src/blogGenerator/nodes/yt_transcript_node.py

from blogGenerator.state.state import State
from youtube_transcript_api import YouTubeTranscriptApi


class YTTranscriptNode:
    """
    Get Youtube transcription
    """

    def process(self, state: State) -> dict:
        """Fetches transcript from a given YouTube URL"""

        # print(f"Node Called : yt_transcipt")

        video_id = state["yt_url"].replace("https://www.youtube.com/watch?v=", "")

        try:
            transcript = YouTubeTranscriptApi.get_transcript(video_id)
            output = "\n".join([x["text"] for x in transcript])
            # print(f"Output : {output}")
            print("✅ Transcription fetched successfully.")
        except Exception as e:
            print(f"❌ Error fetching transcript: {e}")
            output = ""

        return {"yt_transcript": output}