Enhance video download functionality in Streamlit app with optional cookies support for YouTube authentication

Dockerfile

@@ -2,6 +2,11 @@ FROM python:3.9-slim
 
 WORKDIR /app
 
+# Set DNS to improve network connectivity during build
+# Using Google DNS servers for better reliability
+RUN echo "nameserver 8.8.8.8" > /etc/resolv.conf && \
+    echo "nameserver 8.8.4.4" >> /etc/resolv.conf
+
 # Install system dependencies including ffmpeg for audio processing
 RUN apt-get update && apt-get install -y \
     build-essential \
@@ -10,6 +15,8 @@ RUN apt-get update && apt-get install -y \
     git \
     ffmpeg \
     libsndfile1 \
+    ca-certificates \
+    && apt-get clean \
     && rm -rf /var/lib/apt/lists/*
 
 # Copy requirements and install Python dependencies

src/streamlit_app.py

@@ -52,12 +52,28 @@ ENGLISH_ACCENTS = {
     "en-caribbean": "Caribbean English",
 }
 
-def download_video(url, video_path="video.mp4"):
+def download_video(url, video_path="video.mp4", cookies_file=None):
     """Download a video from a URL"""
-    ydl_opts = {"outtmpl": video_path}
-    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
-        ydl.download([url])
-    return os.path.exists(video_path)
+    ydl_opts = {
+        "outtmpl": video_path,
+    }
+    
+    # Try to use provided cookies file first if it exists
+    if cookies_file and os.path.exists(cookies_file):
+        ydl_opts["cookiefile"] = cookies_file
+    else:
+        # Fall back to browser cookies
+        ydl_opts["cookiesfrombrowser"] = ("chrome",)
+    
+    try:
+        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+            ydl.download([url])
+        return os.path.exists(video_path)
+    except Exception as e:
+        st.error(f"Download error: {str(e)}")
+        if "youtube" in url.lower() and "bot" in str(e).lower():
+            st.warning("YouTube is requesting authentication. Please see the 'Having trouble with YouTube videos?' section for help.")
+        return False
 
 def extract_audio(video_path="video.mp4", audio_path="audio.wav"):
     """Extract audio from video file using ffmpeg"""
@@ -268,6 +284,31 @@ tab1, tab2 = st.tabs(["Video URL", "Upload Audio"])
 with tab1:
     url = st.text_input("Enter a public video URL (e.g. Loom, YouTube, or direct MP4 link)")
     
+    # Add file uploader for cookies.txt
+    cookies_file = None
+    uploaded_cookies = st.file_uploader("Optional: Upload cookies.txt for YouTube authentication", type="txt", help="Only needed if you have issues with YouTube videos")
+    
+    if uploaded_cookies is not None:
+        # Save the uploaded cookies file to a temporary file
+        cookies_file = f"cookies_{int(time.time())}.txt"
+        with open(cookies_file, "wb") as f:
+            f.write(uploaded_cookies.getbuffer())
+    
+    with st.expander("Having trouble with YouTube videos?"):
+        st.markdown("""
+        **YouTube Authentication Issues**
+        
+        YouTube sometimes requires authentication to verify you're not a bot. If you encounter errors while analyzing YouTube videos, try these solutions:
+        
+        1. **Use a different video source**: Try Loom or a direct MP4 link instead
+        2. **Export cookies from your browser**:
+           - Install the [cookies.txt extension](https://chrome.google.com/webstore/detail/get-cookiestxt-locally/cclelndahbckbenkjhflpdbgdldlbecc) for Chrome
+           - Visit YouTube and login 
+           - Use the extension to export your cookies to a file
+           - Place the cookies file in the app's directory
+        3. **Try a shorter video**: YouTube may be less likely to require authentication for shorter clips
+        """)
+    
     if st.button("Analyze Video"):
         if not url:
             st.warning("Please enter a valid URL")
@@ -283,7 +324,7 @@ with tab1:
                 
                 # Download and process the video
                 status.text("Downloading video...")
-                download_success = download_video(url, video_path)
+                download_success = download_video(url, video_path, cookies_file)
                 if not download_success:
                     st.error("Failed to download video")
                 else:
@@ -318,13 +359,14 @@ with tab1:
                             
                             # Show audio playback
                             st.audio(audio_path)
-                
-                # Clean up files
+                  # Clean up files
                 try:
                     if os.path.exists(video_path):
                         os.remove(video_path)
                     if os.path.exists(audio_path):
                         os.remove(audio_path)
+                    if cookies_file and os.path.exists(cookies_file):
+                        os.remove(cookies_file)
                 except Exception as e:
                     st.warning(f"Couldn't clean up temporary files: {str(e)}")