Update app.py

app.py

@@ -421,58 +421,151 @@ def validate_youtube_url(url):
     return False, "Invalid YouTube URL format"
 
 def process_video(url, cookies_file, progress=gr.Progress()):
-    """Main function to process YouTube video"""
+    """Main function to process YouTube video with detailed debugging"""
+    
+    # Detailed debugging info
+    debug_info = []
+    debug_info.append(f"🔍 Starting process at {time.strftime('%H:%M:%S')}")
+    debug_info.append(f"📡 Python version: {sys.version.split()[0]}")
+    debug_info.append(f"📦 yt-dlp available: {YT_DLP_AVAILABLE}")
+    debug_info.append(f"🎙️ Whisper available: {WHISPER_AVAILABLE} (type: {WHISPER_TYPE})")
     
     # Check if required packages are available
     if not YT_DLP_AVAILABLE:
-        return "❌ Error: yt-dlp is not installed. Please install it using: pip install yt-dlp", "", "❌ Missing yt-dlp"
+        error_msg = "❌ ERROR: yt-dlp is not installed properly.\n\n"
+        error_msg += "SOLUTION: Install yt-dlp using:\n"
+        error_msg += "pip install yt-dlp\n\n"
+        error_msg += "DEBUG INFO:\n" + "\n".join(debug_info)
+        return error_msg, "", "❌ Missing yt-dlp"
     
     if not WHISPER_AVAILABLE:
-        return "❌ Error: OpenAI Whisper is not installed. Please install it using: pip install openai-whisper", "", "❌ Missing Whisper"
+        error_msg = "❌ ERROR: OpenAI Whisper is not installed properly.\n\n"
+        error_msg += "SOLUTION: Install Whisper using:\n"
+        error_msg += "pip install openai-whisper\n"
+        error_msg += "OR\n"
+        error_msg += "pip install transformers torch torchaudio\n\n"
+        error_msg += "DEBUG INFO:\n" + "\n".join(debug_info)
+        return error_msg, "", "❌ Missing Whisper"
     
     # Validate URL
     is_valid, validation_msg = validate_youtube_url(url)
     if not is_valid:
-        return f"❌ Error: {validation_msg}", "", "❌ Invalid URL"
+        error_msg = f"❌ ERROR: {validation_msg}\n\n"
+        error_msg += f"PROVIDED URL: {url}\n\n"
+        error_msg += "VALID URL FORMATS:\n"
+        error_msg += "• https://www.youtube.com/watch?v=VIDEO_ID\n"
+        error_msg += "• https://youtu.be/VIDEO_ID\n"
+        error_msg += "• https://www.youtube.com/embed/VIDEO_ID\n\n"
+        error_msg += "DEBUG INFO:\n" + "\n".join(debug_info)
+        return error_msg, "", "❌ Invalid URL"
     
     audio_path = None
     cookies_temp_path = None
     
     try:
         progress(0.05, desc="🔍 Validating URL...")
+        debug_info.append(f"✅ URL validation passed: {url}")
         
         # Process cookies file if provided
         progress(0.1, desc="🍪 Processing cookies...")
         cookies_temp_path = process_cookies_file(cookies_file)
         
+        if cookies_temp_path:
+            debug_info.append(f"✅ Cookies processed: {cookies_temp_path}")
+        else:
+            debug_info.append("⚠️ No cookies provided - this may cause access errors")
+        
         status_msg = "✅ Cookies loaded" if cookies_temp_path else "⚠️ No cookies (may encounter restrictions)"
         
