tools/youtube_tools.py

from langchain_core.tools import tool
from youtube_transcript_api import YouTubeTranscriptApi, NoTranscriptFound, TranscriptsDisabled

@tool("youtube_transcript_extractor", parse_docstring=True)
def extract_youtube_transcript(youtube_url: str) -> str:
    """Extracts the transcript from a given YouTube video URL.

    Args:
        youtube_url (str): The URL of the YouTube video.

    Returns:
        str: The transcript as a single string, or an error message if the transcript
             cannot be found or an error occurs.
    """
    try:
        video_id = youtube_url.split("v=")[1].split("&")[0]
        transcript_list = YouTubeTranscriptApi.get_transcript(video_id)
        transcript = " ".join([item['text'] for item in transcript_list])
        return transcript
    except NoTranscriptFound:
        return "Error: No transcript found for this video. It might be disabled or not available in English."
    except TranscriptsDisabled:
        return "Error: Transcripts are disabled for this video."
    except Exception as e:
        return f"Error extracting transcript: {str(e)}"