New upstream version 2020.05.08

[youtubedl] / youtube_dl / extractor / vimeo.py

diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py
index ddf375c6c2189f4eea655196a69c7e2339952527..8cd611e1e42f177e7331ca4c3ea08a350a613e7f 100644 (file)
--- a/youtube_dl/extractor/vimeo.py
+++ b/youtube_dl/extractor/vimeo.py
@@ -15,23 +15,25 @@ from ..compat import (
     compat_urlparse,
 )
 from ..utils import (
     compat_urlparse,
 )
 from ..utils import (

+    clean_html,

     determine_ext,
     determine_ext,

+    dict_get,

     ExtractorError,
     js_to_json,
     int_or_none,
     merge_dicts,
     ExtractorError,
     js_to_json,
     int_or_none,
     merge_dicts,

-    NO_DEFAULT,

     OnDemandPagedList,
     parse_filesize,
     OnDemandPagedList,
     parse_filesize,

-    qualities,

     RegexNotFoundError,
     sanitized_Request,
     smuggle_url,
     std_headers,
     RegexNotFoundError,
     sanitized_Request,
     smuggle_url,
     std_headers,

+    str_or_none,

     try_get,
     unified_timestamp,
     unsmuggle_url,
     urlencode_postdata,
     try_get,
     unified_timestamp,
     unsmuggle_url,
     urlencode_postdata,

+    urljoin,

     unescapeHTML,
 )
 
     unescapeHTML,
 )
 


@@ -190,7 +192,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
             for tt in text_tracks:
                 subtitles[tt['lang']] = [{
                     'ext': 'vtt',
             for tt in text_tracks:
                 subtitles[tt['lang']] = [{
                     'ext': 'vtt',

-                    'url': 'https://vimeo.com' + tt['url'],
+                    'url': urljoin('https://vimeo.com', tt['url']),

                 }]
 
         thumbnails = []
                 }]
 
         thumbnails = []


@@ -211,6 +213,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
         video_uploader_url = owner.get('url')
 
         return {
         video_uploader_url = owner.get('url')
 
         return {

+            'id': str_or_none(video_data.get('id')) or video_id,

             'title': self._live_title(video_title) if is_live else video_title,
             'uploader': owner.get('name'),
             'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
             'title': self._live_title(video_title) if is_live else video_title,
             'uploader': owner.get('name'),
             'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,


@@ -258,11 +261,11 @@ class VimeoIE(VimeoBaseInfoExtractor):
                         (?:
                             (?:
                                 www|
                         (?:
                             (?:
                                 www|

-                                (?P<player>player)
+                                player

                             )
                             \.
                         )?
                             )
                             \.
                         )?

-                        vimeo(?P<pro>pro)?\.com/
+                        vimeo(?:pro)?\.com/

                         (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
                         (?:.*?/)?
                         (?:
                         (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
                         (?:.*?/)?
                         (?:


@@ -284,7 +287,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'id': '56015672',
                 'ext': 'mp4',
                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
                 'id': '56015672',
                 'ext': 'mp4',
                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",

-                'description': 'md5:509a9ad5c9bf97c60faee9203aca4479',
+                'description': 'md5:2d3305bad981a06ff79f027f19865021',

                 'timestamp': 1355990239,
                 'upload_date': '20121220',
                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
                 'timestamp': 1355990239,
                 'upload_date': '20121220',
                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',


@@ -293,6 +296,9 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'duration': 10,
                 'license': 'by-sa',
             },
                 'duration': 10,
                 'license': 'by-sa',
             },

+            'params': {
+                'format': 'best[protocol=https]',
+            },

         },
         {
             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
         },
         {
             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',


@@ -305,8 +311,13 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 '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:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
+                'description': 'md5:2c362968038d4499f4d79f88458590c1',

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

+                'upload_date': '20130610',
+                'timestamp': 1370893156,
+            },
+            'params': {
+                'format': 'best[protocol=https]',

