util.py

from urllib.parse import urlparse, parse_qs
from youtube_transcript_api import YouTubeTranscriptApi

def get_video_id(url: str) -> str:
    """
    Examples:
    - http://youtu.be/SA2iWivDJiE
    - http://www.youtube.com/watch?v=_oPAwA_Udwc&feature=feedu
    - http://www.youtube.com/embed/SA2iWivDJiE
    - http://www.youtube.com/v/SA2iWivDJiE?version=3&hl=en_US
    """
    query = urlparse(url)
    if query.hostname == 'youtu.be':
        return query.path[1:]
    if query.hostname in ('www.youtube.com', 'youtube.com'):
        if query.path == '/watch':
            p = parse_qs(query.query)
            return p['v'][0]
        if query.path[:7] == '/embed/':
            return query.path.split('/')[2]
        if query.path[:3] == '/v/':
            return query.path.split('/')[2]
    return None


def get_youtube_subtitle(video_id: str) -> str:
    try:  
        parse = YouTubeTranscriptApi.get_transcript(video_id, languages=['ru'])
        result = ''
        for i in parse:
            if (i['text'][0] =='[') & (i['text'][-1] ==']'): continue
            result += ' ' + i['text']
        result = result.strip()[0].upper() + result.strip()[1:]
        return result.strip()
    except:
        return None