Update app.py

app.py

@@ -130,253 +130,143 @@ 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", "", ""
-
-#         # 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", "", ""
-
-
-# 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()
-
-#         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)}
-
-
-# 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: 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)}"
-
-
-# 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
-######################################
-from textblob import TextBlob
-from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound
-import re
-from collections import Counter
-from googleapiclient.discovery import build
-import os
-
-# Set your YouTube API key
-YOUTUBE_API_KEY = "AIzaSyB7X-RYjZmUuDSMTQsvCfyzURw5bhqOto4"  # Replace with your actual API key
-# Alternatively, you can set it as an environment variable:
-# YOUTUBE_API_KEY = os.getenv('YOUTUBE_API_KEY')
-
-def process_youtube_video(url=""):
-    """
-    Process a YouTube video URL and return sentiment analysis of its content.
-    """
+def process_youtube_video(url="", keywords=""):
     try:
-        # Input validation
+        #Initialize variables
+        thumbnail = None
+        summary = "No transcript available"
+        sentiment_label = "N/A"
+        recommendations = ""
+        subtitle_info = "No additional information available"
+
         if not url.strip():
-            return {"error": "Please enter a YouTube URL"}
+            return None, "Please enter a YouTube URL", "N/A", "", ""
 
-        # Extract video ID
         video_id = extract_video_id(url)
         if not video_id:
-            return {"error": "Invalid YouTube URL"}
-
-        # Get video transcript
-        text = get_video_transcript(video_id)
-        if isinstance(text, dict) and "error" in text:
-            return text
+            return None, "Invalid YouTube URL", "N/A", "", ""
 
-        # Get video metadata
-        metadata = get_video_metadata(video_id)
-        if "error" in metadata:
-            return metadata
+        thumbnail = f"https://img.youtube.com/vi/{video_id}/maxresdefault.jpg"
 
-        # Perform sentiment analysis
-        sentiment_result = analyze_sentiment(text)
-        
-        return {
-            "success": True,
-            "metadata": metadata,
-            "sentiment": sentiment_result,
-            "video_id": video_id
-        }
+        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 {"error": f"An error occurred: {str(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 get_video_metadata(video_id):
     """
-    Fetches video metadata using the YouTube Data API.
+    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
-        )
+        request = youtube.videos().list(part="snippet", id=video_id)
         response = request.execute()
 
-        if response.get("items"):
+        if "items" in response and len(response["items"]) > 0:
             snippet = response["items"][0]["snippet"]
             return {
-                "title": snippet.get("title", ""),
-                "description": snippet.get("description", ""),
-                "publishedAt": snippet.get("publishedAt", ""),
-                "channelTitle": snippet.get("channelTitle", "")
+                "title": snippet.get("title", "No title available"),
+                "description": snippet.get("description", "No description available"),
             }
-        return {"error": "Video not found"}
+        return {}
 
     except Exception as e:
-        return {"error": f"Error fetching metadata: {str(e)}"}
+        return {"title": "Error fetching metadata", "description": str(e)}
 
-# [Previous functions remain the same: get_video_transcript, analyze_sentiment, 
-#  extract_video_id, clean_text_for_analysis, get_detailed_sentiment]
 
-# Example usage with proper error handling:
-if __name__ == "__main__":
-    # Example with a real YouTube URL
-    test_url = "https://www.youtube.com/watch?v=dQw4w9WgXcQ"  # Replace with any YouTube URL
-    
-    # Check if API key is set
-    if YOUTUBE_API_KEY == "AIzaSyD_SDF4lC3vpHVAMnBOcN2ZCTz7dRjUc98":
-        print("Error: Please set your YouTube API key first!")
-    else:
-        result = process_youtube_video(test_url)
+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(". ")
         
-        if "error" in result:
-            print(f"Error: {result['error']}")
-        else:
-            print("\n=== Video Information ===")
-            print(f"Title: {result['metadata']['title']}")
-            print(f"Channel: {result['metadata']['channelTitle']}")
-            
-            print("\n=== Sentiment Analysis Results ===")
-            sentiment = result['sentiment']
-            print(f"Overall Sentiment: {sentiment['overall_sentiment']}")
-            print(f"Average Polarity: {sentiment['average_polarity']}")
-            
-            print("\nSentiment Distribution:")
-            dist = sentiment['sentiment_distribution']
-            total = sum(dist.values())
-            if total > 0:
-                print(f"Positive: {dist['positive']} ({(dist['positive']/total*100):.1f}%)")
-                print(f"Neutral: {dist['neutral']} ({(dist['neutral']/total*100):.1f}%)")
-                print(f"Negative: {dist['negative']} ({(dist['negative']/total*100):.1f}%)")
-            
-            print(f"\nTotal Sentences Analyzed: {sentiment['total_sentences']}")
-#####################################################################################################
+        # 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)}."
+
+        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 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, max_results=5):
     if not keywords: