[vimeo] Add an extractor for groups

This commit is contained in:
Jaime Marquínez Ferrándiz 2013-12-06 22:01:41 +01:00
parent 5cc14c2fd7
commit fb30ec22fd
3 changed files with 29 additions and 5 deletions

View file

@ -17,6 +17,7 @@ from youtube_dl.extractor import (
VimeoChannelIE, VimeoChannelIE,
VimeoUserIE, VimeoUserIE,
VimeoAlbumIE, VimeoAlbumIE,
VimeoGroupsIE,
UstreamChannelIE, UstreamChannelIE,
SoundcloudSetIE, SoundcloudSetIE,
SoundcloudUserIE, SoundcloudUserIE,
@ -74,6 +75,14 @@ class TestPlaylists(unittest.TestCase):
self.assertEqual(result['title'], u'Staff Favorites: November 2013') self.assertEqual(result['title'], u'Staff Favorites: November 2013')
self.assertTrue(len(result['entries']) > 12) 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): def test_ustream_channel(self):
dl = FakeYDL() dl = FakeYDL()
ie = UstreamChannelIE(dl) ie = UstreamChannelIE(dl)

View file

@ -171,6 +171,7 @@ from .vimeo import (
VimeoChannelIE, VimeoChannelIE,
VimeoUserIE, VimeoUserIE,
VimeoAlbumIE, VimeoAlbumIE,
VimeoGroupsIE,
) )
from .vine import VineIE from .vine import VineIE
from .viki import VikiIE from .viki import VikiIE

View file

@ -20,7 +20,7 @@ class VimeoIE(InfoExtractor):
"""Information extractor for vimeo.com.""" """Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs # _VALID_URL matches Vimeo URLs
_VALID_URL = r'(?P<proto>https?://)?(?:(?:www|(?P<player>player))\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$' _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|(?P<player>player))\.)?vimeo(?P<pro>pro)?\.com/(?:.*?/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$'
_NETRC_MACHINE = 'vimeo' _NETRC_MACHINE = 'vimeo'
IE_NAME = u'vimeo' IE_NAME = u'vimeo'
_TESTS = [ _TESTS = [
@ -267,6 +267,9 @@ class VimeoChannelIE(InfoExtractor):
def _page_url(self, base_url, pagenum): def _page_url(self, base_url, pagenum):
return '%s/videos/page:%d/' % (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): def _extract_videos(self, list_id, base_url):
video_ids = [] video_ids = []
for pagenum in itertools.count(1): for pagenum in itertools.count(1):
@ -279,11 +282,9 @@ class VimeoChannelIE(InfoExtractor):
entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo') entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
for video_id in video_ids] for video_id in video_ids]
list_title = self._html_search_regex(self._TITLE_RE, webpage,
u'list title')
return {'_type': 'playlist', return {'_type': 'playlist',
'id': list_id, 'id': list_id,
'title': list_title, 'title': self._extract_list_title(webpage),
'entries': entries, 'entries': entries,
} }
@ -300,7 +301,7 @@ class VimeoUserIE(VimeoChannelIE):
@classmethod @classmethod
def suitable(cls, url): 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 False
return super(VimeoUserIE, cls).suitable(url) return super(VimeoUserIE, cls).suitable(url)
@ -322,3 +323,16 @@ class VimeoAlbumIE(VimeoChannelIE):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
album_id = mobj.group('id') album_id = mobj.group('id')
return self._extract_videos(album_id, 'http://vimeo.com/album/%s' % album_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<name>[^/]+)'
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)