Update app.py

app.py

@@ -136,44 +136,170 @@ from googleapiclient.discovery import build
 
 YOUTUBE_API_KEY = "AIzaSyD_SDF4lC3vpHVAMnBOcN2ZCTz7dRjUc98"  # Replace with your actual API key
 
+# def extract_video_id(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):
+#     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 extract_subtitle_info(text):
+#     try:
+#         sentences = text.split(". ")
+#         words = text.split()
+#         common_words = Counter(words).most_common(10)
+#         key_topics = ", ".join([word for word, count in common_words])
+#         info = {
+#             "key_topics": key_topics,
+#             "sentence_count": len(sentences),
+#             "word_count": len(words),
+#         }
+#         return info
+#     except Exception as e:
+#         return {"error": str(e)}
+
+# 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, keywords):
+#     try:
+#         thumbnail = None
+#         summary = "No transcript available"
+#         sentiment_label = "N/A"
+#         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:
+#             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)
+#             subtitle_info = extract_subtitle_info(cleaned_text)
+
+#             sentiment = TextBlob(cleaned_text).sentiment
+#             sentiment_label = f"{'Positive' if sentiment.polarity > 0 else 'Negative' if sentiment.polarity < 0 else 'Neutral'} ({sentiment.polarity:.2f})"
+
+#             summary = f"Summary: {cleaned_text[:400]}..."
+
+#         except (TranscriptsDisabled, NoTranscriptFound):
+#             metadata = get_video_metadata(video_id)
+#             summary = metadata.get("description", "No subtitles available")
+#             sentiment_label = "N/A"
+
+#         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 sanitize_text(text):
+    """Remove invalid Unicode characters."""
+    return text.encode("utf-8", "replace").decode("utf-8")
+
 def extract_video_id(url):
-    match = re.search(r"(?:v=|\/)([0-9A-Za-z_-]{11})", url)
-    return match.group(1) if match else None
+    if not url:
+        return None
+    patterns = [
+        r'(?:v=|\/videos\/|embed\/|youtu.be\/|\/v\/|\/e\/|watch\?v=|\/watch\?v=)([^#\&\?]*)'
+    ]
+    for pattern in patterns:
+        match = re.search(pattern, url)
+        if match:
+            return match.group(1)
+    return None
 
-def get_video_metadata(video_id):
+def process_youtube_video(url="", keywords=""):
+    """Process either video URL or keywords or both"""
     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 {}
+        thumbnail = None
+        summary = ""
+        sentiment_label = "N/A"
+        recommendations = ""
 
-    except Exception as e:
-        return {"title": "Error fetching metadata", "description": str(e)}
+        if url.strip():
+            video_id = extract_video_id(url)
+            if video_id:
+                transcript = YouTubeTranscriptApi.get_transcript(video_id)
+                text = " ".join([t['text'] for t in transcript])
+                
+                # Sanitize text
+                text = sanitize_text(text)
+                
+                model = genai.GenerativeModel("gemini-pro")
+                summary = model.generate_content(f"Summarize this: {text}").text
+                
+                sentiment = TextBlob(text).sentiment
+                sentiment_label = f"{'Positive' if sentiment.polarity > 0 else 'Negative' if sentiment.polarity < 0 else 'Neutral'} ({sentiment.polarity:.2f})"
+                
+                thumbnail = f"https://img.youtube.com/vi/{video_id}/maxresdefault.jpg"
 
-def clean_text_for_analysis(text):
-    return " ".join(text.split())
+        if keywords.strip():
+            recommendations = get_recommendations(keywords)
 
-def extract_subtitle_info(text):
-    try:
-        sentences = text.split(". ")
-        words = text.split()
-        common_words = Counter(words).most_common(10)
-        key_topics = ", ".join([word for word, count in common_words])
-        info = {
-            "key_topics": key_topics,
-            "sentence_count": len(sentences),
-            "word_count": len(words),
-        }
-        return info
+        return (
+            thumbnail,
+            summary or "Enter a video URL for analysis",
+            sentiment_label,
+            recommendations or "Enter keywords for recommendations"
+        )
     except Exception as e:
-        return {"error": str(e)}
+        return None, f"Error: {str(e)}", "N/A", ""
 
 def get_recommendations(keywords, max_results=5):
     if not keywords:
@@ -190,66 +316,18 @@ def get_recommendations(keywords, max_results=5):
                 "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, keywords):
-    try:
-        thumbnail = None
-        summary = "No transcript available"
-        sentiment_label = "N/A"
-        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:
-            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)
-            subtitle_info = extract_subtitle_info(cleaned_text)
-
-            sentiment = TextBlob(cleaned_text).sentiment
-            sentiment_label = f"{'Positive' if sentiment.polarity > 0 else 'Negative' if sentiment.polarity < 0 else 'Neutral'} ({sentiment.polarity:.2f})"
-
-            summary = f"Summary: {cleaned_text[:400]}..."
-
-        except (TranscriptsDisabled, NoTranscriptFound):
-            metadata = get_video_metadata(video_id)
-            summary = metadata.get("description", "No subtitles available")
-            sentiment_label = "N/A"
-
-        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", {}, ""
-
-
 
 
 # Gradio Interface