From 55a10eab48776197245d3d87b86195f182d8d82a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Sun, 1 Dec 2013 22:36:18 +0100 Subject: [PATCH] [vimeo] Add an extractor for users (closes #1871) --- test/test_all_urls.py | 4 ++++ test/test_playlists.py | 9 +++++++ youtube_dl/extractor/__init__.py | 6 ++++- youtube_dl/extractor/vimeo.py | 41 ++++++++++++++++++++++++-------- 4 files changed, 49 insertions(+), 11 deletions(-) diff --git a/test/test_all_urls.py b/test/test_all_urls.py index 1f1adb6b46..6b9764c67e 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -106,6 +106,10 @@ class TestAllURLsMatching(unittest.TestCase): self.assertMatch(':colbertreport', ['ComedyCentralShows']) self.assertMatch(':cr', ['ComedyCentralShows']) + def test_vimeo_matching(self): + self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel']) + self.assertMatch('http://vimeo.com/user7108434', ['vimeo:user']) + if __name__ == '__main__': unittest.main() diff --git a/test/test_playlists.py b/test/test_playlists.py index 167801ae24..13a6f4b2fb 100644 --- a/test/test_playlists.py +++ b/test/test_playlists.py @@ -15,6 +15,7 @@ from youtube_dl.extractor import ( DailymotionPlaylistIE, DailymotionUserIE, VimeoChannelIE, + VimeoUserIE, UstreamChannelIE, SoundcloudSetIE, SoundcloudUserIE, @@ -54,6 +55,14 @@ class TestPlaylists(unittest.TestCase): self.assertEqual(result['title'], u'Vimeo Tributes') self.assertTrue(len(result['entries']) > 24) + def test_vimeo_user(self): + dl = FakeYDL() + ie = VimeoUserIE(dl) + result = ie.extract('http://vimeo.com/nkistudio/videos') + self.assertIsPlaylist(result) + self.assertEqual(result['title'], u'Nki') + self.assertTrue(len(result['entries']) > 65) + 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 664639b53e..cc93e619c0 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -159,7 +159,11 @@ from .viddler import ViddlerIE from .videodetective import VideoDetectiveIE from .videofyme import VideofyMeIE from .videopremium import VideoPremiumIE -from .vimeo import VimeoIE, VimeoChannelIE +from .vimeo import ( + VimeoIE, + VimeoChannelIE, + VimeoUserIE, +) from .vine import VineIE from .viki import VikiIE from .vk import VKIE diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 7d82c2cfa8..f27763ae2f 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -249,25 +249,46 @@ class VimeoChannelIE(InfoExtractor): IE_NAME = u'vimeo:channel' _VALID_URL = r'(?:https?://)?vimeo.\com/channels/(?P[^/]+)' _MORE_PAGES_INDICATOR = r']+?title="(.*?)"' - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - channel_id = mobj.group('id') + def _extract_videos(self, list_id, base_url): video_ids = [] - for pagenum in itertools.count(1): - webpage = self._download_webpage('http://vimeo.com/channels/%s/videos/page:%d' % (channel_id, pagenum), - channel_id, u'Downloading page %s' % pagenum) + webpage = self._download_webpage( + '%s/videos/page:%d/' % (base_url, pagenum),list_id, + u'Downloading page %s' % pagenum) video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage)) if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: break entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo') for video_id in video_ids] - channel_title = self._html_search_regex(r'(.*?)' % channel_id, - webpage, u'channel title') + list_title = self._html_search_regex(self._TITLE_RE, webpage, + u'list title') return {'_type': 'playlist', - 'id': channel_id, - 'title': channel_title, + 'id': list_id, + 'title': list_title, 'entries': entries, } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + channel_id = mobj.group('id') + return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id) + + +class VimeoUserIE(VimeoChannelIE): + IE_NAME = u'vimeo:user' + _VALID_URL = r'(?:https?://)?vimeo.\com/(?P[^/]+)' + _TITLE_RE = r']+?class="user">([^<>]+?)' + + @classmethod + def suitable(cls, url): + if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url): + return False + return super(VimeoUserIE, cls).suitable(url) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + name = mobj.group('name') + return self._extract_videos(name, 'http://vimeo.com/%s' % name)