Update app.py

app.py

@@ -88,63 +88,57 @@ def process_audio():
             print(f"Temporary WAV file deleted: {temp_audio_path}")
 
 
-# @app.route('/process-youtube', methods=['POST'])
-# def process_youtube():
-#     youtube_url = request.json.get('youtube_url')
 
-#     if not youtube_url:
-#         return jsonify({"error": "No YouTube URL provided"}), 400
 
-#     try:
-
-        
-#         # Extract the video ID from the YouTube URL
-#         video_id = youtube_url.split("v=")[-1].split("&")[0]
-
-#         # Fetch the transcript for the given video ID
-#         transcript_data = YouTubeTranscriptApi.get_transcript(video_id)
-
-#         # Print transcript to console
-#         print(f"Transcript for video ID {video_id}:")
-#         transcript = " ".join([segment['text'] for segment in transcript_data])
-
-        
-
-#         # Send the transcript to the Gemini API for structured data
-#         structured_data = query_gemini_api(transcript)
-    
-
-#         # Return the structured data
-#         return jsonify(structured_data)
+import logging
+logging.basicConfig(level=logging.DEBUG)
 
-#     except Exception as e:
-#         return jsonify({"error": str(e)}), 500
+from urllib.parse import urlparse, parse_qs
 
+def extract_video_id(youtube_url):
+    """
+    Extracts the video ID from a YouTube URL.
+    """
+    try:
+        parsed_url = urlparse(youtube_url)
+        query_params = parse_qs(parsed_url.query)
+        video_id = query_params.get('v', [None])[0]
+        return video_id
+    except Exception as e:
+        print(f"Error extracting video ID: {e}")
+        return None
 
-import logging
-logging.basicConfig(level=logging.DEBUG)
 
 @app.route('/process-youtube', methods=['POST'])
 def process_youtube():
     youtube_url = request.json.get('youtube_url')
-
+    
     if not youtube_url:
         return jsonify({"error": "No YouTube URL provided"}), 400
 
     try:
         # Extract the video ID from the YouTube URL
-        video_id = youtube_url.split("v=")[-1].split("&")[0]
+        video_id = extract_video_id(youtube_url)
+        
         logging.debug(f"Processing video ID: {video_id}")
-
+        
         try:
             # Fetch transcript
-            transcript_data = YouTubeTranscriptApi.get_transcript(video_id)
+            # transcript_data = YouTubeTranscriptApi.get_transcript(video_id)
+            transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
+            for transcript in transcript_list:
+                # translating the transcript will return another transcript object
+                req_transcript = transcript.translate('en').fetch())
+
+            transcript = req[0].get('text')
+            
+
         except Exception as e:
             logging.error(f"Error fetching transcript for {video_id}: {e}")
             return jsonify({"error": f"Could not retrieve transcript for video {video_id}: {str(e)}"}), 500
 
         # Concatenate transcript
-        transcript = " ".join([segment['text'] for segment in transcript_data])
+        # transcript = " ".join([segment['text'] for segment in transcript_data])
         logging.debug(f"Transcript: {transcript}")
 
         # Send to Gemini API