[vimeo] Add an extractor for albums (closes #1911)

This commit is contained in:
Jaime Marquínez Ferrándiz 2013-12-06 21:47:32 +01:00
parent d349cd2240
commit 5cc14c2fd7
3 changed files with 30 additions and 3 deletions

View File

@ -16,6 +16,7 @@ from youtube_dl.extractor import (
DailymotionUserIE, DailymotionUserIE,
VimeoChannelIE, VimeoChannelIE,
VimeoUserIE, VimeoUserIE,
VimeoAlbumIE,
UstreamChannelIE, UstreamChannelIE,
SoundcloudSetIE, SoundcloudSetIE,
SoundcloudUserIE, SoundcloudUserIE,
@ -65,6 +66,14 @@ class TestPlaylists(unittest.TestCase):
self.assertEqual(result['title'], u'Nki') self.assertEqual(result['title'], u'Nki')
self.assertTrue(len(result['entries']) > 65) self.assertTrue(len(result['entries']) > 65)
def test_vimeo_album(self):
dl = FakeYDL()
ie = VimeoAlbumIE(dl)
result = ie.extract('http://vimeo.com/album/2632481')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], u'Staff Favorites: November 2013')
self.assertTrue(len(result['entries']) > 12)
def test_ustream_channel(self): def test_ustream_channel(self):
dl = FakeYDL() dl = FakeYDL()
ie = UstreamChannelIE(dl) ie = UstreamChannelIE(dl)

View File

@ -170,6 +170,7 @@ from .vimeo import (
VimeoIE, VimeoIE,
VimeoChannelIE, VimeoChannelIE,
VimeoUserIE, VimeoUserIE,
VimeoAlbumIE,
) )
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|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$' _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|(?P<player>player))\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$'
_NETRC_MACHINE = 'vimeo' _NETRC_MACHINE = 'vimeo'
IE_NAME = u'vimeo' IE_NAME = u'vimeo'
_TESTS = [ _TESTS = [
@ -264,11 +264,14 @@ class VimeoChannelIE(InfoExtractor):
_MORE_PAGES_INDICATOR = r'<a.+?rel="next"' _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
_TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"' _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
def _page_url(self, base_url, pagenum):
return '%s/videos/page:%d/' % (base_url, pagenum)
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):
webpage = self._download_webpage( webpage = self._download_webpage(
'%s/videos/page:%d/' % (base_url, pagenum),list_id, self._page_url(base_url, pagenum) ,list_id,
u'Downloading page %s' % pagenum) u'Downloading page %s' % pagenum)
video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage)) video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
@ -297,7 +300,7 @@ class VimeoUserIE(VimeoChannelIE):
@classmethod @classmethod
def suitable(cls, url): def suitable(cls, url):
if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url): if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url) or VimeoAlbumIE.suitable(url):
return False return False
return super(VimeoUserIE, cls).suitable(url) return super(VimeoUserIE, cls).suitable(url)
@ -305,3 +308,17 @@ class VimeoUserIE(VimeoChannelIE):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
name = mobj.group('name') name = mobj.group('name')
return self._extract_videos(name, 'http://vimeo.com/%s' % name) return self._extract_videos(name, 'http://vimeo.com/%s' % name)
class VimeoAlbumIE(VimeoChannelIE):
IE_NAME = u'vimeo:album'
_VALID_URL = r'(?:https?://)?vimeo.\com/album/(?P<id>\d+)'
_TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
def _page_url(self, base_url, pagenum):
return '%s/page:%d/' % (base_url, pagenum)
def _real_extract(self, url):
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)