             },
         },
         {
             },
         },
         {


@@ -323,6 +334,10 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'duration': 3610,
                 'description': None,
             },
                 'duration': 3610,
                 'description': None,
             },

+            'params': {
+                'format': 'best[protocol=https]',
+            },
+            'expected_warnings': ['Unable to download JSON metadata'],

         },
         {
             'url': 'http://vimeo.com/68375962',
         },
         {
             'url': 'http://vimeo.com/68375962',


@@ -341,6 +356,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
             },
             'params': {
                 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
             },
             'params': {

+                'format': 'best[protocol=https]',

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


@@ -441,10 +457,14 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'uploader': '10Ft Films',
                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
                 'uploader_id': 'tenfootfilms',
                 'uploader': '10Ft Films',
                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
                 'uploader_id': 'tenfootfilms',

+                'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
+                'upload_date': '20130830',
+                'timestamp': 1377853339,

             },
             'params': {
                 'skip_download': True,
             },
             },
             'params': {
                 'skip_download': True,
             },

+            'expected_warnings': ['Unable to download JSON metadata'],

         },
         {
             'url': 'http://player.vimeo.com/video/68375962',
         },
         {
             'url': 'http://player.vimeo.com/video/68375962',


@@ -459,6 +479,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'duration': 10,
             },
             'params': {
                 'duration': 10,
             },
             'params': {

+                'format': 'best[protocol=https]',

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


@@ -523,7 +544,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
     def _verify_player_video_password(self, url, video_id, headers):
         password = self._downloader.params.get('videopassword')
         if password is None:
     def _verify_player_video_password(self, url, video_id, headers):
         password = self._downloader.params.get('videopassword')
         if password is None:

-            raise ExtractorError('This video is protected by a password, use the --video-password option')
+            raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)

         data = urlencode_postdata({
             'password': base64.b64encode(password.encode()),
         })
         data = urlencode_postdata({
             'password': base64.b64encode(password.encode()),
         })


@@ -552,28 +573,26 @@ class VimeoIE(VimeoBaseInfoExtractor):
             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
 
         # Extract ID from URL
             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
 
         # Extract ID from URL

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)

         orig_url = url
         orig_url = url

-        if mobj.group('pro'):
+        is_pro = 'vimeopro.com/' in url
+        is_player = '://player.vimeo.com/video/' in url
+        if is_pro:

             # some videos require portfolio_id to be present in player url
             # https://github.com/ytdl-org/youtube-dl/issues/20070
             url = self._extract_url(url, self._download_webpage(url, video_id))
             # some videos require portfolio_id to be present in player url
             # https://github.com/ytdl-org/youtube-dl/issues/20070
             url = self._extract_url(url, self._download_webpage(url, video_id))

-        elif mobj.group('player'):
+            if not url:
+                url = 'https://vimeo.com/' + video_id
+        elif is_player:

             url = 'https://player.vimeo.com/video/' + video_id
         elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
             url = 'https://vimeo.com/' + video_id
 
             url = 'https://player.vimeo.com/video/' + video_id
         elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
             url = 'https://vimeo.com/' + video_id
 

-        # Retrieve video webpage to extract further information
-        request = sanitized_Request(url, headers=headers)

         try:
         try:

-            webpage, urlh = self._download_webpage_handle(request, video_id)
-            redirect_url = compat_str(urlh.geturl())
-            # Some URLs redirect to ondemand can't be extracted with
-            # this extractor right away thus should be passed through
-            # ondemand extractor (e.g. https://vimeo.com/73445910)
-            if VimeoOndemandIE.suitable(redirect_url):
-                return self.url_result(redirect_url, VimeoOndemandIE.ie_key())
+            # Retrieve video webpage to extract further information
+            webpage, urlh = self._download_webpage_handle(
+                url, video_id, headers=headers)
+            redirect_url = urlh.geturl()

         except ExtractorError as ee:
             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
                 errmsg = ee.cause.read()
         except ExtractorError as ee:
             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
                 errmsg = ee.cause.read()


