youtube_utils.py

#                             YouTubeMDBot
#                  Copyright (C) 2019 - Javinator9889
#
#    This program is free software: you can redistribute it and/or modify
#    it under the terms of the GNU General Public License as published by
#      the Free Software Foundation, either version 3 of the License, or
#                   (at your option) any later version.
#
#       This program is distributed in the hope that it will be useful,
#       but WITHOUT ANY WARRANTY; without even the implied warranty of
#        MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
#               GNU General Public License for more details.
#
#     You should have received a copy of the GNU General Public License
#    along with this program. If not, see <http://www.gnu.org/licenses/>.


def get_yt_video_id(url: str) -> str:
    # initial version: http://stackoverflow.com/a/7936523/617185 \
    #    by Mikhail Kashkin(http://stackoverflow.com/users/85739/mikhail-kashkin)
    """Returns Video_ID extracting from the given url of Youtube

    Examples of URLs:
      Valid:
        'http://youtu.be/_lOT2p_FCvA',
        'www.youtube.com/watch?v=_lOT2p_FCvA&feature=feedu',
        'http://www.youtube.com/embed/_lOT2p_FCvA',
        'http://www.youtube.com/v/_lOT2p_FCvA?version=3&amp;hl=en_US',
        'https://www.youtube.com/watch?v=rTHlyTphWP0&index=6&list=PLjeDyYvG6-40qawYNR4juzvSOg-ezZ2a6',
        'youtube.com/watch?v=_lOT2p_FCvA',

      Invalid:
        'youtu.be/watch?v=_lOT2p_FCvA',
    """

    from urllib.parse import urlparse
    from urllib.parse import parse_qs

    if url.startswith(('youtu', 'www')):
        url = 'http://' + url

    query = urlparse(url)

    if 'youtube' in query.hostname:
        if query.path == '/watch':
            return parse_qs(query.query)['v'][0]
        elif query.path.startswith(('/embed/', '/v/')):
            return query.path.split('/')[2]
    elif 'youtu.be' in query.hostname:
        return query.path[1:]
    else:
        raise ValueError