Update app.py

app.py

@@ -1,3 +1,6 @@
+# First install required packages (this should be at the very top)
+!pip install --upgrade gradio yt-dlp openai-whisper transformers ffmpeg-python pydub
+
 import gradio as gr
 from transformers import pipeline
 import yt_dlp
@@ -7,76 +10,166 @@ import requests
 import uuid
 import re
 
-# [Keep all your existing functions here: clean_old_files, download_video, 
-# download_direct_video, extract_audio, transcribe_audio, classify_content, is_tiktok_url]
+# Delete old files
+def clean_old_files():
+    files = ["video.mp4", "audio.mp3", "transcription.txt"]
+    for file in files:
+        if os.path.exists(file):
+            os.remove(file)
+
+# Download TikTok video
+def download_video(video_url):
+    unique_name = f"video_{uuid.uuid4().hex[:8]}.mp4"
+    
+    ydl_opts = {
+        'format': 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]',
+        'outtmpl': unique_name,
+        'quiet': True,
+        'no_warnings': True,
+        'extractor_args': {
+            'tiktok': {
+                'skip_watermark': True
+            }
+        }
+    }
+    
+    try:
+        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+            ydl.download([video_url])
+        return unique_name
+    except Exception as e:
+        print(f"Error downloading video: {e}")
+        return None
 
+# Extract audio from video
+def extract_audio(video_path):
+    audio_path = "audio.mp3"
+    os.system(f"ffmpeg -i \"{video_path}\" -vn -acodec libmp3lame -q:a 3 \"{audio_path}\" -y")
+    if not os.path.exists(audio_path):
+        raise RuntimeError("Error: Failed to extract audio.")
+    return audio_path
+
+# Convert audio to text
+def transcribe_audio(audio_path):
+    try:
+        model = whisper.load_model("base")
+        result = model.transcribe(audio_path)
+        return result['text']
+    except Exception as e:
+        return f"Transcription error: {str(e)}"
+
+# Classify content
+def classify_content(text):
+    try:
+        if not text or len(text.strip()) == 0:
+            return "No text to classify"
+            
+        classifier = pipeline("zero-shot-classification", 
+                           model="facebook/bart-large-mnli")
+        
+        labels = ["Challenge", "Comedy", "Dance", "Educational", "TikTok Trend", 
+                "Music", "Lifestyle", "Beauty", "Cooking", "Fashion"]
+        
+        clean_text = ' '.join(text.split()[:500])
+        result = classifier(clean_text, 
+                          candidate_labels=labels, 
+                          hypothesis_template="This content is about {}.")
+        
+        return f"{result['labels'][0]} (Confidence: {result['scores'][0]:.2f})"
+    except Exception as e:
+        return f"Classification error: {str(e)}"
+
+# Main video processing function
 def process_video(video_url):
     try:
         clean_old_files()
         
-        if video_url.endswith(".mp4"):
-            video_path = video_url
-        elif is_tiktok_url(video_url):
-            print("Downloading video from TikTok...")
-            video_path = download_video(video_url)
-        elif "youtube.com" in video_url or "youtu.be" in video_url:
-            print("Downloading video from YouTube...")
-            video_path = download_video(video_url)
-        else:
-            print("Downloading video from direct link...")
-            video_path = download_direct_video(video_url)
+        if not video_url or len(video_url.strip()) == 0:
+            return ["Please enter a valid video URL", "", None, None]
+        
+        if "tiktok.com" not in video_url and "vm.tiktok.com" not in video_url:
+            return ["This app is for TikTok links only", "", None, None]
+        
+        print(f"Downloading video: {video_url}")
+        video_path = download_video(video_url)
         
-        if not video_path or not os.path.exists(video_path):
-            return "Error: Failed to download video."
+        if not video_path:
+            return ["Failed to download video. Please check the URL.", "", None, None]
         
         print("Extracting audio...")
         audio_path = extract_audio(video_path)
         
-        print("Transcribing...")
+        print("Transcribing audio...")
         transcription = transcribe_audio(audio_path)
         
         print("Classifying content...")
         category = classify_content(transcription)
         
-        return {
-            "transcription": transcription,
-            "category": category,
-            "video_path": video_path,
-            "audio_path": audio_path
-        }
+        return [transcription, category, video_path, audio_path]
+        
     except Exception as e:
-        return f"Error processing video: {str(e)}"
+        return [f"Processing error: {str(e)}", "", None, None]
 
-# Gradio Interface
-with gr.Blocks(title="Video Content Analyzer") as demo:
+# Gradio interface
+with gr.Blocks(title="TikTok Content Analyzer") as demo:
     gr.Markdown("""
-    # 🎥 Video Content Analyzer
-    Analyze videos from TikTok, YouTube, or direct links. Get transcription and content classification.
+    # 🎬 TikTok Content Analyzer
+    Enter a TikTok video URL to get transcription and content classification
     """)
     
     with gr.Row():
-        url_input = gr.Textbox(label="Video URL", placeholder="Enter TikTok, YouTube or direct video URL...")
-        submit_btn = gr.Button("Analyze", variant="primary")
+        url_input = gr.Textbox(
+            label="TikTok URL",
+            placeholder="Enter TikTok video URL here...",
+            scale=4
+        )
+        submit_btn = gr.Button("Analyze Video", variant="primary", scale=1)
     
     with gr.Row():
         with gr.Column():
-            transcription_output = gr.Textbox(label="Transcription", interactive=False)
-            category_output = gr.Textbox(label="Content Category", interactive=False)
+            transcription_output = gr.Textbox(
+                label="Extracted Text",
+                interactive=True,
+                lines=10,
+                max_lines=20
+            )
+            category_output = gr.Textbox(
+                label="Content Category",
+                interactive=False
+            )
         
         with gr.Column():
-            video_preview = gr.Video(label="Downloaded Video")
-            audio_preview = gr.Audio(label="Extracted Audio")
+            video_preview = gr.Video(
+                label="Downloaded Video",
+                interactive=False
+            )
+            audio_preview = gr.Audio(
+                label="Extracted Audio",
+                interactive=False
+            )
+    
+    # TikTok URL examples
+    gr.Examples(
+        examples=[
+            ["https://www.tiktok.com/@example/video/123456789"],
+            ["https://www.tiktok.com/@user2/video/987654321"],
+            ["https://vm.tiktok.com/ZMexample/"]
+        ],
+        inputs=url_input,
+        label="Try these examples"
+    )
     
+    # Button click event
     submit_btn.click(
         fn=process_video,
         inputs=url_input,
-        outputs={
-            "transcription": transcription_output,
-            "category": category_output,
-            "video_path": video_preview,
-            "audio_path": audio_preview
-        }
+        outputs=[transcription_output, category_output, video_preview, audio_preview]
     )
 
+# Launch the app
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)
+    demo.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=False
+    )