diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2014-09-01 00:01:48 +0200 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2014-09-01 00:01:48 +0200 |
commit | 7d48c06f27fba7287c6c548e930f90f3aebac07a (patch) | |
tree | 91351ba2ce7b52ab6ea877216e9eb8327a907839 /youtube_dl/extractor/youtube.py | |
parent | d169e36f5c4dc50a6c19c2155ea7ea7a89dd5c31 (diff) | |
parent | 9ea9b614489038cc7e51f71c0f8ecc7d84534a30 (diff) | |
download | youtube-dl-7d48c06f27fba7287c6c548e930f90f3aebac07a.tar.xz |
Merge remote-tracking branch 'origin/master'
Diffstat (limited to 'youtube_dl/extractor/youtube.py')
-rw-r--r-- | youtube_dl/extractor/youtube.py | 43 |
1 files changed, 37 insertions, 6 deletions
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 3417c1275..78f3b7e7b 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1434,12 +1434,6 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): paging = mobj.group('paging') return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE) -class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): - IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' - _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' - _FEED_NAME = 'subscriptions' - _PLAYLIST_TITLE = u'Youtube Subscriptions' - class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): IE_DESC = u'YouTube.com recommended videos, "ytrec" keyword (requires authentication)' _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?' @@ -1472,6 +1466,43 @@ class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): return self.url_result(playlist_id, 'YoutubePlaylist') +class YoutubeSubscriptionsIE(YoutubePlaylistIE): + IE_NAME = u'youtube:subscriptions' + IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' + _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' + + def _real_extract(self, url): + title = u'Youtube Subscriptions' + page = self._download_webpage('https://www.youtube.com/feed/subscriptions', title) + + # The extraction process is the same as for playlists, but the regex + # for the video ids doesn't contain an index + ids = [] + more_widget_html = content_html = page + + for page_num in itertools.count(1): + matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) + new_ids = orderedSet(matches) + ids.extend(new_ids) + + mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) + if not mobj: + break + + more = self._download_json( + 'https://youtube.com/%s' % mobj.group('more'), title, + 'Downloading page #%s' % page_num, + transform_source=uppercase_escape) + content_html = more['content_html'] + more_widget_html = more['load_more_widget_html'] + + return { + '_type': 'playlist', + 'title': title, + 'entries': self._ids_to_results(ids), + } + + class YoutubeTruncatedURLIE(InfoExtractor): IE_NAME = 'youtube:truncated_url' IE_DESC = False # Do not list |