Update app.py

app.py

@@ -134,69 +134,178 @@ def extract_video_id(url):
     return None
 
 
+# def process_youtube_video(url="", keywords=""):
+#     try:
+#         # Initialize variables
+#         thumbnail = None  # Default value for thumbnail
+#         summary = "No transcript available"
+#         sentiment_label = "N/A"
+
+#         if not url.strip():
+#             return None, "Please enter a YouTube URL", "N/A", ""
+            
+#         video_id = extract_video_id(url)
+#         if not video_id:
+#             return None, "Invalid YouTube URL", "N/A", ""
+
+#         thumbnail = f"https://img.youtube.com/vi/{video_id}/maxresdefault.jpg"
+
+#         try:
+#             # Try multiple transcript options
+#             transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
+            
+#             try:
+#                 transcript = transcript_list.find_transcript(['en'])
+#             except:
+#                 try:
+#                     transcript = transcript_list.find_transcript(['en-US'])
+#                 except:
+#                     try:
+#                         # Try auto-generated
+#                         transcript = transcript_list.find_generated_transcript(['en'])
+#                     except:
+#                         raise NoTranscriptFound()
+
+#             text = " ".join([t['text'] for t in transcript.fetch()])
+            
+#             # Generate summary
+#             model = genai.GenerativeModel("gemini-pro")
+#             summary = model.generate_content(f"Summarize this: {text[:4000]}").text
+            
+#             # Analysis
+#             sentiment = TextBlob(text[:1000]).sentiment
+#             sentiment_label = f"{'Positive' if sentiment.polarity > 0 else 'Negative' if sentiment.polarity < 0 else 'Neutral'} ({sentiment.polarity:.2f})"
+
+#         except TranscriptsDisabled:
+#             # Fallback: Use video metadata if available
+#             metadata = get_video_metadata(video_id)
+#             summary = metadata.get("description", "⚠️ This video has disabled subtitles. No transcript available.")
+#         except NoTranscriptFound:
+#             # Fallback: Use video metadata if available
+#             metadata = get_video_metadata(video_id)
+#             summary = metadata.get("description", "⚠️ No English transcript available. No transcript available.")
+#         except Exception as e:
+#             return thumbnail, f"⚠️ Error: {str(e)}", "N/A", ""
+
+#         # Get recommendations
+#         if keywords.strip():
+#             recommendations = get_recommendations(keywords)
+#         else:
+#             recommendations = ""
+
+#         return thumbnail, summary, sentiment_label, recommendations
+
+#     except Exception as e:
+#         return None, f"Error: {str(e)}", "N/A", ""
+
+
+# def get_video_metadata(video_id):
+#     """
+#     Fetches video metadata such as title and description using the YouTube Data API.
+#     """
+#     try:
+#         from googleapiclient.discovery import build
+
+#         # Replace with your YouTube Data API key
+#         API_KEY = "AIzaSyB7X-RYjZmUuDSMTQsvCfyzURw5bhqOto4"
+#         youtube = build("youtube", "v3", developerKey=API_KEY)
+#         request = youtube.videos().list(part="snippet", id=video_id)
+#         response = request.execute()
+
+#         if "items" in response and len(response["items"]) > 0:
+#             snippet = response["items"][0]["snippet"]
+#             return {
+#                 "title": snippet.get("title", "No title available"),
+#                 "description": snippet.get("description", "No description available"),
+#             }
+#         return {}
+
+#     except Exception as e:
+#         return {"title": "Error fetching metadata", "description": str(e)}
+
+#         # Get recommendations
+#         if keywords.strip():
+#             recommendations = get_recommendations(keywords)
+#         else:
+#             recommendations = ""
+
+#         return thumbnail, summary, sentiment_label, recommendations
+
+#     except Exception as e:
+#         return None, f"Error: {str(e)}", "N/A", ""
+
 def process_youtube_video(url="", keywords=""):
     try:
         # Initialize variables
-        thumbnail = None  # Default value for thumbnail
+        thumbnail = None
         summary = "No transcript available"
         sentiment_label = "N/A"
+        recommendations = ""
+        subtitle_info = "No additional information available"
 
         if not url.strip():
-            return None, "Please enter a YouTube URL", "N/A", ""
-            
+            return None, "Please enter a YouTube URL", "N/A", "", ""
+
         video_id = extract_video_id(url)
         if not video_id:
-            return None, "Invalid YouTube URL", "N/A", ""
+            return None, "Invalid YouTube URL", "N/A", "", ""
 
         thumbnail = f"https://img.youtube.com/vi/{video_id}/maxresdefault.jpg"
 
