def get_vid_from_url(url):
"""Extracts video ID from URL.
"""
return match1(url, r'youtu\.be/([^?/]+)') or \
match1(url, r'youtube\.com/embed/([^/?]+)') or \
match1(url, r'youtube\.com/v/([^/?]+)') or \
match1(url, r'youtube\.com/watch/([^/?]+)') or \
parse_query_param(url, 'v') or \
parse_query_param(parse_query_param(url, 'u'), 'v')
def download_playlist_by_url(self, url, **kwargs):
self.url = url
playlist_id = self.__class__.get_playlist_id_from_url(self.url)
if playlist_id is None:
log.wtf('[Failed] Unsupported URL pattern.')
video_page = get_content(
'https://www.youtube.com/playlist?list={}'.format(playlist_id))
from html.parser import HTMLParser
videos = sorted([
HTMLParser().unescape(video)
for video in re.findall(r'<a href="(/watch\?[^"]+)"', video_page)
if parse_query_param(video, 'index')
],
key=lambda video: parse_query_param(video, 'index'))
# Parse browse_ajax page for more videos to load
load_more_href = match1(video_page,
r'data-uix-load-more-href="([^"]+)"')
while load_more_href:
browse_ajax = get_content(
'https://www.youtube.com/{}'.format(load_more_href))
browse_data = json.loads(browse_ajax)
load_more_widget_html = browse_data['load_more_widget_html']
content_html = browse_data['content_html']
vs = set(re.findall(r'href="(/watch\?[^"]+)"', content_html))
videos += sorted([
HTMLParser().unescape(video) for video in list(vs)
if parse_query_param(video, 'index')
])
load_more_href = match1(load_more_widget_html,
r'data-uix-load-more-href="([^"]+)"')
self.title = re.search(r'<meta name="title" content="([^"]+)"',
video_page).group(1)
self.p_playlist()
for video in videos:
vid = parse_query_param(video, 'v')
index = parse_query_param(video, 'index')
self.__class__().download_by_url(
self.__class__.get_url_from_vid(vid), index=index, **kwargs)
def get_playlist_id_from_url(url):
"""Extracts playlist ID from URL.
"""
return parse_query_param(url, 'list') or \
parse_query_param(url, 'p')