+        # First, try to get video info for debugging
+        progress(0.15, desc="🔍 Checking video accessibility...")
+        try:
+            video_info = get_video_info(url, cookies_temp_path)
+            if 'error' in video_info:
+                debug_info.append(f"❌ Video info error: {video_info['error']}")
+                raise Exception(f"Video accessibility check failed: {video_info['error']}")
+            else:
+                debug_info.append(f"✅ Video info: {video_info}")
+        except Exception as e:
+            debug_info.append(f"❌ Video info check failed: {str(e)}")
+            # Continue anyway, but log the issue
+        
         # Download audio
         progress(0.2, desc="📥 Downloading audio...")
+        debug_info.append("🔄 Starting audio download...")
         audio_path = download_audio(url, cookies_temp_path)
+        debug_info.append(f"✅ Audio downloaded: {audio_path}")
+        
+        # Check if audio file exists and get size
+        if audio_path and os.path.exists(audio_path):
+            file_size = os.path.getsize(audio_path)
+            debug_info.append(f"📊 Audio file size: {file_size/1024/1024:.2f} MB")
+        else:
+            raise Exception("Audio file not found after download")
         
         # Transcribe audio
         progress(0.6, desc="🎙️ Transcribing audio...")
+        debug_info.append("🔄 Starting transcription...")
         transcript = transcribe_audio(audio_path)
+        debug_info.append(f"✅ Transcription completed: {len(transcript)} characters")
         
         if not transcript.strip():
-            return "❌ No speech detected in the video", "", "❌ No speech detected"
+            error_msg = "❌ ERROR: No speech detected in the video\n\n"
+            error_msg += "POSSIBLE CAUSES:\n"
+            error_msg += "• Video has no audio track\n"
+            error_msg += "• Audio is too quiet or unclear\n"
+            error_msg += "• Video is not in English\n"
+            error_msg += "• Audio file is corrupted\n\n"
+            error_msg += "DEBUG INFO:\n" + "\n".join(debug_info)
+            return error_msg, "", "❌ No speech detected"
         
         # Extract stock information
         progress(0.9, desc="📊 Analyzing content...")
+        debug_info.append("🔄 Starting stock analysis...")
         stock_details = extract_stock_info_enhanced(transcript)
+        debug_info.append("✅ Stock analysis completed")
         
         progress(1.0, desc="✅ Complete!")
-        return transcript, stock_details, "✅ Processing completed successfully"
+        
+        # Add debug info to transcript
+        debug_section = "\n\n" + "="*50 + "\n"
+        debug_section += "🔍 DEBUG INFORMATION\n"
+        debug_section += "="*50 + "\n"
+        debug_section += "\n".join(debug_info)
+        
+        return transcript + debug_section, stock_details, "✅ Processing completed successfully"
         
     except Exception as e:
-        error_msg = str(e)
-        return error_msg, "", f"❌ Error occurred"
+        error_msg = f"❌ DETAILED ERROR INFORMATION:\n\n"
+        error_msg += f"ERROR MESSAGE: {str(e)}\n\n"
+        error_msg += f"ERROR TYPE: {type(e).__name__}\n\n"
+        
+        # Add context based on where the error occurred
+        if "download" in str(e).lower():
+            error_msg += "🔧 DOWNLOAD TROUBLESHOOTING:\n"
+            error_msg += "• Check if video URL is accessible in browser\n"
+            error_msg += "• Upload fresh cookies.txt file\n"
+            error_msg += "• Try a different video\n"
+            error_msg += "• Wait 10-15 minutes if rate limited\n\n"
+        elif "transcribe" in str(e).lower():
+            error_msg += "🔧 TRANSCRIPTION TROUBLESHOOTING:\n"
+            error_msg += "• Check if audio file was downloaded properly\n"
+            error_msg += "• Ensure video has clear audio\n"
+            error_msg += "• Try a shorter video\n\n"
+        
+        error_msg += "📊 PROCESSING STEPS COMPLETED:\n"
+        error_msg += "\n".join(debug_info)
+        
+        return error_msg, "", f"❌ Error: {type(e).__name__}"
     
     finally:
         # Clean up temporary files
-        cleanup_file(audio_path)
-        cleanup_file(cookies_temp_path)
+        if audio_path:
+            debug_info.append(f"🗑️ Cleaning up: {audio_path}")
+            cleanup_file(audio_path)
+        if cookies_temp_path:
+            debug_info.append(f"🗑️ Cleaning up: {cookies_temp_path}")
+            cleanup_file(cookies_temp_path)
 