@@ -600,6 +619,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
 
         cc_license = None
         timestamp = None
 
         cc_license = None
         timestamp = None

+        video_description = None

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


@@ -611,17 +631,17 @@ class VimeoIE(VimeoBaseInfoExtractor):
                     # Sometimes new react-based page is served instead of old one that require
                     # different config URL extraction approach (see
                     # https://github.com/ytdl-org/youtube-dl/pull/7209)
                     # Sometimes new react-based page is served instead of old one that require
                     # different config URL extraction approach (see
                     # https://github.com/ytdl-org/youtube-dl/pull/7209)

-                    vimeo_clip_page_config = self._search_regex(
-                        r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
-                        'vimeo clip page config')
-                    page_config = self._parse_json(vimeo_clip_page_config, video_id)
+                    page_config = self._parse_json(self._search_regex(
+                        r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
+                        webpage, 'page config'), video_id)

                     config_url = page_config['player']['config_url']
                     cc_license = page_config.get('cc_license')
                     timestamp = try_get(
                         page_config, lambda x: x['clip']['uploaded_on'],
                         compat_str)
                     config_url = page_config['player']['config_url']
                     cc_license = page_config.get('cc_license')
                     timestamp = try_get(
                         page_config, lambda x: x['clip']['uploaded_on'],
                         compat_str)

-                config_json = self._download_webpage(config_url, video_id)
-                config = json.loads(config_json)
+                    video_description = clean_html(dict_get(
+                        page_config, ('description', 'description_html_escaped')))
+                config = self._download_json(config_url, video_id)

             except RegexNotFoundError:
                 # For pro videos or player.vimeo.com urls
                 # We try to find out to which variable is assigned the config dic
             except RegexNotFoundError:
                 # For pro videos or player.vimeo.com urls
                 # We try to find out to which variable is assigned the config dic


@@ -675,14 +695,14 @@ class VimeoIE(VimeoBaseInfoExtractor):
                     {'force_feature_id': True}), 'Vimeo')
 
         # Extract video description
                     {'force_feature_id': True}), 'Vimeo')
 
         # Extract video description

-
-        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_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:
             video_description = self._html_search_meta(
                 'description', webpage, default=None)

-        if not video_description and mobj.group('pro'):
+        if not video_description and is_pro:

             orig_webpage = self._download_webpage(
                 orig_url, video_id,
                 note='Downloading webpage for description',
             orig_webpage = self._download_webpage(
                 orig_url, video_id,
                 note='Downloading webpage for description',


@@ -690,7 +710,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
             if orig_webpage:
                 video_description = self._html_search_meta(
                     'description', orig_webpage, default=None)
             if orig_webpage:
                 video_description = self._html_search_meta(
                     'description', orig_webpage, default=None)

-        if not video_description and not mobj.group('player'):
+        if not video_description and not is_player:

             self._downloader.report_warning('Cannot find video description')
 
         # Extract upload date
             self._downloader.report_warning('Cannot find video description')
 
         # Extract upload date


@@ -730,7 +750,6 @@ class VimeoIE(VimeoBaseInfoExtractor):
         channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
 
         info_dict = {
         channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
 
         info_dict = {

-            'id': video_id,

             'formats': formats,
             'timestamp': unified_timestamp(timestamp),
             'description': video_description,
             'formats': formats,
             'timestamp': unified_timestamp(timestamp),
             'description': video_description,


@@ -748,9 +767,9 @@ class VimeoIE(VimeoBaseInfoExtractor):
         return info_dict
 
 
         return info_dict
 
 

-class VimeoOndemandIE(VimeoBaseInfoExtractor):
+class VimeoOndemandIE(VimeoIE):

     IE_NAME = 'vimeo:ondemand'
     IE_NAME = 'vimeo:ondemand'

-    _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/([^/]+/)?(?P<id>[^/?#&]+)'

