Update app.py

app.py

@@ -13,23 +13,28 @@ from selenium import webdriver
 from selenium.webdriver.chrome.options import Options
 from selenium.webdriver.chrome.service import Service
 
+def is_direct_video_url(url: str):
+    """
+    Naive check if the user input is a direct link to a video file.
+    You can expand this list as needed (e.g. .mp4, .webm, .mov, .avi).
+    """
+    video_extensions = (".mp4", ".webm", ".mov", ".avi", ".mkv")
+    return url.lower().endswith(video_extensions)
+
 def get_video_url(page_url):
     """
     Uses Selenium in headless mode to load the page and extract the video URL from a <video> element.
     Adjust the element-finding logic if the video is embedded differently.
     """
-    # Set Chrome options for headless operation.
     chrome_options = Options()
     chrome_options.add_argument("--headless")
     chrome_options.add_argument("--no-sandbox")
     chrome_options.add_argument("--disable-dev-shm-usage")
-    # Point to the apt-installed Chromium binary
+    # Location of Chromium browser
     chrome_options.binary_location = "/usr/bin/chromium-browser"
-
-    # Point to the apt-installed ChromiumDriver
+    # Location of the matching Chromedriver
     service = Service("/usr/bin/chromedriver")
 
-    # Initialize Chrome driver
     driver = webdriver.Chrome(service=service, options=chrome_options)
     driver.get(page_url)
     
@@ -48,7 +53,7 @@ def get_video_url(page_url):
 
 def download_video(video_url, output_path):
     """
-    Downloads the video from the extracted URL to a local file.
+    Downloads the video from the extracted URL (or direct link) to a local file.
     """
     response = requests.get(video_url, stream=True)
     if response.status_code != 200:
@@ -62,15 +67,15 @@ def download_video(video_url, output_path):
 
 def extract_audio(video_file, audio_file):
     """
-    Uses FFmpeg (installed via apt.txt) to extract the audio track from the video.
+    Uses FFmpeg to extract the audio track from the video.
     """
     command = [
         "ffmpeg",
         "-i", video_file,         # Input video file
-        "-vn",                    # Disable video recording
+        "-vn",                    # Disable video output
         "-acodec", "pcm_s16le",   # Audio codec for WAV
-        "-ar", "44100",           # Set audio sample rate
-        "-ac", "2",               # Set number of audio channels
+        "-ar", "44100",           # Sample rate
+        "-ac", "2",               # Stereo channels
         audio_file
     ]
     try:
@@ -85,8 +90,7 @@ def transcribe_audio(audio_file):
     """
     model = whisper.load_model("base")
     result = model.transcribe(audio_file)
-    transcription = result["text"]
-    return transcription
+    return result["text"]
 
 def summarize_text(transcription, openai_api_key, model_name="text-davinci-003"):
     """
@@ -104,74 +108,23 @@ def summarize_text(transcription, openai_api_key, model_name="text-davinci-003")
         max_tokens=150,
         temperature=0.5
     )
-    summary = response.choices[0].text.strip()
-    return summary
+    return response.choices[0].text.strip()
 
 def process_page(page_url, openai_api_key):
     """
-    Processes the given course page URL:
-      1. Scrapes the page to find the embedded video URL.
-      2. Downloads the video.
-      3. Extracts the audio using FFmpeg.
-      4. Transcribes the audio with Whisper.
-      5. Summarizes the transcription via OpenAI.
+    Main function that:
+      1. Checks if user input is direct video URL or a page.
+      2. Scrapes for video URL if needed.
+      3. Downloads the video.
+      4. Extracts the audio using FFmpeg.
+      5. Transcribes audio with Whisper.
+      6. Summarizes via OpenAI.
     
-    Returns the extracted video URL, full transcription, and summary.
+    Returns (video_url, transcription, summary).
     """
     try:
-        # 1. Get the video URL from the course page.
-        video_url = get_video_url(page_url)
-        
-        # 2. Create a temporary file for the video.
-        video_temp = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False)
-        video_file = video_temp.name
-        video_temp.close()
-        
-        # Download the video.
-        download_video(video_url, video_file)
-        
-        # 3. Create a temporary file for the audio.
-        audio_temp = tempfile.NamedTemporaryFile(suffix=".wav", delete=False)
-        audio_file = audio_temp.name
-        audio_temp.close()
-        
-        # Extract audio from the video.
-        extract_audio(video_file, audio_file)
-        
-        # 4. Transcribe the audio.
-        transcription = transcribe_audio(audio_file)
-        
-        # 5. Summarize the transcription.
-        summary = summarize_text(transcription, openai_api_key)
-        
-        # Clean up temporary files.
-        os.remove(video_file)
-        os.remove(audio_file)
-        
-        return video_url, transcription, summary
-    except Exception as e:
-        return "Error: " + str(e), "", ""
-
-# Create a Gradio interface for the HF Spaces app.
-interface = gr.Interface(
-    fn=process_page,
-    inputs=[
-        gr.Textbox(label="Course Page URL", placeholder="Enter the deeplearning.ai course page URL here..."),
-        gr.Textbox(label="OpenAI API Key", type="password", placeholder="Enter your OpenAI API key")
-    ],
-    outputs=[
-        gr.Textbox(label="Extracted Video URL"),
-        gr.Textbox(label="Transcription"),
-        gr.Textbox(label="Summary")
-    ],
-    title="Video Analyzer",
-    description=(
-        "Enter a page URL with embedded video or video URL and your OpenAI API key. "
-        "The app will scrape the page to find the embedded video, download it, "
-        "extract the audio, transcribe the speech using Whisper, and summarize the content using GPT.\n\n"
-        "Note: Ensure FFmpeg, Chromium, and ChromiumDriver are installed via apt.txt."
-    )
-)
-
-if __name__ == "__main__":
-    interface.launch()
+        if is_direct_video_url(page_url):
+            # The user provided a direct video link; no scraping needed
+            video_url = page_url
+        else:
+            # The user provided a page URL,