Roxedus/ytdl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'master' of github.com:rg3/youtube-dl

Browse Source
This commit is contained in:
Philipp Hagemeister 2013-11-28 04:37:02 +01:00
commit 9d93e7da6c
2 changed files with 8 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
youtube_dl/extractor/yahoo.py
View File

@ -46,7 +46,7 @@ class YahooIE(InfoExtractor):
video_id = mobj.group('id') video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
items_json = self._search_regex(r'YVIDEO_INIT_ITEMS = ({.*?});$', items_json = self._search_regex(r'mediaItems: ({.*?})$',
webpage, u'items', flags=re.MULTILINE) webpage, u'items', flags=re.MULTILINE)
items = json.loads(items_json) items = json.loads(items_json)
info = items['mediaItems']['query']['results']['mediaObj'][0] info = items['mediaItems']['query']['results']['mediaObj'][0]
@ -91,17 +91,13 @@ class YahooIE(InfoExtractor):
formats.append(format_info) formats.append(format_info)
formats = sorted(formats, key=lambda f:(f['height'], f['width'])) formats = sorted(formats, key=lambda f:(f['height'], f['width']))
info = { return {
'id': video_id, 'id': video_id,
'title': meta['title'], 'title': meta['title'],
'formats': formats, 'formats': formats,
'description': clean_html(meta['description']), 'description': clean_html(meta['description']),
'thumbnail': meta['thumbnail'], 'thumbnail': meta['thumbnail'],
} }
# TODO: Remove when #980 has been merged
info.update(formats[-1])
return info
class YahooSearchIE(SearchInfoExtractor): class YahooSearchIE(SearchInfoExtractor):

19
youtube_dl/extractor/youtube.py
View File

@ -1547,7 +1547,9 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
# 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[2:], playlist_id) url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[2:], playlist_id)
webpage = self._download_webpage(url, playlist_id, u'Downloading Youtube mix') webpage = self._download_webpage(url, playlist_id, u'Downloading Youtube mix')
title = clean_html(get_element_by_attribute('class', 'title long-title', webpage)) title_span = (get_element_by_attribute('class', 'title long-title', webpage) or
get_element_by_attribute('class', 'title ', webpage))
title = clean_html(title_span)
video_re = r'data-index="\d+".*?href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s' % re.escape(playlist_id) video_re = r'data-index="\d+".*?href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s' % re.escape(playlist_id)
ids = orderedSet(re.findall(video_re, webpage)) ids = orderedSet(re.findall(video_re, webpage))
url_results = self._ids_to_results(ids) url_results = self._ids_to_results(ids)
@ -1789,7 +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
@ -1809,9 +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)
@ -1824,6 +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):
@ -1843,7 +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):
@ -1853,13 +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)'