     _TESTS = [{
         # ondemand video not available via https://vimeo.com/id
         'url': 'https://vimeo.com/ondemand/20704',
     _TESTS = [{
         # ondemand video not available via https://vimeo.com/id
         'url': 'https://vimeo.com/ondemand/20704',


@@ -762,24 +781,32 @@ class VimeoOndemandIE(VimeoBaseInfoExtractor):
             'uploader': 'גם סרטים',
             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
             'uploader_id': 'gumfilms',
             'uploader': 'גם סרטים',
             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
             'uploader_id': 'gumfilms',

+            'description': 'md5:4c027c965e439de4baab621e48b60791',
+            'upload_date': '20140906',
+            'timestamp': 1410032453,

         },
         'params': {
             'format': 'best[protocol=https]',
         },
         },
         'params': {
             'format': 'best[protocol=https]',
         },

+        'expected_warnings': ['Unable to download JSON metadata'],

     }, {
         # requires Referer to be passed along with og:video:url
         'url': 'https://vimeo.com/ondemand/36938/126682985',
         'info_dict': {
     }, {
         # requires Referer to be passed along with og:video:url
         'url': 'https://vimeo.com/ondemand/36938/126682985',
         'info_dict': {

-            'id': '126682985',
+            'id': '126584684',

             'ext': 'mp4',
             'title': 'Rävlock, rätt läte på rätt plats',
             'uploader': 'Lindroth & Norin',
             'ext': 'mp4',
             'title': 'Rävlock, rätt läte på rätt plats',
             'uploader': 'Lindroth & Norin',

-            'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user14430847',
-            'uploader_id': 'user14430847',
+            'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
+            'uploader_id': 'lindrothnorin',
+            'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
+            'upload_date': '20150502',
+            'timestamp': 1430586422,

         },
         'params': {
             'skip_download': True,
         },
         },
         'params': {
             'skip_download': True,
         },

+        'expected_warnings': ['Unable to download JSON metadata'],

     }, {
         'url': 'https://vimeo.com/ondemand/nazmaalik',
         'only_matching': True,
     }, {
         'url': 'https://vimeo.com/ondemand/nazmaalik',
         'only_matching': True,


@@ -791,16 +818,6 @@ class VimeoOndemandIE(VimeoBaseInfoExtractor):
         'only_matching': True,
     }]
 
         'only_matching': True,
     }]
 

-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        return self.url_result(
-            # Some videos require Referer to be passed along with og:video:url
-            # similarly to generic vimeo embeds (e.g.
-            # https://vimeo.com/ondemand/36938/126682985).
-            VimeoIE._smuggle_referrer(self._og_search_video_url(webpage), url),
-            VimeoIE.ie_key())
-

 
 class VimeoChannelIE(VimeoBaseInfoExtractor):
     IE_NAME = 'vimeo:channel'
 
 class VimeoChannelIE(VimeoBaseInfoExtractor):
     IE_NAME = 'vimeo:channel'


@@ -816,6 +833,7 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
         },
         'playlist_mincount': 25,
     }]
         },
         'playlist_mincount': 25,
     }]

+    _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'

 
     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)


@@ -824,33 +842,6 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
         return self._TITLE or self._html_search_regex(
             self._TITLE_RE, webpage, 'list title', fatal=False)
 
         return self._TITLE or self._html_search_regex(
             self._TITLE_RE, webpage, 'list title', fatal=False)
 

-    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')
-        if password is None:
-            raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
-        fields = self._hidden_inputs(login_form)
-        token, vuid = self._extract_xsrft_and_vuid(webpage)
-        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 = sanitized_Request(password_url, post)
-        password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
-        self._set_vimeo_cookie('vuid', vuid)
-        self._set_vimeo_cookie('xsrft', token)
-
-        return self._download_webpage(
-            password_request, list_id,
-            'Verifying the password', 'Wrong password')
-

     def _title_and_entries(self, list_id, base_url):
         for pagenum in itertools.count(1):
             page_url = self._page_url(base_url, pagenum)
     def _title_and_entries(self, list_id, base_url):
         for pagenum in itertools.count(1):
             page_url = self._page_url(base_url, pagenum)


