Merge tag 'upstream/2015.06.04.1'

[youtubedl] / youtube_dl / extractor / vimeo.py

diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py
index 255855558cf64ddfe847db56e00e029f4bbbdf22..f300c7ca40eeba75f872bbd6cd79c3f0720e0955 100644 (file)
--- a/youtube_dl/extractor/vimeo.py
+++ b/youtube_dl/extractor/vimeo.py
@@ -6,19 +6,22 @@ import re
 import itertools
 
 from .common import InfoExtractor
 import itertools
 
 from .common import InfoExtractor

-from .subtitles import SubtitlesInfoExtractor
-from ..utils import (
+from ..compat import (

     compat_HTTPError,
     compat_urllib_parse,
     compat_urllib_request,
     compat_HTTPError,
     compat_urllib_parse,
     compat_urllib_request,

-    clean_html,
-    get_element_by_attribute,
+    compat_urlparse,
+)
+from ..utils import (

     ExtractorError,
     ExtractorError,

+    InAdvancePagedList,
+    int_or_none,

     RegexNotFoundError,
     RegexNotFoundError,

+    smuggle_url,

     std_headers,
     std_headers,

+    unified_strdate,

     unsmuggle_url,
     urlencode_postdata,
     unsmuggle_url,
     urlencode_postdata,

-    int_or_none,

 )
 
 
 )
 
 


@@ -35,7 +38,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
         self.report_login()
         login_url = 'https://vimeo.com/log_in'
         webpage = self._download_webpage(login_url, None, False)
         self.report_login()
         login_url = 'https://vimeo.com/log_in'
         webpage = self._download_webpage(login_url, None, False)

-        token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
+        token = self._search_regex(r'xsrft":"(.*?)"', webpage, 'login token')

         data = urlencode_postdata({
             'email': username,
             'password': password,
         data = urlencode_postdata({
             'email': username,
             'password': password,


@@ -49,14 +52,15 @@ class VimeoBaseInfoExtractor(InfoExtractor):
         self._download_webpage(login_request, None, False, 'Wrong login info')
 
 
         self._download_webpage(login_request, None, False, 'Wrong login info')
 
 

-class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
+class VimeoIE(VimeoBaseInfoExtractor):

     """Information extractor for vimeo.com."""
 
     # _VALID_URL matches Vimeo URLs
     _VALID_URL = r'''(?x)
     """Information extractor for vimeo.com."""
 
     # _VALID_URL matches Vimeo URLs
     _VALID_URL = r'''(?x)

-        (?P<proto>(?:https?:)?//)?
+        https?://

         (?:(?:www|(?P<player>player))\.)?
         vimeo(?P<pro>pro)?\.com/
         (?:(?:www|(?P<player>player))\.)?
         vimeo(?P<pro>pro)?\.com/

+        (?!channels/[^/?#]+/?(?:$|[?#])|album/)

         (?:.*?/)?
         (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
         (?:videos?/)?
         (?:.*?/)?
         (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
         (?:videos?/)?


@@ -88,6 +92,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
                 'uploader_id': 'openstreetmapus',
                 'uploader': 'OpenStreetMap US',
                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
                 'uploader_id': 'openstreetmapus',
                 'uploader': 'OpenStreetMap US',
                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',

+                'description': 'md5:380943ec71b89736ff4bf27183233d09',

                 'duration': 1595,
             },
         },
                 'duration': 1595,
             },
         },


@@ -98,10 +103,11 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
             'info_dict': {
                 'id': '54469442',
                 'ext': 'mp4',
             'info_dict': {
                 'id': '54469442',
                 'ext': 'mp4',

-                'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software',
+                'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',

                 'uploader': 'The BLN & Business of Software',
                 'uploader_id': 'theblnbusinessofsoftware',
                 'duration': 3610,
                 'uploader': 'The BLN & Business of Software',
                 'uploader_id': 'theblnbusinessofsoftware',
                 'duration': 3610,

+                'description': None,

             },
         },
         {
             },
         },
         {


@@ -116,11 +122,28 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
                 'uploader_id': 'user18948128',
                 'uploader': 'Jaime Marquínez Ferrándiz',
                 'duration': 10,
                 'uploader_id': 'user18948128',
                 'uploader': 'Jaime Marquínez Ferrándiz',
                 'duration': 10,

+                'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people who love them.',

             },
             'params': {
                 'videopassword': 'youtube-dl',
             },
         },
             },
             'params': {
                 'videopassword': 'youtube-dl',
             },
         },

