video_utils.py

from urllib.parse import urlparse, parse_qs


def video_id(value):
    """Video ID from youtube, vimeo and facebook links

    >>> video_id('http://youtu.be/SA2iWivDJiE')
    'SA2iWivDJiE'
    >>> video_id('http://www.youtube.com/watch?v=_oPAwA_Udwc&feature=feedu')
    '_oPAwA_Udwc'
    >>> video_id('http://www.youtube.com/embed/SA2iWivDJiE')
    'SA2iWivDJiE'
    >>> video_id('http://www.youtube.com/v/SA2iWivDJiE?version=3&hl=en_US')
    'SA2iWivDJiE'
    >>> video_id('http://vimeo.com/999999')
    '999999'
    >>> video_id('http://www.vimeo.com/999999')
    '999999'
    >>> video_id('http://player.vimeo.com/video/999999')
    '999999'
    >>> video_id('https://facebook.com/pagina/videos/9999999999999999/')
    '9999999999999999'
    >>> video_id('https://web.facebook.com/pagina/videos/9999999999999999/')
    '9999999999999999'
    >>> video_id('https://www.facebook.com/pagina/videos/9999999999999999/')
    '9999999999999999'
    """

    result = urlparse(value)
    if result.hostname == 'youtu.be':
        return result.path[1:]
    if result.hostname in ('www.youtube.com', 'youtube.com'):
        if result.path == '/watch':
            p = parse_qs(result.query)
            return p['v'][0]
        if result.path[:7] == '/embed/':
            return result.path.split('/')[2]
        if result.path[:3] == '/v/':
            return result.path.split('/')[2]
    if result.hostname in ('vimeo.com', 'www.vimeo.com'):
        return result.path.split('/')[1]
    elif result.hostname == 'player.vimeo.com':
        return result.path.split('/')[2]
    if result.hostname in ('web.facebook.com', 'facebook.com', 'www.facebook.com'):
        return result.path.split('/')[3]
    return None


if __name__ == '__main__':
    import doctest
    doctest.testmod()