@@ -859,7 +850,6 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
                 'Downloading page %s' % pagenum)
 
             if pagenum == 1:
                 'Downloading page %s' % pagenum)
 
             if pagenum == 1:

-                webpage = self._login_list_password(page_url, list_id, webpage)

                 yield self._extract_list_title(webpage)
 
             # Try extracting href first since not all videos are available via
                 yield self._extract_list_title(webpage)
 
             # Try extracting href first since not all videos are available via


@@ -887,14 +877,13 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
         return self.playlist_result(title_and_entries, list_id, list_title)
 
     def _real_extract(self, url):
         return self.playlist_result(title_and_entries, list_id, list_title)
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        channel_id = mobj.group('id')
-        return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
+        channel_id = self._match_id(url)
+        return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)

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

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

     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
     _TESTS = [{
         'url': 'https://vimeo.com/nkistudio/videos',
     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
     _TESTS = [{
         'url': 'https://vimeo.com/nkistudio/videos',


@@ -904,14 +893,10 @@ class VimeoUserIE(VimeoChannelIE):
         },
         'playlist_mincount': 66,
     }]
         },
         'playlist_mincount': 66,
     }]

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

 
 
 
 

-class VimeoAlbumIE(VimeoChannelIE):
+class VimeoAlbumIE(VimeoBaseInfoExtractor):

     IE_NAME = 'vimeo:album'
     _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
     IE_NAME = 'vimeo:album'
     _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'


@@ -939,7 +924,7 @@ class VimeoAlbumIE(VimeoChannelIE):
     def _fetch_page(self, album_id, authorizaion, hashed_pass, page):
         api_page = page + 1
         query = {
     def _fetch_page(self, album_id, authorizaion, hashed_pass, page):
         api_page = page + 1
         query = {

-            'fields': 'link',
+            'fields': 'link,uri',

             'page': api_page,
             'per_page': self._PAGE_SIZE,
         }
             'page': api_page,
             'per_page': self._PAGE_SIZE,
         }


@@ -954,39 +939,60 @@ class VimeoAlbumIE(VimeoChannelIE):
             link = video.get('link')
             if not link:
                 continue
             link = video.get('link')
             if not link:
                 continue

-            yield self.url_result(link, VimeoIE.ie_key(), VimeoIE._match_id(link))
+            uri = video.get('uri')
+            video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
+            yield self.url_result(link, VimeoIE.ie_key(), video_id)

 
     def _real_extract(self, url):
         album_id = self._match_id(url)
         webpage = self._download_webpage(url, album_id)
 
     def _real_extract(self, url):
         album_id = self._match_id(url)
         webpage = self._download_webpage(url, album_id)

-        webpage = self._login_list_password(url, album_id, webpage)
-        api_config = self._extract_vimeo_config(webpage, album_id)['api']
+        viewer = self._parse_json(self._search_regex(
+            r'bootstrap_data\s*=\s*({.+?})</script>',
+            webpage, 'bootstrap data'), album_id)['viewer']
+        jwt = viewer['jwt']
+        album = self._download_json(
+            'https://api.vimeo.com/albums/' + album_id,
+            album_id, headers={'Authorization': 'jwt ' + jwt},
+            query={'fields': 'description,name,privacy'})
+        hashed_pass = None
+        if try_get(album, lambda x: x['privacy']['view']) == 'password':
+            password = self._downloader.params.get('videopassword')
+            if not password:
+                raise ExtractorError(
+                    'This album is protected by a password, use the --video-password option',
+                    expected=True)
+            self._set_vimeo_cookie('vuid', viewer['vuid'])
+            try:
+                hashed_pass = self._download_json(
+                    'https://vimeo.com/showcase/%s/auth' % album_id,
+                    album_id, 'Verifying the password', data=urlencode_postdata({
+                        'password': password,
+                        'token': viewer['xsrft'],
+                    }), headers={
+                        'X-Requested-With': 'XMLHttpRequest',
+                    })['hashed_pass']
+            except ExtractorError as e:
+                if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                    raise ExtractorError('Wrong password', expected=True)
+                raise

         entries = OnDemandPagedList(functools.partial(
         entries = OnDemandPagedList(functools.partial(