+        {
+            'url': 'http://vimeo.com/channels/keypeele/75629013',
+            'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
+            'note': 'Video is freely available via original URL '
+                    'and protected with password when accessed via http://vimeo.com/75629013',
+            'info_dict': {
+                'id': '75629013',
+                'ext': 'mp4',
+                'title': 'Key & Peele: Terrorist Interrogation',
+                'description': 'md5:8678b246399b070816b12313e8b4eb5c',
+                'uploader_id': 'atencio',
+                'uploader': 'Peter Atencio',
+                'upload_date': '20130927',
+                'duration': 187,
+            },
+        },

         {
             'url': 'http://vimeo.com/76979871',
             'md5': '3363dd6ffebe3784d56f4132317fd446',
         {
             'url': 'http://vimeo.com/76979871',
             'md5': '3363dd6ffebe3784d56f4132317fd446',


@@ -136,37 +159,38 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
                 'duration': 62,
             }
         },
                 'duration': 62,
             }
         },

+        {
+            # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
+            'url': 'https://player.vimeo.com/video/98044508',
+            'note': 'The js code contains assignments to the same variable as the config',
+            'info_dict': {
+                'id': '98044508',
+                'ext': 'mp4',
+                'title': 'Pier Solar OUYA Official Trailer',
+                'uploader': 'Tulio Gonçalves',
+                'uploader_id': 'user28849593',
+            },
+        },

     ]
 
     ]
 

-    @classmethod
-    def suitable(cls, url):
-        if VimeoChannelIE.suitable(url):
-            # Otherwise channel urls like http://vimeo.com/channels/31259 would
-            # match
-            return False
-        else:
-            return super(VimeoIE, cls).suitable(url)
-

     def _verify_video_password(self, url, video_id, webpage):
         password = self._downloader.params.get('videopassword', None)
         if password is None:
     def _verify_video_password(self, url, video_id, webpage):
         password = self._downloader.params.get('videopassword', None)
         if password is None:

-            raise ExtractorError('This video is protected by a password, use the --video-password option')
-        token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
-        data = compat_urllib_parse.urlencode({
+            raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
+        token = self._search_regex(r'xsrft[\s=:"\']+([^"\']+)', webpage, 'login token')
+        data = urlencode_postdata({

             'password': password,
             'token': token,
         })
             'password': password,
             'token': token,
         })

-        # I didn't manage to use the password with https
-        if url.startswith('https'):
-            pass_url = url.replace('https', 'http')
-        else:
-            pass_url = url
-        password_request = compat_urllib_request.Request(pass_url + '/password', data)
+        if url.startswith('http://'):
+            # vimeo only supports https now, but the user can give an http url
+            url = url.replace('http://', 'https://')
+        password_request = compat_urllib_request.Request(url + '/password', data)

         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         password_request.add_header('Cookie', 'xsrft=%s' % token)
         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         password_request.add_header('Cookie', 'xsrft=%s' % token)

-        self._download_webpage(password_request, video_id,
-                               'Verifying the password',
-                               'Wrong password')
+        return self._download_webpage(
+            password_request, video_id,
+            'Verifying the password', 'Wrong password')

 
     def _verify_player_video_password(self, url, video_id):
         password = self._downloader.params.get('videopassword', None)
 
     def _verify_player_video_password(self, url, video_id):
         password = self._downloader.params.get('videopassword', None)


@@ -190,12 +214,15 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
         if data is not None:
             headers = headers.copy()
             headers.update(data)
         if data is not None:
             headers = headers.copy()
             headers.update(data)

+        if 'Referer' not in headers:
+            headers['Referer'] = url

 
         # Extract ID from URL
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
         # Extract ID from URL
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')

+        orig_url = url

         if mobj.group('pro') or mobj.group('player'):
         if mobj.group('pro') or mobj.group('player'):

-            url = 'http://player.vimeo.com/video/' + video_id
+            url = 'https://player.vimeo.com/video/' + video_id

         else:
             url = 'https://vimeo.com/' + video_id
 
         else:
             url = 'https://vimeo.com/' + video_id
 


@@ -219,6 +246,16 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
         # and latter we extract those that are Vimeo specific.
         self.report_extraction(video_id)
 
         # and latter we extract those that are Vimeo specific.
         self.report_extraction(video_id)
 

+        vimeo_config = self._search_regex(
+            r'vimeo\.config\s*=\s*({.+?});', webpage,
+            'vimeo config', default=None)
+        if vimeo_config:
+            seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
+            if seed_status.get('state') == 'failed':
+                raise ExtractorError(
+                    '%s returned error: %s' % (self.IE_NAME, seed_status['title']),
+                    expected=True)
+

         # Extract the config JSON
         try:
             try:
         # Extract the config JSON
         try:
             try:


