Update app.py

app.py

@@ -10,6 +10,8 @@ import dash_bootstrap_components as dbc
 from pydub import AudioSegment
 import requests
 from pytube import YouTube
+import mimetypes
+import urllib.parse
 
 # Configure logging
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
@@ -81,43 +83,65 @@ def process_media(file_path, is_url=False):
     wav_path = None
     try:
         if is_url:
+            logger.info(f"Processing URL: {file_path}")
             if 'youtube.com' in file_path or 'youtu.be' in file_path:
-                yt = YouTube(file_path)
-                stream = yt.streams.filter(progressive=True, file_extension='mp4').order_by('resolution').desc().first()
-                temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.mp4')
-                stream.download(output_path=os.path.dirname(temp_file.name), filename=os.path.basename(temp_file.name))
+                try:
+                    yt = YouTube(file_path)
+                    stream = yt.streams.filter(progressive=True, file_extension='mp4').order_by('resolution').desc().first()
+                    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.mp4')
+                    stream.download(output_path=os.path.dirname(temp_file.name), filename=os.path.basename(temp_file.name))
+                    logger.info(f"YouTube video downloaded: {temp_file.name}")
+                except Exception as e:
+                    logger.error(f"Error downloading YouTube video: {str(e)}")
+                    return f"Error downloading YouTube video: {str(e)}", False
             else:
-                response = requests.get(file_path)
-                content_type = response.headers.get('content-type', '')
-                if 'audio' in content_type:
-                    suffix = '.mp3'
-                elif 'video' in content_type:
-                    suffix = '.mp4'
-                else:
-                    suffix = ''
-                temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=suffix)
-                temp_file.write(response.content)
-                temp_file.close()
+                try:
+                    response = requests.get(file_path)
+                    response.raise_for_status()
+                    content_type = response.headers.get('content-type', '')
+                    logger.info(f"URL content type: {content_type}")
+                    
+                    # Determine file extension from URL or content type
+                    url_path = urllib.parse.urlparse(file_path).path
+                    ext = os.path.splitext(url_path)[1]
+                    if not ext:
+                        ext = mimetypes.guess_extension(content_type) or ''
+                    
+                    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=ext)
+                    temp_file.write(response.content)
+                    temp_file.close()
+                    logger.info(f"URL content downloaded: {temp_file.name}")
+                except Exception as e:
+                    logger.error(f"Error downloading URL content: {str(e)}")
+                    return f"Error downloading URL content: {str(e)}", False
         else:
+            logger.info("Processing uploaded file")
             temp_file = tempfile.NamedTemporaryFile(delete=False)
             temp_file.write(file_path)
             temp_file.close()
+            logger.info(f"Uploaded file saved: {temp_file.name}")
 
         file_extension = os.path.splitext(temp_file.name)[1].lower()
+        logger.info(f"Detected file extension: {file_extension}")
         
         if file_extension in VIDEO_FORMATS:
+            logger.info("Processing video file")
             video = VideoFileClip(temp_file.name)
             audio = video.audio
             wav_path = temp_file.name + ".wav"
             audio.write_audiofile(wav_path)
             video.close()
-        elif file_extension in AUDIO_FORMATS:
-            audio = AudioSegment.from_file(temp_file.name)
+        elif file_extension in AUDIO_FORMATS or not file_extension:
+            logger.info("Processing audio file")
+            audio = AudioSegment.from_file(temp_file.name, format=file_extension[1:] if file_extension else None)
             wav_path = temp_file.name + ".wav"
             audio.export(wav_path, format="wav")
         else:
+            logger.error(f"Unsupported file format: {file_extension}")
             return f"Unsupported file format: {file_extension}. Please upload a supported audio or video file.", False
 
+        logger.info(f"Audio extracted to WAV: {wav_path}")
+
         with open(wav_path, "rb") as audio_file:
             transcript = openai.Audio.transcribe("whisper-1", audio_file)
             audio_file.seek(0)
@@ -134,6 +158,7 @@ def process_media(file_path, is_url=False):
         
         transcription_text = formatted_transcript
         generated_file = io.BytesIO(transcription_text.encode())
+        logger.info("Transcription and diarization completed successfully")
         return "Transcription and diarization completed successfully!", True
     except Exception as e:
         logger.error(f"Error during processing: {str(e)}")