Update tool.py

tool.py

@@ -6,14 +6,16 @@ from langchain_community.document_loaders.arxiv import ArxivLoader
 from langchain_community.document_loaders.pubmed import PubMedLoader
 from typing import Optional
 
+
 import os
 import tempfile
 import requests
-from urllib.parse import urlparse
+from urllib.parse import urlparse, parse_qs
 import pytesseract
 from PIL import Image
 import pandas as pd
 import uuid
+from youtube_transcript_api import YouTubeTranscriptApi
 
 ## Simple algebra tools
 @tool
@@ -257,4 +259,44 @@ def analyze_excel_file(file_path: str, query: str) -> str:
         return result
 
     except Exception as e:
-        return f"Error analyzing Excel file: {str(e)}"
+        return f"Error analyzing Excel file: {str(e)}"
+
+
+## Analyze Youtube Transcript tools
+
+def extract_video_id(youtube_url: str) -> str | None:
+    """Extract the video ID from a YouTube URL.
+
+    Supports standard and shortened formats like:
+    - https://www.youtube.com/watch?v=VIDEO_ID
+    - https://youtu.be/VIDEO_ID
+    """
+    try:
+        parsed_url = urlparse(youtube_url)
+        host = parsed_url.hostname
+
+        if host in ("www.youtube.com", "youtube.com"):
+            return parse_qs(parsed_url.query).get("v", [None])[0]
+        elif host == "youtu.be":
+            return parsed_url.path.strip("/")
+    except Exception:
+        return None
+
+    return None
+
+@tool
+def get_youtube_transcript(youtube_url: str) -> str:
+    """Returns the transcript of a YouTube video as plain text.
+
+    Use this tool to extract spoken words from videos for Q&A, summarization,
+    or analysis. This does not include visual or on-screen content.
+    """
+    video_id = extract_video_id(youtube_url)
+    if not video_id:
+        return "Invalid or unsupported YouTube URL format."
+
+    try:
+        transcript = YouTubeTranscriptApi.get_transcript(video_id)
+        return " ".join(entry["text"] for entry in transcript)
+    except Exception as e:
+        return f"Transcript unavailable: {str(e)}"