@@ -231,19 +268,22 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
                 # 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:
                 # 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))
+                    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, 'info section',
                 else:
                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
                 config = self._search_regex(config_re, webpage, 'info section',

-                    flags=re.DOTALL)
+                                            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):
                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 
                 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):
                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 

-            if re.search('<form[^>]+?id="pw_form"', webpage) is not None:
+            if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
+                if data and '_video_password_verified' in data:
+                    raise ExtractorError('video password verification failed!')

                 self._verify_video_password(url, video_id, webpage)
                 self._verify_video_password(url, video_id, webpage)

-                return self._real_extract(url)
+                return self._real_extract(
+                    smuggle_url(url, {'_video_password_verified': 'verified'}))

             else:
                 raise ExtractorError('Unable to extract info section',
                                      cause=e)
             else:
                 raise ExtractorError('Unable to extract info section',
                                      cause=e)


@@ -263,30 +303,35 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
         if video_thumbnail is None:
             video_thumbs = config["video"].get("thumbs")
             if video_thumbs and isinstance(video_thumbs, dict):
         if video_thumbnail is None:
             video_thumbs = config["video"].get("thumbs")
             if video_thumbs and isinstance(video_thumbs, dict):

-                _, video_thumbnail = sorted((int(width), t_url) for (width, t_url) in video_thumbs.items())[-1]
+                _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]

 
         # Extract video description
 
         # Extract video description

-        video_description = None
-        try:
-            video_description = get_element_by_attribute("class", "description_wrapper", webpage)
-            if video_description:
-                video_description = clean_html(video_description)
-        except AssertionError as err:
-            # On some pages like (http://player.vimeo.com/video/54469442) the
-            # html tags are not closed, python 2.6 cannot handle it
-            if err.args[0] == 'we should not get here!':
-                pass
-            else:
-                raise
+
+        video_description = self._html_search_regex(
+            r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
+            webpage, 'description', default=None)
+        if not video_description:
+            video_description = self._html_search_meta(
+                'description', webpage, default=None)
+        if not video_description and mobj.group('pro'):
+            orig_webpage = self._download_webpage(
+                orig_url, video_id,
+                note='Downloading webpage for description',
+                fatal=False)
+            if orig_webpage:
+                video_description = self._html_search_meta(
+                    'description', orig_webpage, default=None)
+        if not video_description and not mobj.group('player'):
+            self._downloader.report_warning('Cannot find video description')

 
         # Extract video duration
         video_duration = int_or_none(config["video"].get("duration"))
 
         # Extract upload date
         video_upload_date = None
 
         # Extract video duration
         video_duration = int_or_none(config["video"].get("duration"))
 
         # Extract upload date
         video_upload_date = None

-        mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage)
+        mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)

         if mobj is not None:
         if mobj is not None:

-            video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
+            video_upload_date = unified_strdate(mobj.group(1))

 
         try:
             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 
         try:
             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))


@@ -338,12 +383,10 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
         text_tracks = config['request'].get('text_tracks')
         if text_tracks:
             for tt in text_tracks:
         text_tracks = config['request'].get('text_tracks')
         if text_tracks:
             for tt in text_tracks:

-                subtitles[tt['lang']] = 'http://vimeo.com' + tt['url']
-
-        video_subtitles = self.extract_subtitles(video_id, subtitles)
-        if self._downloader.params.get('listsubtitles', False):
-            self._list_available_subtitles(video_id, subtitles)
-            return
+                subtitles[tt['lang']] = [{
+                    'ext': 'vtt',
+                    'url': 'https://vimeo.com' + tt['url'],
+                }]

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,


@@ -359,15 +402,23 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
             'view_count': view_count,
             'like_count': like_count,
             'comment_count': comment_count,
             'view_count': view_count,
             'like_count': like_count,
             'comment_count': comment_count,

-            'subtitles': video_subtitles,
+            'subtitles': subtitles,

         }
 
 
 class VimeoChannelIE(InfoExtractor):
     IE_NAME = 'vimeo:channel'
         }
 
 
 class VimeoChannelIE(InfoExtractor):
     IE_NAME = 'vimeo:channel'

-    _VALID_URL = r'(?:https?://)?vimeo\.com/channels/(?P<id>[^/]+)/?(\?.*)?$'
+    _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'

     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'

+    _TESTS = [{
+        'url': 'https://vimeo.com/channels/tributes',
+        'info_dict': {
+            'id': 'tributes',
+            'title': 'Vimeo Tributes',
+        },
+        'playlist_mincount': 25,
+    }]

 
     def _page_url(self, base_url, pagenum):
         return '%s/videos/page:%d/' % (base_url, pagenum)
 
     def _page_url(self, base_url, pagenum):
         return '%s/videos/page:%d/' % (base_url, pagenum)


