From faab1d3836ca6c2a3c28ee02efe25d211282f45f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Fri, 6 Sep 2013 14:38:41 +0200 Subject: [youtube] Fix detection of feeds urls (fixes #1294) Urls like https://www.youtube.com/feed/watch_later were being as users (before the last changes to YoutubeUserIE, as videos) --- youtube_dl/extractor/youtube.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'youtube_dl/extractor/youtube.py') diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 98a44f333..62aecea02 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1015,14 +1015,14 @@ class YoutubeChannelIE(InfoExtractor): class YoutubeUserIE(InfoExtractor): IE_DESC = u'YouTube.com user videos (URL or "ytuser" keyword)' - _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?)|ytuser:)([A-Za-z0-9_-]+)' + _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?)|ytuser:)(?!feed/)([A-Za-z0-9_-]+)' _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' _GDATA_PAGE_SIZE = 50 _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d&alt=json' IE_NAME = u'youtube:user' def suitable(cls, url): - if YoutubeIE.suitable(url): return False + if YoutubeIE.suitable(url) or YoutubeFavouritesIE.suitable(url): return False else: return super(YoutubeUserIE, cls).suitable(url) def _real_extract(self, url): -- cgit v1.2.3 From e3ea47908747bff4b46b4000fb1de944b400c21a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Fri, 6 Sep 2013 16:24:24 +0200 Subject: [youtube] Fix some issues with the detection of playlist/channel urls (reported in #1374) They were being caught by YoutubeUserIE, now it only extracts a url if the rest of extractors aren't suitable. Now the url tests check that the urls can only be extracted with an specific extractor. --- youtube_dl/extractor/youtube.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'youtube_dl/extractor/youtube.py') diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 62aecea02..423a5e973 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -386,7 +386,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): @classmethod def suitable(cls, url): """Receives a URL and returns True if suitable for this IE.""" - if YoutubePlaylistIE.suitable(url) or YoutubeSubscriptionsIE.suitable(url): return False + if YoutubePlaylistIE.suitable(url): return False return re.match(cls._VALID_URL, url, re.VERBOSE) is not None def report_video_webpage_download(self, video_id): @@ -1021,8 +1021,12 @@ class YoutubeUserIE(InfoExtractor): _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d&alt=json' IE_NAME = u'youtube:user' + @classmethod def suitable(cls, url): - if YoutubeIE.suitable(url) or YoutubeFavouritesIE.suitable(url): return False + # Don't return True if the url can be extracted with other youtube + # extractor, the regex would is too permissive and it would match. + other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls) + if any(ie.suitable(url) for ie in other_ies): return False else: return super(YoutubeUserIE, cls).suitable(url) def _real_extract(self, url): -- cgit v1.2.3