Update processors/input_processor.py

processors/input_processor.py

@@ -27,16 +27,12 @@ class ContentProcessor:
         return pages
     
     def process_youtube(self, video_url):
-        # Extract video ID from URL
         video_id = self._extract_video_id(video_url)
         if not video_id:
-            raise ValueError("Invalid YouTube URL")
+            raise ValueError("This appears to be an invalid YouTube URL. Please check the URL and try again.")
         
         try:
-            # Get transcript directly using youtube_transcript_api
             transcript_list = YouTubeTranscriptApi.get_transcript(video_id)
-            
-            # Combine all transcript pieces
             full_transcript = " ".join([entry['text'] for entry in transcript_list])
             
             # Create a document-like structure
@@ -46,11 +42,12 @@ class ContentProcessor:
                 metadata={"source": video_url}
             )
             
-            # Split the document
             return self.text_splitter.split_documents([doc])
             
+        except TranscriptsDisabled:
+            raise Exception("This video does not have subtitles/captions enabled. Please try a different video that has captions available.")
         except Exception as e:
-            raise Exception(f"Error getting transcript: {str(e)}")
+            raise Exception(f"Unable to get transcript: {str(e)}. Please ensure the video has captions enabled.")
     
     def _extract_video_id(self, url):
         # Handle different YouTube URL formats