-            self._fetch_page, album_id, api_config['jwt'],
-            api_config.get('hashed_pass')), self._PAGE_SIZE)
-        return self.playlist_result(entries, album_id, self._html_search_regex(
-            r'<title>\s*(.+?)(?:\s+on Vimeo)?</title>', webpage, 'title', fatal=False))
+            self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
+        return self.playlist_result(
+            entries, album_id, album.get('name'), album.get('description'))

 
 
 
 

-class VimeoGroupsIE(VimeoAlbumIE):
+class VimeoGroupsIE(VimeoChannelIE):

     IE_NAME = 'vimeo:group'
     IE_NAME = 'vimeo:group'

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

     _TESTS = [{
     _TESTS = [{

-        'url': 'https://vimeo.com/groups/rolexawards',
+        'url': 'https://vimeo.com/groups/kattykay',

         'info_dict': {
         'info_dict': {

-            'id': 'rolexawards',
-            'title': 'Rolex Awards for Enterprise',
+            'id': 'kattykay',
+            'title': 'Katty Kay',

         },
         },

-        'playlist_mincount': 73,
+        'playlist_mincount': 27,

     }]
     }]

-
-    def _extract_list_title(self, webpage):
-        return self._og_search_title(webpage, fatal=False)
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        name = mobj.group('name')
-        return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
+    _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'

 
 
 class VimeoReviewIE(VimeoBaseInfoExtractor):
 
 
 class VimeoReviewIE(VimeoBaseInfoExtractor):


@@ -1002,7 +1008,9 @@ class VimeoReviewIE(VimeoBaseInfoExtractor):
             'title': "DICK HARDWICK 'Comedian'",
             'uploader': 'Richard Hardwick',
             'uploader_id': 'user21297594',
             'title': "DICK HARDWICK 'Comedian'",
             'uploader': 'Richard Hardwick',
             'uploader_id': 'user21297594',

-        }
+            'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
+        },
+        'expected_warnings': ['Unable to download JSON metadata'],

     }, {
         'note': 'video player needs Referer',
         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
     }, {
         'note': 'video player needs Referer',
         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',


@@ -1015,7 +1023,8 @@ class VimeoReviewIE(VimeoBaseInfoExtractor):
             'duration': 2773,
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader_id': 'user22258446',
             'duration': 2773,
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader_id': 'user22258446',

-        }
+        },
+        'skip': 'video gone',

     }, {
         'note': 'Password protected',
         'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
     }, {
         'note': 'Password protected',
         'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',


@@ -1035,33 +1044,20 @@ class VimeoReviewIE(VimeoBaseInfoExtractor):
     def _real_initialize(self):
         self._login()
 
     def _real_initialize(self):
         self._login()
 

-    def _get_config_url(self, webpage_url, video_id, video_password_verified=False):
-        webpage = self._download_webpage(webpage_url, video_id)
-        config_url = self._html_search_regex(
-            r'data-config-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
-            'config URL', default=None, group='url')
-        if not config_url:
-            data = self._parse_json(self._search_regex(
-                r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data',
-                default=NO_DEFAULT if video_password_verified else '{}'), video_id)
-            config = data.get('vimeo_esi', {}).get('config', {})
-            config_url = config.get('configUrl') or try_get(config, lambda x: x['clipData']['configUrl'])
-        if config_url is None:
-            self._verify_video_password(webpage_url, video_id, webpage)
-            config_url = self._get_config_url(
-                webpage_url, video_id, video_password_verified=True)
-        return config_url
-

     def _real_extract(self, url):
         page_url, video_id = re.match(self._VALID_URL, url).groups()
     def _real_extract(self, url):
         page_url, video_id = re.match(self._VALID_URL, url).groups()

