from youtube_transcript_api import YouTubeTranscriptApi
from googleapiclient.discovery import build
from docx import Document
import re
import os

def get_youtube_transcript(video_id):
    try:
        transcript = YouTubeTranscriptApi.get_transcript(video_id)
        return transcript
    except Exception as e:
        print(f"An error occurred: {e}")
        return None

def get_video_title(api_key, video_id):
    youtube = build('youtube', 'v3', developerKey=api_key)
    request = youtube.videos().list(part='snippet', id=video_id)
    response = request.execute()
    if 'items' in response and len(response['items']) > 0:
        return response['items'][0]['snippet']['title']
    return None

def save_transcript_to_doc(transcript, filename):
    doc = Document()
    doc.add_heading('YouTube Video Transcript', 0)
    
    for entry in transcript:
        start_time = entry['start']
        duration = entry['duration']
        text = entry['text']
        doc.add_paragraph(f"{start_time:.2f} - {duration:.2f}: {text}")
    
    doc.save(filename)

def sanitize_filename(filename):
    return re.sub(r'[\\/*?:"<>|]', "_", filename)

if __name__ == "__main__":
    api_key = os.getenv('YOUR_YOUTUBE_DATA_API_KEY')  # Replace this with your API key
    video_id = 'nTQIYWgn-lQ'  # Replace this with your video ID

    transcript = get_youtube_transcript(video_id)
    video_title = get_video_title(api_key, video_id)

    if transcript and video_title:
        sanitized_title = sanitize_filename(video_title)
        output_filename = f"./{sanitized_title}.txt"
        #save_transcript_to_doc(transcript, output_filename)
        print(f"Transcript texty is {transcript}.")
    else:
        print("Transcript or video title not available.")