Update youtube_tool.py

youtube_tool.py

@@ -14,46 +14,6 @@ def extract_video_id(url: str) -> str:
     Returns:
         str: The extracted video ID or raises ValueError.
     """
-    patterns = [
-        r"youtube\.com/watch\?v=([a-zA-Z0-9_-]{11})",
-        r"youtu\.be/([a-zA-Z0-9_-]{11})"
-    ]
-    for pattern in patterns:
-        match = re.search(pattern, url)
-        if match:
-            return match.group(1)
-    raise ValueError("Invalid YouTube URL or unable to extract video ID.")
-
-def get_youtube_transcript(url: str) -> str:
-    """
-    Fetches the transcript text for a given YouTube video.
-    Args:
-        url (str): The YouTube video URL.
-    Returns:
-        str: Combined transcript text or an error message.
-    """
-    try:
-        video_id = extract_video_id(url)
-        transcript_list = YouTubeTranscriptApi.get_transcript(video_id)
-        full_text = " ".join([entry["text"] for entry in transcript_list])
-        return full_text.strip()[:2000]  # Truncate to 2000 chars to prevent token overflow
-    except TranscriptsDisabled:
-        return "This video has transcripts disabled."
-    except NoTranscriptFound:
-        return "No transcript was found for this video."
-    except Exception as e:
-        return f"Transcript error: {str(e)}"
-    
-youtube_tool = FunctionTool.from_defaults(get_youtube_transcript)
-
-
-def extract_video_id(url: str) -> str:
-    """
-    Handles typical YouTube URLs:
-    - https://www.youtube.com/watch?v=VIDEO_ID
-    - https://youtu.be/VIDEO_ID
-    - with extra query params
-    """
     parsed = urlparse(url)
     if parsed.hostname in {"www.youtube.com", "youtube.com"}:
         qs = parse_qs(parsed.query)
@@ -62,10 +22,14 @@ def extract_video_id(url: str) -> str:
     # fallback for youtu.be or raw IDs
     return parsed.path.lstrip("/")
 
+
 def fetch_youtube_transcript(video_url: str) -> str:
     """
-    Fetch YouTube transcript text for the given URL.
-    In English language.
+    Fetches the transcript text for a given YouTube video.
+    Args:
+        url (str): The YouTube video URL.
+    Returns:
+        str: Combined transcript text or an error message.
     """
     video_id = extract_video_id(video_url)
 
@@ -77,9 +41,8 @@ def fetch_youtube_transcript(video_url: str) -> str:
         )
 
         #FROM TRANSCRIPT DATA, YOU CAN CREATE A OBJECT OF TRANSCRIPT SNIPET AND TIME
-        arr = [snippet.text for snippet in transcript_data]
-        return " ".join(arr)
-        #return " ".join(entry["text"] for entry in arr)
+        arr = [ {"text": snippet.text} for snippet in transcript_data]
+        return " ".join(f"{entry['text']}" for entry in arr)
     except Exception as e:
         return f"Error fetching video details: {str(e)}"