Merge remote-tracking branch 'rzhxeo/crunchyroll'

[youtube-dl] / youtube_dl / extractor / vimeo.py

diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py
index 293dad3c02e92b62dad48fe63f6fbf248fc14375..ea440952898a15f24019ba421c9efbe810ff1fec 100644 (file)
--- a/youtube_dl/extractor/vimeo.py
+++ b/youtube_dl/extractor/vimeo.py
@@ -20,7 +20,7 @@ class VimeoIE(InfoExtractor):
     """Information extractor for vimeo.com."""
 
     # _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'
     IE_NAME = u'vimeo'
     _TESTS = [
@@ -115,7 +115,7 @@ class VimeoIE(InfoExtractor):
     def _real_initialize(self):
         self._login()
 
-    def _real_extract(self, url, new_video=True):
+    def _real_extract(self, url):
         url, data = unsmuggle_url(url)
         headers = std_headers
         if data is not None:
@@ -151,8 +151,14 @@ class VimeoIE(InfoExtractor):
                 config = json.loads(config_json)
             except RegexNotFoundError:
                 # For pro videos or player.vimeo.com urls
-                config = self._search_regex([r' = {config:({.+?}),assets:', r'(?:c|b)=({.+?});'],
-                    webpage, u'info section', flags=re.DOTALL)
+                # We try to find out to which variable is assigned the config dic
+                m_variable_name = re.search('(\w)\.video\.id', webpage)
+                if m_variable_name is not None:
+                    config_re = r'%s=({.+?});' % re.escape(m_variable_name.group(1))
+                else:
+                    config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
+                config = self._search_regex(config_re, webpage, u'info section',
+                    flags=re.DOTALL)
                 config = json.loads(config)
         except Exception as e:
             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
@@ -267,6 +273,9 @@ class VimeoChannelIE(InfoExtractor):
     def _page_url(self, 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):
         video_ids = []
         for pagenum in itertools.count(1):
@@ -279,11 +288,9 @@ class VimeoChannelIE(InfoExtractor):
 
         entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
                    for video_id in video_ids]
-        list_title = self._html_search_regex(self._TITLE_RE, webpage,
-            u'list title')
         return {'_type': 'playlist',
                 'id': list_id,
-                'title': list_title,
+                'title': self._extract_list_title(webpage),
                 'entries': entries,
                 }
 
@@ -300,7 +307,7 @@ class VimeoUserIE(VimeoChannelIE):
 
     @classmethod
     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 super(VimeoUserIE, cls).suitable(url)
 
@@ -322,3 +329,16 @@ class VimeoAlbumIE(VimeoChannelIE):
         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)
+
+
+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)