[vimeo] Add an extractor for users (closes #1871)

diff --git a/test/test_all_urls.py b/test/test_all_urls.py
index 1f1adb6b46e0fa2e8a683e6593f699476397a0cd..6b9764c67e98ba47a63b227d824bb97b82757b53 100644 (file)
--- 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 167801ae246087aae4c7068cb11b84245e560649..13a6f4b2fb88da50bf42fa38bbb2203b06807bc7 100644 (file)
--- 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 664639b53e642b39c58b3d9721f74b6e63448f67..cc93e619c034577d4204e75b3a8f22f374b95861 100644 (file)
--- 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 7d82c2cfa84bd9b57b7ebc9eb35537b4033ba45d..f27763ae2ff110051613243ef2543e3349d6b019 100644 (file)
--- 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<id>[^/]+)'
     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
+    _TITLE_RE = r'<link rel="alternate"[^>]+?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'<a href="/channels/%s">(.*?)</a>' % 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<name>[^/]+)'
+    _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
+
+    @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)