tools/YouTubeTool.py

from smolagents import Tool
from youtube_transcript_api import YouTubeTranscriptApi, NoTranscriptFound, TranscriptsDisabled
import re

class YouTubeTool(Tool):
    name = "youtube_reader"
    description= "Fetches the transcript for the youtube video url"
    inputs= {"video_url": {"type": "string", "description": "URL or ID of the Youtube video"}}
    output_type = "string"

    def forward(self, video_url: str) -> str:
        try:
            # Extract video ID
            match = re.search(r"v=([A-Za-z0-9_-]{11})", video_url)
            if not match:
                return "Invalid YouTube URL."
            video_id = match.group(1)

            # Fetch transcript
            transcript_list = YouTubeTranscriptApi.get_transcript(video_id)
            transcript_text = " ".join([t["text"] for t in transcript_list])

            return transcript_text

        except NoTranscriptFound:
            return "Transcript not available for this video."
        except TranscriptsDisabled:
            return "Transcripts are disabled for this video."
        except Exception as e:
            return f"Error fetching transcript: {str(e)}"