From fb30ec22fd25e2dfc57ecf821d3072c2d8ab3ce7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Fri, 6 Dec 2013 22:01:41 +0100 Subject: [PATCH] [vimeo] Add an extractor for groups --- test/test_playlists.py | 9 +++++++++ youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/vimeo.py | 24 +++++++++++++++++++----- 3 files changed, 29 insertions(+), 5 deletions(-) diff --git a/test/test_playlists.py b/test/test_playlists.py index 6a5e0b780..87ca401e5 100644 --- a/test/test_playlists.py +++ b/test/test_playlists.py @@ -17,6 +17,7 @@ from youtube_dl.extractor import ( VimeoChannelIE, VimeoUserIE, VimeoAlbumIE, + VimeoGroupsIE, UstreamChannelIE, SoundcloudSetIE, SoundcloudUserIE, @@ -74,6 +75,14 @@ class TestPlaylists(unittest.TestCase): self.assertEqual(result['title'], u'Staff Favorites: November 2013') self.assertTrue(len(result['entries']) > 12) + def test_vimeo_groups(self): + dl = FakeYDL() + ie = VimeoGroupsIE(dl) + result = ie.extract('http://vimeo.com/groups/rolexawards') + self.assertIsPlaylist(result) + self.assertEqual(result['title'], u'Rolex Awards for Enterprise') + self.assertTrue(len(result['entries']) > 72) + def test_ustream_channel(self): dl = FakeYDL() ie = UstreamChannelIE(dl) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index ac0a11dfe..f6a23f663 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -171,6 +171,7 @@ from .vimeo import ( VimeoChannelIE, VimeoUserIE, VimeoAlbumIE, + VimeoGroupsIE, ) from .vine import VineIE from .viki import VikiIE diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 293dad3c0..fb2bd225a 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -20,7 +20,7 @@ class VimeoIE(InfoExtractor): """Information extractor for vimeo.com.""" # _VALID_URL matches Vimeo URLs - _VALID_URL = r'(?Phttps?://)?(?:(?:www|(?Pplayer))\.)?vimeo(?Ppro)?\.com/(?:(?:(?:groups)/[^/]+)|(?:.*?)/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)/?(?:[?].*)?(?:#.*)?$' + _VALID_URL = r'(?Phttps?://)?(?:(?:www|(?Pplayer))\.)?vimeo(?Ppro)?\.com/(?:.*?/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)/?(?:[?].*)?(?:#.*)?$' _NETRC_MACHINE = 'vimeo' IE_NAME = u'vimeo' _TESTS = [ @@ -267,6 +267,9 @@ class VimeoChannelIE(InfoExtractor): def _page_url(self, base_url, pagenum): return '%s/videos/page:%d/' % (base_url, pagenum) + def _extract_list_title(self, webpage): + return self._html_search_regex(self._TITLE_RE, webpage, u'list title') + def _extract_videos(self, list_id, base_url): video_ids = [] for pagenum in itertools.count(1): @@ -279,11 +282,9 @@ class VimeoChannelIE(InfoExtractor): entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo') for video_id in video_ids] - list_title = self._html_search_regex(self._TITLE_RE, webpage, - u'list title') return {'_type': 'playlist', 'id': list_id, - 'title': list_title, + 'title': self._extract_list_title(webpage), 'entries': entries, } @@ -300,7 +301,7 @@ class VimeoUserIE(VimeoChannelIE): @classmethod def suitable(cls, url): - if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url) or VimeoAlbumIE.suitable(url): + if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url) or VimeoAlbumIE.suitable(url) or VimeoGroupsIE.suitable(url): return False return super(VimeoUserIE, cls).suitable(url) @@ -322,3 +323,16 @@ class VimeoAlbumIE(VimeoChannelIE): mobj = re.match(self._VALID_URL, url) album_id = mobj.group('id') return self._extract_videos(album_id, 'http://vimeo.com/album/%s' % album_id) + + +class VimeoGroupsIE(VimeoAlbumIE): + IE_NAME = u'vimeo:group' + _VALID_URL = r'(?:https?://)?vimeo.\com/groups/(?P[^/]+)' + + def _extract_list_title(self, webpage): + return self._og_search_title(webpage) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + name = mobj.group('name') + return self._extract_videos(name, 'http://vimeo.com/groups/%s' % name)