         try:
-            # Try multiple transcript options
+            # Fetch transcript
             transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
-            
+            transcript = None
             try:
                 transcript = transcript_list.find_transcript(['en'])
             except:
-                try:
-                    transcript = transcript_list.find_transcript(['en-US'])
-                except:
-                    try:
-                        # Try auto-generated
-                        transcript = transcript_list.find_generated_transcript(['en'])
-                    except:
-                        raise NoTranscriptFound()
+                transcript = transcript_list.find_generated_transcript(['en'])
 
             text = " ".join([t['text'] for t in transcript.fetch()])
-            
+            if not text.strip():
+                raise ValueError("Transcript is empty")
+
             # Generate summary
             model = genai.GenerativeModel("gemini-pro")
             summary = model.generate_content(f"Summarize this: {text[:4000]}").text
-            
-            # Analysis
+
+            # Extract subtitle information
+            subtitle_info = extract_subtitle_info(text)
+
+            # Sentiment analysis
             sentiment = TextBlob(text[:1000]).sentiment
             sentiment_label = f"{'Positive' if sentiment.polarity > 0 else 'Negative' if sentiment.polarity < 0 else 'Neutral'} ({sentiment.polarity:.2f})"
 
         except TranscriptsDisabled:
-            # Fallback: Use video metadata if available
             metadata = get_video_metadata(video_id)
-            summary = metadata.get("description", "⚠️ This video has disabled subtitles. No transcript available.")
+            summary = metadata.get("description", "⚠️ This video has disabled subtitles.")
+            sentiment_label = "N/A"
+            subtitle_info = "No subtitles available for analysis."
         except NoTranscriptFound:
-            # Fallback: Use video metadata if available
             metadata = get_video_metadata(video_id)
-            summary = metadata.get("description", "⚠️ No English transcript available. No transcript available.")
+            summary = metadata.get("description", "⚠️ No English transcript available.")
+            sentiment_label = "N/A"
+            subtitle_info = "No subtitles available for analysis."
         except Exception as e:
-            return thumbnail, f"⚠️ Error: {str(e)}", "N/A", ""
+            return thumbnail, f"⚠️ Error processing transcript: {str(e)}", "N/A", "", ""
 
         # Get recommendations
         if keywords.strip():
             recommendations = get_recommendations(keywords)
-        else:
-            recommendations = ""
 
-        return thumbnail, summary, sentiment_label, recommendations
+        return thumbnail, summary, sentiment_label, subtitle_info, recommendations
 
     except Exception as e:
-        return None, f"Error: {str(e)}", "N/A", ""
+        return None, f"Error: {str(e)}", "N/A", "", ""
+
+
+def extract_video_id(url):
+    """
+    Extracts the video ID from a YouTube URL.
+    """
+    import re
+    match = re.search(r"(?:v=|\/)([0-9A-Za-z_-]{11})", url)
+    return match.group(1) if match else None
 
 
 def get_video_metadata(video_id):
@@ -207,8 +316,8 @@ def get_video_metadata(video_id):
         from googleapiclient.discovery import build
 
         # Replace with your YouTube Data API key
-        API_KEY = "AIzaSyB7X-RYjZmUuDSMTQsvCfyzURw5bhqOto4"
-        youtube = build("youtube", "v3", developerKey=API_KEY)
+        YOUTUBE_API_KEY = "AIzaSyD_SDF4lC3vpHVAMnBOcN2ZCTz7dRjUc98"
+        youtube = build("youtube", "v3", developerKey=YOUTUBE_API_KEY)
         request = youtube.videos().list(part="snippet", id=video_id)
         response = request.execute()
 
@@ -223,16 +332,36 @@ def get_video_metadata(video_id):
     except Exception as e:
         return {"title": "Error fetching metadata", "description": str(e)}
 
-        # Get recommendations
-        if keywords.strip():
-            recommendations = get_recommendations(keywords)
-        else:
-            recommendations = ""
 
-        return thumbnail, summary, sentiment_label, recommendations
+def extract_subtitle_info(text):
+    """
+    Extracts meaningful information from the subtitles.
+    This could include topics, key insights, or a breakdown of the content.
+    """
+    try:
+        # Split text into sentences for better analysis
+        sentences = text.split(". ")
+        
+        # Example: Extract key topics or keywords
+        from collections import Counter
+        words = text.split()
+        common_words = Counter(words).most_common(10)
+        key_topics = ", ".join([word for word, count in common_words])
+
+        # Example: Provide a breakdown of the content
+        info = f"Key topics discussed: {key_topics}. \nNumber of sentences: {len(sentences)}. \nTotal words: {len(words)}."
 
+        return info
     except Exception as e:
-        return None, f"Error: {str(e)}", "N/A", ""
+        return f"Error extracting subtitle information: {str(e)}"
+
+
+
+
+
+
+
+
 def get_recommendations(keywords, max_results=5):
     if not keywords:
         return "Please provide search keywords"