 # Create Gradio interface optimized for Gradio Cloud
 with gr.Blocks(
@@ -545,9 +638,23 @@ with gr.Blocks(
             with gr.Group():
                 gr.Markdown("### 📥 Input")
                 
+                # Add a test button first
+                test_btn = gr.Button(
+                    "🧪 Test System (Click First!)", 
+                    variant="secondary",
+                    size="sm"
+                )
+                
+                test_output = gr.Textbox(
+                    label="🧪 System Test Results",
+                    lines=5,
+                    visible=False,
+                    interactive=False
+                )
+                
                 # Cookies upload with better instructions
                 cookies_input = gr.File(
-                    label="🍪 Upload Cookies File (cookies.txt) - REQUIRED",
+                    label="🍪 Upload Cookies File (cookies.txt) - HIGHLY RECOMMENDED",
                     file_types=[".txt"],
                     file_count="single"
                 )
@@ -588,7 +695,7 @@ with gr.Blocks(
                 # Status display
                 status_output = gr.Textbox(
                     label="📊 Status",
-                    lines=1,
+                    lines=3,
                     interactive=False,
                     info="Current processing status"
                 )
@@ -673,11 +780,62 @@ with gr.Blocks(
         status = check_requirements()
         return gr.update(value=status, visible=True)
     
+    def test_system():
+        """Test system components and return detailed status"""
+        test_results = []
+        test_results.append("🧪 SYSTEM TEST RESULTS")
+        test_results.append("="*30)
+        
+        # Test imports
+        test_results.append(f"✅ yt-dlp: {'Available' if YT_DLP_AVAILABLE else 'NOT AVAILABLE'}")
+        test_results.append(f"✅ Whisper: {'Available' if WHISPER_AVAILABLE else 'NOT AVAILABLE'} (Type: {WHISPER_TYPE})")
+        
+        # Test yt-dlp functionality
+        if YT_DLP_AVAILABLE:
+            try:
+                from yt_dlp import YoutubeDL
+                test_ydl = YoutubeDL({'quiet': True})
+                test_results.append("✅ yt-dlp: Can create YoutubeDL instance")
+            except Exception as e:
+                test_results.append(f"❌ yt-dlp: Error creating instance - {str(e)}")
+        
+        # Test Whisper functionality
+        if WHISPER_AVAILABLE:
+            try:
+                if WHISPER_TYPE == "openai-whisper":
+                    import whisper
+                    test_results.append("✅ Whisper: OpenAI Whisper can be imported")
+                elif WHISPER_TYPE == "transformers":
+                    from transformers import pipeline
+                    test_results.append("✅ Whisper: Transformers Whisper can be imported")
+            except Exception as e:
+                test_results.append(f"❌ Whisper: Error testing - {str(e)}")
+        
+        # Test file operations
+        try:
+            temp_file = tempfile.mktemp()
+            with open(temp_file, 'w') as f:
+                f.write("test")
+            os.remove(temp_file)
+            test_results.append("✅ File operations: Working")
+        except Exception as e:
+            test_results.append(f"❌ File operations: Error - {str(e)}")
+        
+        test_results.append("\n💡 If you see any ❌ errors above, install missing packages:")
+        test_results.append("pip install yt-dlp openai-whisper torch torchaudio")
+        
+        return gr.update(value="\n".join(test_results), visible=True)
+    
     check_req_btn.click(
         fn=show_requirements,
         outputs=[requirements_output]
     )
     
+    test_btn.click(
+        fn=test_system,
+        outputs=[test_output]
+    )
+    
     process_btn.click(
         fn=process_video,
         inputs=[url_input, cookies_input],