[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:
Jaime Marquínez Ferrándiz 2016-04-17 17:07:57 +02:00
parent 7bab22a402
commit 1b6182d8f7
2 changed files with 21 additions and 9 deletions

View file

@ -44,7 +44,7 @@ class TestYoutubeLists(unittest.TestCase):
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/watch?v=W01L70IGBgE&index=2&list=RDOQpdSVF_k_w')
entries = result['entries']
self.assertTrue(len(entries) >= 20)
self.assertTrue(len(entries) >= 50)
original_video = entries[0]
self.assertEqual(original_video['id'], 'OQpdSVF_k_w')

View file

@ -1818,20 +1818,32 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
def _extract_mix(self, playlist_id):
# The mixes are generated from a single video
# 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 = []
last_id = playlist_id[-11:]
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 Youtube mix')
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)
title_span = (
search_title('playlist-title') or
search_title('title long-title') or
search_title('title'))
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)