@@ -375,17 +426,52 @@ class VimeoChannelIE(InfoExtractor):
     def _extract_list_title(self, webpage):
         return self._html_search_regex(self._TITLE_RE, webpage, 'list title')
 
     def _extract_list_title(self, webpage):
         return self._html_search_regex(self._TITLE_RE, webpage, 'list title')
 

+    def _login_list_password(self, page_url, list_id, webpage):
+        login_form = self._search_regex(
+            r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
+            webpage, 'login form', default=None)
+        if not login_form:
+            return webpage
+
+        password = self._downloader.params.get('videopassword', None)
+        if password is None:
+            raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
+        fields = dict(re.findall(r'''(?x)<input\s+
+            type="hidden"\s+
+            name="([^"]+)"\s+
+            value="([^"]*)"
+            ''', login_form))
+        token = self._search_regex(r'xsrft[\s=:"\']+([^"\']+)', webpage, 'login token')
+        fields['token'] = token
+        fields['password'] = password
+        post = urlencode_postdata(fields)
+        password_path = self._search_regex(
+            r'action="([^"]+)"', login_form, 'password URL')
+        password_url = compat_urlparse.urljoin(page_url, password_path)
+        password_request = compat_urllib_request.Request(password_url, post)
+        password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
+        self._set_cookie('vimeo.com', 'xsrft', token)
+
+        return self._download_webpage(
+            password_request, list_id,
+            'Verifying the password', 'Wrong password')
+

     def _extract_videos(self, list_id, base_url):
         video_ids = []
         for pagenum in itertools.count(1):
     def _extract_videos(self, list_id, base_url):
         video_ids = []
         for pagenum in itertools.count(1):

+            page_url = self._page_url(base_url, pagenum)

             webpage = self._download_webpage(
             webpage = self._download_webpage(

-                self._page_url(base_url, pagenum), list_id,
+                page_url, list_id,

                 'Downloading page %s' % pagenum)
                 'Downloading page %s' % pagenum)

+
+            if pagenum == 1:
+                webpage = self._login_list_password(page_url, list_id, webpage)
+

             video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
                 break
 
             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')
+        entries = [self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')

                    for video_id in video_ids]
         return {'_type': 'playlist',
                 'id': list_id,
                    for video_id in video_ids]
         return {'_type': 'playlist',
                 'id': list_id,


@@ -396,43 +482,71 @@ class VimeoChannelIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         channel_id = mobj.group('id')
     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)
+        return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)

 
 
 class VimeoUserIE(VimeoChannelIE):
     IE_NAME = 'vimeo:user'
 
 
 class VimeoUserIE(VimeoChannelIE):
     IE_NAME = 'vimeo:user'

-    _VALID_URL = r'(?:https?://)?vimeo\.com/(?P<name>[^/]+)(?:/videos|[#?]|$)'
+    _VALID_URL = r'https://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'

     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'

-
-    @classmethod
-    def suitable(cls, 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)
+    _TESTS = [{
+        'url': 'https://vimeo.com/nkistudio/videos',
+        'info_dict': {
+            'title': 'Nki',
+            'id': 'nkistudio',
+        },
+        'playlist_mincount': 66,
+    }]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
 
     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)
+        return self._extract_videos(name, 'https://vimeo.com/%s' % name)

 
 
 class VimeoAlbumIE(VimeoChannelIE):
     IE_NAME = 'vimeo:album'
 
 
 class VimeoAlbumIE(VimeoChannelIE):
     IE_NAME = 'vimeo:album'

-    _VALID_URL = r'(?:https?://)?vimeo\.com/album/(?P<id>\d+)'
+    _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'

     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'

+    _TESTS = [{
+        'url': 'https://vimeo.com/album/2632481',
+        'info_dict': {
+            'id': '2632481',
+            'title': 'Staff Favorites: November 2013',
+        },
+        'playlist_mincount': 13,
+    }, {
+        'note': 'Password-protected album',
+        'url': 'https://vimeo.com/album/3253534',
+        'info_dict': {
+            'title': 'test',
+            'id': '3253534',
+        },
+        'playlist_count': 1,
+        'params': {
+            'videopassword': 'youtube-dl',
+        }
+    }]

 
     def _page_url(self, base_url, pagenum):
         return '%s/page:%d/' % (base_url, pagenum)
 
     def _real_extract(self, url):
 
     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)
+        album_id = self._match_id(url)
+        return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)

