Update app.py

app.py

@@ -33,6 +33,7 @@ import re
 from googleapiclient.discovery import build
 from huggingface_hub import login
 from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound
+from youtube_transcript_api._errors import NoTranscriptFound, TranscriptsDisabled
 def install_missing_packages():
     required_packages = {
          "torch":">=1.11.0",
@@ -109,16 +110,123 @@ courses_data = [
 ]
 
 
+# def extract_video_id(url):
+#     # Improved regex to handle various YouTube URL formats
+#     match = re.search(r"(?:v=|\/|be\/|embed\/|watch\?v=)([0-9A-Za-z_-]{11})", url)
+#     return match.group(1) if match else None
+
+
+# def get_video_metadata(video_id):
+#     try:
+#         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 clean_text_for_analysis(text):
+#     return " ".join(text.split())
+
+# def generate_summary(content):
+#     return "\n".join([
+#         "**Key Insights**",
+#         "",
+#         content[:400] + "..." if len(content) > 400 else content
+#     ])
+
+# def analyze_sentiment(text):
+#     sentiment = TextBlob(text).sentiment
+#     sentiment_label = (
+#         "Positive" if sentiment.polarity > 0 else
+#         "Negative" if sentiment.polarity < 0 else
+#         "Neutral"
+#     )
+#     return f"{sentiment_label} ({sentiment.polarity:.2f})"
+
+# def get_recommendations(keywords, max_results=5):
+#     if not keywords:
+#         return "Please provide search keywords"
+#     try:
+#         response = requests.get(
+#             "https://www.googleapis.com/youtube/v3/search",
+#             params={
+#                 "part": "snippet",
+#                 "q": f"educational {keywords}",
+#                 "type": "video",
+#                 "maxResults": max_results,
+#                 "relevanceLanguage": "en",
+#                 "key": YOUTUBE_API_KEY
+#             }
+#         ).json()
+
+#         results = []
+#         for item in response.get("items", []):
+#             title = item["snippet"]["title"]
+#             channel = item["snippet"]["channelTitle"]
+#             video_id = item["id"]["videoId"]
+#             results.append(f"📺 {title}\n👤 {channel}\n🔗 https://youtube.com/watch?v={video_id}\n")
+
+#         return "\n".join(results) if results else "No recommendations found"
+#     except Exception as e:
+#         return f"Error: {str(e)}"
+
+# def process_youtube_video(url):
+#     try:
+#         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:
+#             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")
+
+#             cleaned_text = clean_text_for_analysis(text)
+#             summary = generate_summary(cleaned_text)
+#             sentiment_label = analyze_sentiment(cleaned_text)
+
+#         except (TranscriptsDisabled, NoTranscriptFound):
+#             metadata = get_video_metadata(video_id)
+#             summary = generate_summary(metadata.get("description", "No subtitles available"))
+#             sentiment_label = "N/A"
+
+#         return thumbnail, summary, sentiment_label
+
+#     except Exception as e:
+#         return None, f"Error: {str(e)}", "N/A"
+        
+# url = "https://www.youtube.com/watch?v=q1XFm21I-VQ"
+# thumbnail, summary, sentiment = process_youtube_video(url)
+# print(f"Thumbnail: {thumbnail}\n")
+# print(f"Summary:\n{summary}\n")
+# print(f"Sentiment: {sentiment}")
 def extract_video_id(url):
     # Improved regex to handle various YouTube URL formats
     match = re.search(r"(?:v=|\/|be\/|embed\/|watch\?v=)([0-9A-Za-z_-]{11})", url)
     return match.group(1) if match else None
 
-
 def get_video_metadata(video_id):
     try:
         youtube = build("youtube", "v3", developerKey=YOUTUBE_API_KEY)
-        request = youtube.videos().list(part="snippet", id=video_id)
+        request = youtube.videos().list(part="snippet,contentDetails", id=video_id)
         response = request.execute()
 
         if "items" in response and len(response["items"]) > 0:
@@ -126,6 +234,8 @@ def get_video_metadata(video_id):
             return {
                 "title": snippet.get("title", "No title available"),
                 "description": snippet.get("description", "No description available"),
+                "publishedAt": snippet.get("publishedAt", "Unknown"),
+                "channelTitle": snippet.get("channelTitle", "Unknown"),
             }
         return {}
 
