from youtube_transcript_api import YouTubeTranscriptApi
from youtube_transcript_api.formatters import TextFormatter
from transformers import pipeline
import re
import gradio

pipe = pipeline("summarization", model="Falconsai/text_summarization")

def summary(text_transcript):
    output = pipe(text_transcript)
    return output[0]['summary_text']

def get_youtube_transcript(link):
    video_id= extract_youtube_id(link)
    if not video_id:
        return "Video ID could not be extracted"

    try:
        transcript= YouTubeTranscriptApi.get_transcript(video_id) # fetches the trancript

        formatter= TextFormatter()
        text_transcript = formatter.format_transcript(transcript) # This will format the transcript
        
        summarized_text = summary(text_transcript)
        
        return summarized_text
    except Exception as e:
        return f"An error has occured: {e}"