preprocessed_frame = preprocess_frame(frame)  # Preprocess the frame
+
+            # Perform OCR on the preprocessed frame
             text = pytesseract.image_to_string(preprocessed_frame, lang='eng', config='--psm 6 --oem 3')
             cleaned_text = clean_ocr_text(text)
-            if cleaned_text:
-                extracted_text += cleaned_text + "\n\n"
-                # print(f"Text found at frame {frame_count}: {cleaned_text[:50]}...")
+
+            if cleaned_text:  # Only save non-empty results
+                with open(output_file, 'a', encoding='utf-8') as f:
+                    f.write(cleaned_text + "\n\n")
+                print(f"Extracted text at {timestamp:.2f} seconds")
 
         frame_count += 1
 
@@ -183,7 +188,7 @@ def process_video():
             download_video(video_url, temp_video_path)
 
         # Step 2: Get the information from the downloaded MP4 file synchronously
-        video_info = get_information_from_video_using_OCR(temp_video_path, interval=1)
+        video_info = get_information_from_video_using_OCR(temp_video_path, interval=2)
 
         if not video_info:
             video_info = ""
@@ -233,8 +238,8 @@ def query_gemini_api(video_transcription, audio_transcription):
             "3. Steps for Preparation: Provide a step-by-step breakdown of the recipe's preparation process, organized and numbered sequentially.\n"
             "4. Cooking Techniques Used: Highlight the cooking techniques demonstrated in the video, such as searing, blitzing, wrapping, etc.\n"
             "5. Equipment Needed: List all tools, appliances, or utensils mentioned, e.g., blender, hot pan, cling film, etc.\n"
-            "6. Nutritional Information (if inferred): Provide an approximate calorie count or nutritional breakdown based on the ingredients used.\n"
-            "7. Serving size: In count of people or portion size.\n"
+            "6. Nutritional Information (if inferred): Provide an approximate calorie count or macro nutritional breakdown based on the recipe cooked and your understanding, the carbs, protein and other macros.\n"
+            "7. Serving size: In count of people or portion size according to you and the recipe cooked e.g., 2 people, 4 people, 2 bowls, 2 cups.\n"
             "8. Special Notes or Variations: Include any specific tips, variations, or alternatives mentioned.\n"
             "9. Festive or Thematic Relevance: Note if the recipe has any special relevance to holidays, events, or seasons.\n"
             "There are errors and missing parts in the video transcription part, if something is not able to interpret from the video information use the audio information\n"