@@ -135,12 +245,14 @@ def get_video_metadata(video_id):
 def clean_text_for_analysis(text):
     return " ".join(text.split())
 
-def generate_summary(content):
-    return "\n".join([
-        "**Key Insights**",
-        "",
-        content[:400] + "..." if len(content) > 400 else content
-    ])
+def generate_detailed_summary(transcript):
+    # Create a detailed summary from the transcript
+    detailed_summary = "**Transcript Breakdown:**\n"
+    for segment in transcript:
+        start_time = segment['start']
+        text = segment['text']
+        detailed_summary += f"- **[{start_time:.2f}s]:** {text}\n"
+    return detailed_summary
 
 def analyze_sentiment(text):
     sentiment = TextBlob(text).sentiment
@@ -151,40 +263,19 @@ def analyze_sentiment(text):
     )
     return f"{sentiment_label} ({sentiment.polarity:.2f})"
 
-def get_recommendations(keywords, max_results=5):
-    if not keywords:
-        return "Please provide search keywords"
-    try:
-        response = requests.get(
-            "https://www.googleapis.com/youtube/v3/search",
-            params={
-                "part": "snippet",
-                "q": f"educational {keywords}",
-                "type": "video",
-                "maxResults": max_results,
-                "relevanceLanguage": "en",
-                "key": YOUTUBE_API_KEY
-            }
-        ).json()
-
-        results = []
-        for item in response.get("items", []):
-            title = item["snippet"]["title"]
-            channel = item["snippet"]["channelTitle"]
-            video_id = item["id"]["videoId"]
-            results.append(f"📺 {title}\n👤 {channel}\n🔗 https://youtube.com/watch?v={video_id}\n")
-
-        return "\n".join(results) if results else "No recommendations found"
-    except Exception as e:
-        return f"Error: {str(e)}"
-
 def process_youtube_video(url):
     try:
         video_id = extract_video_id(url)
         if not video_id:
             return None, "Invalid YouTube URL", "N/A"
 
+        metadata = get_video_metadata(video_id)
+        title = metadata.get("title", "No title")
+        description = metadata.get("description", "No description available")
+
         thumbnail = f"https://img.youtube.com/vi/{video_id}/maxresdefault.jpg"
+        summary = ""
+        sentiment_label = "N/A"
 
         try:
             transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
@@ -194,27 +285,26 @@ def process_youtube_video(url):
             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")
-
-            cleaned_text = clean_text_for_analysis(text)
-            summary = generate_summary(cleaned_text)
+            text_segments = transcript.fetch()
+            transcript_text = " ".join([segment['text'] for segment in text_segments])
+            cleaned_text = clean_text_for_analysis(transcript_text)
+            summary = generate_detailed_summary(text_segments)
             sentiment_label = analyze_sentiment(cleaned_text)
 
         except (TranscriptsDisabled, NoTranscriptFound):
-            metadata = get_video_metadata(video_id)
-            summary = generate_summary(metadata.get("description", "No subtitles available"))
-            sentiment_label = "N/A"
+            summary = "No transcript available."
 
-        return thumbnail, summary, sentiment_label
+        return thumbnail, title, description, summary, sentiment_label
 
     except Exception as e:
-        return None, f"Error: {str(e)}", "N/A"
-        
+        return None, f"Error: {str(e)}", "N/A", "N/A", "N/A"
+
 url = "https://www.youtube.com/watch?v=q1XFm21I-VQ"
-thumbnail, summary, sentiment = process_youtube_video(url)
+thumbnail, title, description, summary, sentiment = process_youtube_video(url)
+
 print(f"Thumbnail: {thumbnail}\n")
+print(f"Title: {title}\n")
+print(f"Description:\n{description}\n")
 print(f"Summary:\n{summary}\n")
 print(f"Sentiment: {sentiment}")