Update app.py

app.py

@@ -3,6 +3,7 @@ from transformers import pipeline
 from youtube_transcript_api import YouTubeTranscriptApi
 from youtube_transcript_api.formatters import TextFormatter
 import re
+from pytube import YouTube
 
 # Define the models
 models = {
@@ -31,6 +32,7 @@ def get_youtube_transcript(video_url):
     if not video_id:
         return "Video ID could not be extracted. Please check the URL format."
 
+    # Try to get transcript using YouTubeTranscriptApi
     try:
         transcript = YouTubeTranscriptApi.get_transcript(video_id)
         formatter = TextFormatter()
@@ -39,9 +41,25 @@ def get_youtube_transcript(video_url):
     except Exception as e:
         error_message = str(e)
         if "Subtitles are disabled for this video" in error_message:
-            return "Subtitles are disabled for this video. Transcript cannot be retrieved."
+            # Try to get subtitles using pytube
+            return get_subtitles_with_pytube(video_url)
         return f"An error occurred while retrieving the transcript: {error_message}"
 
+def get_subtitles_with_pytube(video_url):
+    video_id = extract_video_id(video_url)
+    if not video_id:
+        return "Video ID could not be extracted. Please check the URL format."
+    
+    try:
+        yt = YouTube(video_url)
+        captions = yt.captions.get_by_language_code('en')  # You can modify the language code
+        if captions:
+            return captions.generate_srt_captions()
+        return "No subtitles available in the selected language."
+    except Exception as e:
+        return f"An error occurred while retrieving subtitles with pytube: {str(e)}"
+
+
 # Function to summarize YouTube video with selected model
 def summarize_youtube_video(url, model_name):
     transcript = get_youtube_transcript(url)