 
 
 class VimeoGroupsIE(VimeoAlbumIE):
     IE_NAME = 'vimeo:group'
 
 
 class VimeoGroupsIE(VimeoAlbumIE):
     IE_NAME = 'vimeo:group'

-    _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)'
+    _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)'
+    _TESTS = [{
+        'url': 'https://vimeo.com/groups/rolexawards',
+        'info_dict': {
+            'id': 'rolexawards',
+            'title': 'Rolex Awards for Enterprise',
+        },
+        'playlist_mincount': 73,
+    }]

 
     def _extract_list_title(self, webpage):
         return self._og_search_title(webpage)
 
     def _extract_list_title(self, webpage):
         return self._og_search_title(webpage)


@@ -440,22 +554,35 @@ class VimeoGroupsIE(VimeoAlbumIE):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
     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)
+        return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)

 
 
 class VimeoReviewIE(InfoExtractor):
     IE_NAME = 'vimeo:review'
     IE_DESC = 'Review pages on vimeo'
 
 
 class VimeoReviewIE(InfoExtractor):
     IE_NAME = 'vimeo:review'
     IE_DESC = 'Review pages on vimeo'

-    _VALID_URL = r'(?:https?://)?vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
-    _TEST = {
+    _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
+    _TESTS = [{

         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',

-        'file': '75524534.mp4',

         'md5': 'c507a72f780cacc12b2248bb4006d253',
         'info_dict': {
         'md5': 'c507a72f780cacc12b2248bb4006d253',
         'info_dict': {

+            'id': '75524534',
+            'ext': 'mp4',

             'title': "DICK HARDWICK 'Comedian'",
             'uploader': 'Richard Hardwick',
         }
             'title': "DICK HARDWICK 'Comedian'",
             'uploader': 'Richard Hardwick',
         }

-    }
+    }, {
+        'note': 'video player needs Referer',
+        'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
+        'md5': '6295fdab8f4bf6a002d058b2c6dce276',
+        'info_dict': {
+            'id': '91613211',
+            'ext': 'mp4',
+            'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
+            'uploader': 'DevWeek Events',
+            'duration': 2773,
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)


@@ -467,9 +594,13 @@ class VimeoReviewIE(InfoExtractor):
 class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE):
     IE_NAME = 'vimeo:watchlater'
     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
 class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE):
     IE_NAME = 'vimeo:watchlater'
     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'

-    _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater'
+    _VALID_URL = r'https://vimeo\.com/home/watchlater|:vimeowatchlater'

     _LOGIN_REQUIRED = True
     _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<'
     _LOGIN_REQUIRED = True
     _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<'

+    _TESTS = [{
+        'url': 'https://vimeo.com/home/watchlater',
+        'only_matching': True,
+    }]

 
     def _real_initialize(self):
         self._login()
 
     def _real_initialize(self):
         self._login()


@@ -484,3 +615,59 @@ class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE):
 
     def _real_extract(self, url):
         return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater')
 
     def _real_extract(self, url):
         return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater')

+
+
+class VimeoLikesIE(InfoExtractor):
+    _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
+    IE_NAME = 'vimeo:likes'
+    IE_DESC = 'Vimeo user likes'
+    _TEST = {
+        'url': 'https://vimeo.com/user755559/likes/',
+        'playlist_mincount': 293,
+        "info_dict": {
+            'id': 'user755559_likes',
+            "description": "See all the videos urza likes",
+            "title": 'Videos urza likes',
+        },
+    }
+
+    def _real_extract(self, url):
+        user_id = self._match_id(url)
+        webpage = self._download_webpage(url, user_id)
+        page_count = self._int(
+            self._search_regex(
+                r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
+                    .*?</a></li>\s*<li\s+class="pagination_next">
+                ''', webpage, 'page count'),
+            'page count', fatal=True)
+        PAGE_SIZE = 12
+        title = self._html_search_regex(
+            r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
+        description = self._html_search_meta('description', webpage)
+
+        def _get_page(idx):
+            page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
+                user_id, idx + 1)
+            webpage = self._download_webpage(
+                page_url, user_id,
+                note='Downloading page %d/%d' % (idx + 1, page_count))
+            video_list = self._search_regex(
+                r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
+                webpage, 'video content')
+            paths = re.findall(
+                r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
+            for path in paths:
+                yield {
+                    '_type': 'url',
+                    'url': compat_urlparse.urljoin(page_url, path),
+                }
+
+        pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
+
+        return {
+            '_type': 'playlist',
+            'id': 'user%s_likes' % user_id,
+            'title': title,
+            'description': description,
+            'entries': pl,
+        }