Update app.py

app.py

@@ -801,6 +801,13 @@ import re
 from collections import Counter
 from googleapiclient.discovery import build
 
+
+from textblob import TextBlob
+from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound
+import re
+from collections import Counter
+from googleapiclient.discovery import build
+
 def process_youtube_video(url="", keywords=""):
     try:
         # Initialize variables
@@ -832,16 +839,19 @@ def process_youtube_video(url="", keywords=""):
             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: {text[:4000]}").text
+            summary = model.generate_content(f"Summarize this: {cleaned_text[:4000]}").text
 
             # Extract subtitle information
-            subtitle_info = extract_subtitle_info(text)
-
-            # Sentiment analysis
-            sentiment = TextBlob(text).sentiment  # Use the entire text for sentiment analysis
-            sentiment_label = f"{'Positive' if sentiment.polarity > 0 else 'Negative' if sentiment.polarity < 0 else 'Neutral'} ({sentiment.polarity:.2f})"
+            subtitle_info = extract_subtitle_info(cleaned_text)
 
         except TranscriptsDisabled:
             metadata = get_video_metadata(video_id)
@@ -879,7 +889,7 @@ 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_API_KEY = "YOUR_YOUTUBE_API_KEY"  # 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()
@@ -918,16 +928,22 @@ def extract_subtitle_info(text):
         return f"Error extracting subtitle information: {str(e)}"
 
 
-# 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 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