mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-09-05 10:29:35 +02:00
[youtube:playlist] Fetch all the videos in a mix (fixes #3837)
Since there doesn't seem to be any indication, it stops when there aren't new videos in the webpage.
This commit is contained in:
parent
7bab22a402
commit
1b6182d8f7
@ -44,7 +44,7 @@ def test_youtube_mix(self):
|
|||||||
ie = YoutubePlaylistIE(dl)
|
ie = YoutubePlaylistIE(dl)
|
||||||
result = ie.extract('https://www.youtube.com/watch?v=W01L70IGBgE&index=2&list=RDOQpdSVF_k_w')
|
result = ie.extract('https://www.youtube.com/watch?v=W01L70IGBgE&index=2&list=RDOQpdSVF_k_w')
|
||||||
entries = result['entries']
|
entries = result['entries']
|
||||||
self.assertTrue(len(entries) >= 20)
|
self.assertTrue(len(entries) >= 50)
|
||||||
original_video = entries[0]
|
original_video = entries[0]
|
||||||
self.assertEqual(original_video['id'], 'OQpdSVF_k_w')
|
self.assertEqual(original_video['id'], 'OQpdSVF_k_w')
|
||||||
|
|
||||||
|
@ -1818,20 +1818,32 @@ def _real_initialize(self):
|
|||||||
def _extract_mix(self, playlist_id):
|
def _extract_mix(self, playlist_id):
|
||||||
# The mixes are generated from a single video
|
# The mixes are generated from a single video
|
||||||
# the id of the playlist is just 'RD' + video_id
|
# the id of the playlist is just 'RD' + video_id
|
||||||
url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id)
|
ids = []
|
||||||
webpage = self._download_webpage(
|
last_id = playlist_id[-11:]
|
||||||
url, playlist_id, 'Downloading Youtube mix')
|
for n in itertools.count(1):
|
||||||
|
url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
|
||||||
|
webpage = self._download_webpage(
|
||||||
|
url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
|
||||||
|
new_ids = orderedSet(re.findall(
|
||||||
|
r'''(?xs)data-video-username=".*?".*?
|
||||||
|
href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
|
||||||
|
webpage))
|
||||||
|
# Fetch new pages until all the videos are repeated, it seems that
|
||||||
|
# there are always 51 unique videos.
|
||||||
|
new_ids = [_id for _id in new_ids if _id not in ids]
|
||||||
|
if not new_ids:
|
||||||
|
break
|
||||||
|
ids.extend(new_ids)
|
||||||
|
last_id = ids[-1]
|
||||||
|
|
||||||
|
url_results = self._ids_to_results(ids)
|
||||||
|
|
||||||
search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
|
search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
|
||||||
title_span = (
|
title_span = (
|
||||||
search_title('playlist-title') or
|
search_title('playlist-title') or
|
||||||
search_title('title long-title') or
|
search_title('title long-title') or
|
||||||
search_title('title'))
|
search_title('title'))
|
||||||
title = clean_html(title_span)
|
title = clean_html(title_span)
|
||||||
ids = orderedSet(re.findall(
|
|
||||||
r'''(?xs)data-video-username=".*?".*?
|
|
||||||
href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
|
|
||||||
webpage))
|
|
||||||
url_results = self._ids_to_results(ids)
|
|
||||||
|
|
||||||
return self.playlist_result(url_results, playlist_id, title)
|
return self.playlist_result(url_results, playlist_id, title)
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user