Update app.py

app.py

@@ -130,142 +130,142 @@ import re
 from collections import Counter
 from googleapiclient.discovery import build
 
-def process_youtube_video(url="", keywords=""):
-    try:
-        #Initialize variables
-        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", "", ""
-
-        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:
-            # Fetch transcript
-            transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
-            transcript = None
-            try:
-                transcript = transcript_list.find_transcript(['en'])
-            except:
-                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")
-
-            # Clean up the text for sentiment analysis
-            cleaned_text = clean_text_for_analysis(text)
-
-            # Sentiment analysis
-            sentiment = TextBlob(cleaned_text).sentiment  # Use cleaned text for sentiment analysis
-            sentiment_label = f"{'Positive' if sentiment.polarity > 0 else 'Negative' if sentiment.polarity < 0 else 'Neutral'} ({sentiment.polarity:.2f})"
-
-            # Generate summary
-            model = genai.GenerativeModel("gemini-pro")
-            summary = model.generate_content(f"Summarize this: {cleaned_text[:4000]}").text
-
-            # Extract subtitle information
-            subtitle_info = extract_subtitle_info(cleaned_text)
-
-        except TranscriptsDisabled:
-            metadata = get_video_metadata(video_id)
-            summary = metadata.get("description", "⚠️ This video has disabled subtitles.")
-            sentiment_label = "N/A"
-            subtitle_info = "No subtitles available for analysis."
-        except NoTranscriptFound:
-            metadata = get_video_metadata(video_id)
-            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 processing transcript: {str(e)}", "N/A", "", ""
+# def process_youtube_video(url="", keywords=""):
+#     try:
+#         #Initialize variables
+#         thumbnail = None
+#         summary = "No transcript available"
+#         sentiment_label = "N/A"
+#         recommendations = ""
+#         subtitle_info = "No additional information available"
 
-        # Get recommendations
-        if keywords.strip():
-            recommendations = get_recommendations(keywords)
+#         if not url.strip():
+#             return None, "Please enter a YouTube URL", "N/A", "", ""
 
-        return thumbnail, summary, sentiment_label, subtitle_info, recommendations
+#         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:
+#             # Fetch transcript
+#             transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
+#             transcript = None
+#             try:
+#                 transcript = transcript_list.find_transcript(['en'])
+#             except:
+#                 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")
+
+#             # Clean up the text for sentiment analysis
+#             cleaned_text = clean_text_for_analysis(text)
+
+#             # Sentiment analysis
+#             sentiment = TextBlob(cleaned_text).sentiment  # Use cleaned text for sentiment analysis
+#             sentiment_label = f"{'Positive' if sentiment.polarity > 0 else 'Negative' if sentiment.polarity < 0 else 'Neutral'} ({sentiment.polarity:.2f})"
+
+#             # Generate summary
+#             model = genai.GenerativeModel("gemini-pro")
+#             summary = model.generate_content(f"Summarize this: {cleaned_text[:4000]}").text
+
+#             # Extract subtitle information
+#             subtitle_info = extract_subtitle_info(cleaned_text)
+
+#         except TranscriptsDisabled:
+#             metadata = get_video_metadata(video_id)
+#             summary = metadata.get("description", "⚠️ This video has disabled subtitles.")
+#             sentiment_label = "N/A"
+#             subtitle_info = "No subtitles available for analysis."
+#         except NoTranscriptFound:
+#             metadata = get_video_metadata(video_id)
+#             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 processing transcript: {str(e)}", "N/A", "", ""
+
+#         # Get recommendations
+#         if keywords.strip():
+#             recommendations = get_recommendations(keywords)
+
+#         return thumbnail, summary, sentiment_label, subtitle_info, recommendations
 
-    except Exception as e:
-        return None, f"Error: {str(e)}", "N/A", "", ""
+#     except Exception as e:
+#         return None, f"Error: {str(e)}", "N/A", "", ""
 
 
-def extract_video_id(url):
-    """
-    Extracts the video ID from a YouTube URL.
-    """
-    match = re.search(r"(?:v=|\/)([0-9A-Za-z_-]{11})", url)
-    return match.group(1) if match else None
+# def extract_video_id(url):
+#     """
+#     Extracts the video ID from a YouTube URL.
+#     """
+#     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):
-    """
-    Fetches video metadata such as title and description using the YouTube Data API.
-    """
-    try:
-        YOUTUBE_API_KEY = "AIzaSyD_SDF4lC3vpHVAMnBOcN2ZCTz7dRjUc98"  # Replace with your YouTube Data API key
-        youtube = build("youtube", "v3", developerKey=YOUTUBE_API_KEY)
-        request = youtube.videos().list(part="snippet", id=video_id)
-        response = request.execute()
+# def get_video_metadata(video_id):
+#     """
+#     Fetches video metadata such as title and description using the YouTube Data API.
+#     """
+#     try:
+#         YOUTUBE_API_KEY = "AIzaSyD_SDF4lC3vpHVAMnBOcN2ZCTz7dRjUc98"  # Replace with your YouTube Data API key
+#         youtube = build("youtube", "v3", developerKey=YOUTUBE_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 {}
+#         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)}
+#     except Exception as e:
+#         return {"title": "Error fetching metadata", "description": str(e)}
 
