[vimeo] add an extractor for channels

diff --git a/test/test_playlists.py b/test/test_playlists.py
index f8cc75afbe4b1ff7740700cd22bb6be961813b4c..65de3a55c8694dd764dafa10977448d9274727d2 100644 (file)
--- a/test/test_playlists.py
+++ b/test/test_playlists.py
@@ -8,7 +8,7 @@ import json
 import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 

-from youtube_dl.extractor import DailymotionPlaylistIE
+from youtube_dl.extractor import DailymotionPlaylistIE, VimeoChannelIE

 from youtube_dl.utils import *
 
 from helper import FakeYDL
 from youtube_dl.utils import *
 
 from helper import FakeYDL


@@ -26,5 +26,13 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['title'], u'SPORT')
         self.assertTrue(len(result['entries']) > 20)
 
         self.assertEqual(result['title'], u'SPORT')
         self.assertTrue(len(result['entries']) > 20)
 

+    def test_vimeo_channel(self):
+        dl = FakeYDL()
+        ie = VimeoChannelIE(dl)
+        result = ie.extract('http://vimeo.com/channels/tributes')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'Vimeo Tributes')
+        self.assertTrue(len(result['entries']) > 24)
+

 if __name__ == '__main__':
     unittest.main()
 if __name__ == '__main__':
     unittest.main()

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 063a3d0658fa66536fe43ff3e872567c0e9a6031..9f4dd3c243aaf8fa962ab3b42e674177f14621af 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -71,7 +71,7 @@ from .ustream import UstreamIE
 from .vbox7 import Vbox7IE
 from .veoh import VeohIE
 from .vevo import VevoIE
 from .vbox7 import Vbox7IE
 from .veoh import VeohIE
 from .vevo import VevoIE

-from .vimeo import VimeoIE
+from .vimeo import VimeoIE, VimeoChannelIE

 from .vine import VineIE
 from .c56 import C56IE
 from .wat import WatIE
 from .vine import VineIE
 from .c56 import C56IE
 from .wat import WatIE

diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py
index ac32043c1e651abaadf1a223c18e4983b9301ba7..cc9c8d0188749761b79b90652d3c0c843a24eda3 100644 (file)
--- a/youtube_dl/extractor/vimeo.py
+++ b/youtube_dl/extractor/vimeo.py
@@ -1,5 +1,6 @@
 import json
 import re
 import json
 import re

+import itertools

 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (


@@ -171,3 +172,31 @@ class VimeoIE(InfoExtractor):
             'thumbnail':    video_thumbnail,
             'description':  video_description,
         }]
             'thumbnail':    video_thumbnail,
             'description':  video_description,
         }]

+
+
+class VimeoChannelIE(InfoExtractor):
+    IE_NAME = u'vimeo:channel'
+    _VALID_URL = r'(?:https?://)?vimeo.\com/channels/(?P<id>[^/]+)'
+    _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        channel_id =  mobj.group('id')
+        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)
+            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')
+        return {'_type': 'playlist',
+                'id': channel_id,
+                'title': channel_title,
+                'entries': entries,
+                }