jcgruenhage/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[youtube:feeds] Use the 'paging' value from the downloaded json information (fixes #1845)

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-11-28 00:33:27 +01:00
parent 35907e23ec
commit 0e44d8381a
1 changed files with 3 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
youtube_dl/extractor/youtube.py
View file

@ -1791,7 +1791,6 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties. Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
""" """
_LOGIN_REQUIRED = True _LOGIN_REQUIRED = True
_PAGING_STEP = 30
# use action_load_personal_feed instead of action_load_system_feed # use action_load_personal_feed instead of action_load_system_feed
_PERSONAL_FEED = False _PERSONAL_FEED = False
@ -1811,9 +1810,8 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
feed_entries = [] feed_entries = []
# The step argument is available only in 2.7 or higher paging = 0
for i in itertools.count(0): for i in itertools.count(1):
paging = i*self._PAGING_STEP
info = self._download_webpage(self._FEED_TEMPLATE % paging, info = self._download_webpage(self._FEED_TEMPLATE % paging,
u'%s feed' % self._FEED_NAME, u'%s feed' % self._FEED_NAME,
u'Downloading page %s' % i) u'Downloading page %s' % i)
@ -1826,6 +1824,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
for video_id in ids) for video_id in ids)
if info['paging'] is None: if info['paging'] is None:
break break
paging = info['paging']
return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE) return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE)
class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
@ -1845,7 +1844,6 @@ class YoutubeWatchLaterIE(YoutubeFeedsInfoExtractor):
_VALID_URL = r'https?://www\.youtube\.com/feed/watch_later|:ytwatchlater' _VALID_URL = r'https?://www\.youtube\.com/feed/watch_later|:ytwatchlater'
_FEED_NAME = 'watch_later' _FEED_NAME = 'watch_later'
_PLAYLIST_TITLE = u'Youtube Watch Later' _PLAYLIST_TITLE = u'Youtube Watch Later'
_PAGING_STEP = 100
_PERSONAL_FEED = True _PERSONAL_FEED = True
class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
@ -1855,13 +1853,6 @@ class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
_PERSONAL_FEED = True _PERSONAL_FEED = True
_PLAYLIST_TITLE = u'Youtube Watch History' _PLAYLIST_TITLE = u'Youtube Watch History'
def _real_extract(self, url):
webpage = self._download_webpage('https://www.youtube.com/feed/history', u'History')
data_paging = self._search_regex(r'data-paging="(\d+)"', webpage, u'data-paging')
# The step is actually a ridiculously big number (like 1374343569725646)
self._PAGING_STEP = int(data_paging)
return super(YoutubeHistoryIE, self)._real_extract(url)
class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
IE_NAME = u'youtube:favorites' IE_NAME = u'youtube:favorites'
IE_DESC = u'YouTube.com favourite videos, "ytfav" keyword (requires authentication)' IE_DESC = u'YouTube.com favourite videos, "ytfav" keyword (requires authentication)'