 
-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(". ")
+# 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
-        words = text.split()
-        common_words = Counter(words).most_common(10)
-        key_topics = ", ".join([word for word, count in common_words])
+#         # Example: Extract key topics or keywords
+#         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)}."
+#         # 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 f"Error extracting subtitle information: {str(e)}"
+#         return info
+#     except Exception as e:
+#         return f"Error extracting subtitle information: {str(e)}"
 
 
-def clean_text_for_analysis(text):
-    """
-    Cleans the transcript text by removing extra spaces, line breaks, and non-text elements.
-    """
-    # Remove extra spaces and line breaks
-    cleaned_text = " ".join(text.split())
-    return cleaned_text
+# def clean_text_for_analysis(text):
+#     """
+#     Cleans the transcript text by removing extra spaces, line breaks, and non-text elements.
+#     """
+#     # Remove extra spaces and line breaks
+#     cleaned_text = " ".join(text.split())
+#     return cleaned_text
 
 
-def get_recommendations(keywords):
-    """
-    Fetches related video recommendations based on the provided keywords.
-    This function can be expanded with a proper API or custom logic.
-    """
-    # Placeholder for fetching recommendations based on keywords
-    return f"Recommendations for: {keywords}"  # Dummy return for now
+# def get_recommendations(keywords):
+#     """
+#     Fetches related video recommendations based on the provided keywords.
+#     This function can be expanded with a proper API or custom logic.
+#     """
+#     # Placeholder for fetching recommendations based on keywords
+#     return f"Recommendations for: {keywords}"  # Dummy return for now
 ######################################
 # from textblob import TextBlob
 # from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound
@@ -376,6 +376,79 @@ def get_recommendations(keywords):
 #                 print(f"Negative: {dist['negative']} ({(dist['negative']/total*100):.1f}%)")
             
 #             print(f"\nTotal Sentences Analyzed: {sentiment['total_sentences']}")
+#####################################################################################################
+def process_youtube_video(url="", keywords=""):
+    try:
+        thumbnail = None
+        summary = ""
+        sentiment_label = "N/A"
+        recommendations = ""
+
+        if not url.strip():
+            return thumbnail, "Please enter a YouTube URL", sentiment_label, recommendations
+
+        video_id = extract_video_id(url)
+        if not video_id:
+            return thumbnail, "Invalid YouTube URL", sentiment_label, recommendations
+
+        # Set thumbnail
+        thumbnail = f"https://img.youtube.com/vi/{video_id}/maxresdefault.jpg"
+
+        try:
+            # Get transcript
+            transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
+            transcript = None
+
+            # Try different transcript options
+            for lang in ['en', 'en-US', 'a.en']:
+                try:
+                    transcript = transcript_list.find_transcript([lang])
+                    break
+                except:
+                    continue
+
+            if not transcript:
+                transcript = transcript_list.find_generated_transcript(['en'])
+
+            # Get transcript text
+            text = " ".join([t['text'] for t in transcript.fetch()])
+            
+            # Clean text
+            cleaned_text = re.sub(r'[^\w\s.]', '', text)
+            cleaned_text = ' '.join(cleaned_text.split())
+
+            # Sentiment Analysis
+            blob = TextBlob(cleaned_text[:2000])  # Analyze first 2000 chars
+            polarity = blob.sentiment.polarity
+            subjectivity = blob.sentiment.subjectivity
+
+            sentiment_label = (
+                f"Sentiment: {'Positive' if polarity > 0 else 'Negative' if polarity < 0 else 'Neutral'}\n"
+                f"Confidence: {abs(polarity):.2f}\n"
+                f"Subjectivity: {subjectivity:.2f}"
+            )
+
+            # Generate summary
+            model = genai.GenerativeModel("gemini-pro")
+            summary = model.generate_content(f"Summarize this content: {cleaned_text[:4000]}").text
+
+        except (TranscriptsDisabled, NoTranscriptFound):
+            return thumbnail, "⚠️ No English subtitles available", "N/A", recommendations
+        except Exception as e:
+            return thumbnail, f"⚠️ Error: {str(e)}", "N/A", recommendations
+
+        # Get recommendations
+        if keywords.strip():
+            recommendations = get_recommendations(keywords)
+
+        return thumbnail, summary, sentiment_label, recommendations
+
+    except Exception as e:
+        return None, f"Error: {str(e)}", "N/A", ""
+
+
+
+