Update app.py

app.py

@@ -1,57 +1,45 @@
+from pytube import YouTube
 import streamlit as st
-import yt_dlp
-import torch
 from transformers import pipeline
+from PIL import Image
+import requests
+from io import BytesIO
 
 st.set_page_config(page_title="Video Deepfake Detector", layout="centered")
+st.title("🎥 Video Deepfake Detector")
 
-# Download video using yt-dlp
-def download_video(video_url, output_path="video.mp4"):
-    ydl_opts = {
-        'format': 'best',
-        'outtmpl': output_path,
-        'quiet': True,
-    }
-    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
-        ydl.download([video_url])
-    return output_path
+@st.cache_data
+def get_thumbnail(url):
+    try:
+        yt = YouTube(url)
+        response = requests.get(yt.thumbnail_url)
+        if response.status_code == 200:
+            return Image.open(BytesIO(response.content))
+    except Exception as e:
+        st.error(f"Error fetching thumbnail: {e}")
+    return None
 
-# Load the deepfake detection model
+@st.cache_resource
 def load_model():
-    return pipeline("image-classification", model="microsoft/resnet-50")
+    return pipeline("image-classification", model="facebook/deit-base-distilled-patch16-224")
 
-# Analyze video frames for deepfake detection
-def analyze_video(video_path, model):
-    import cv2
-    cap = cv2.VideoCapture(video_path)
-    frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
-    step = max(frame_count // 5, 1)
-    results = []
-    
-    for i in range(0, frame_count, step):
-        cap.set(cv2.CAP_PROP_POS_FRAMES, i)
-        ret, frame = cap.read()
-        if not ret:
-            continue
-        rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-        prediction = model(rgb_frame)
-        results.append(prediction[0])
-    cap.release()
+def detect_deepfake(image, model):
+    results = model(image)
     return results
 
-# Streamlit interface
-st.title("🎥 Video Deepfake Detector")
-video_url = st.text_input("Enter YouTube Video URL:")
-
-if st.button("Submit") and video_url:
-    with st.spinner("Downloading and analyzing video..."):
-        try:
-            video_path = download_video(video_url)
+def main():
+    video_url = st.text_input("Enter YouTube Video URL:")
+    if st.button("Analyze") and video_url:
+        thumbnail = get_thumbnail(video_url)
+        if thumbnail:
+            st.image(thumbnail, caption="Video Thumbnail", use_container_width=True)
             model = load_model()
-            predictions = analyze_video(video_path, model)
+            results = detect_deepfake(thumbnail, model)
+            st.subheader("Detection Results:")
+            for res in results:
+                st.write(f"{res['label']}: {res['score']:.4f}")
+        else:
+            st.warning("Unable to fetch thumbnail. Please check the video URL.")
 
-            st.success("Analysis Complete!")
-            for idx, pred in enumerate(predictions):
-                st.write(f"Frame {idx + 1}: {pred['label']} with confidence {pred['score']:.2f}")
-        except Exception as e:
-            st.error(f"Error: {e}")
+if __name__ == "__main__":
+    main()