-        config_url = self._get_config_url(url, video_id)
+        clip_data = self._download_json(
+            page_url.replace('/review/', '/review/data/'),
+            video_id)['clipData']
+        config_url = clip_data['configUrl']

         config = self._download_json(config_url, video_id)
         info_dict = self._parse_config(config, video_id)
         config = self._download_json(config_url, video_id)
         info_dict = self._parse_config(config, video_id)

-        source_format = self._extract_original_format(page_url, video_id)
+        source_format = self._extract_original_format(
+            page_url + '/action', video_id)

         if source_format:
             info_dict['formats'].append(source_format)
         self._vimeo_sort_formats(info_dict['formats'])
         if source_format:
             info_dict['formats'].append(source_format)
         self._vimeo_sort_formats(info_dict['formats'])

-        info_dict['id'] = video_id
+        info_dict['description'] = clean_html(clip_data.get('description'))

         return info_dict
 
 
         return info_dict
 
 


@@ -1115,94 +1111,17 @@ class VimeoLikesIE(VimeoChannelIE):
         return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
 
 
         return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
 
 

-class VHXEmbedIE(InfoExtractor):
+class VHXEmbedIE(VimeoBaseInfoExtractor):

     IE_NAME = 'vhx:embed'
     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
 
     IE_NAME = 'vhx:embed'
     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
 

-    def _call_api(self, video_id, access_token, path='', query=None):
-        return self._download_json(
-            'https://api.vhx.tv/videos/' + video_id + path, video_id, headers={
-                'Authorization': 'Bearer ' + access_token,
-            }, query=query)
-

     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)

-        credentials = self._parse_json(self._search_regex(
-            r'(?s)credentials\s*:\s*({.+?}),', webpage,
-            'config'), video_id, js_to_json)
-        access_token = credentials['access_token']
-
-        query = {}
-        for k, v in credentials.items():
-            if k in ('authorization', 'authUserToken', 'ticket') and v and v != 'undefined':
-                if k == 'authUserToken':
-                    query['auth_user_token'] = v
-                else:
-                    query[k] = v
-        files = self._call_api(video_id, access_token, '/files', query)
-
-        formats = []
-        for f in files:
-            href = try_get(f, lambda x: x['_links']['source']['href'])
-            if not href:
-                continue
-            method = f.get('method')
-            if method == 'hls':
-                formats.extend(self._extract_m3u8_formats(
-                    href, video_id, 'mp4', 'm3u8_native',
-                    m3u8_id='hls', fatal=False))
-            elif method == 'dash':
-                formats.extend(self._extract_mpd_formats(
-                    href, video_id, mpd_id='dash', fatal=False))
-            else:
-                fmt = {
-                    'filesize': int_or_none(try_get(f, lambda x: x['size']['bytes'])),
-                    'format_id': 'http',
-                    'preference': 1,
-                    'url': href,
-                    'vcodec': f.get('codec'),
-                }
-                quality = f.get('quality')
-                if quality:
-                    fmt.update({
-                        'format_id': 'http-' + quality,
-                        'height': int_or_none(self._search_regex(r'(\d+)p', quality, 'height', default=None)),
-                    })
-                formats.append(fmt)
-        self._sort_formats(formats)
-
-        video_data = self._call_api(video_id, access_token)
-        title = video_data.get('title') or video_data['name']
-
-        subtitles = {}
-        for subtitle in try_get(video_data, lambda x: x['tracks']['subtitles'], list) or []:
-            lang = subtitle.get('srclang') or subtitle.get('label')
-            for _link in subtitle.get('_links', {}).values():
-                href = _link.get('href')
-                if not href:
-                    continue
-                subtitles.setdefault(lang, []).append({
-                    'url': href,
-                })
-
-        q = qualities(['small', 'medium', 'large', 'source'])
-        thumbnails = []
-        for thumbnail_id, thumbnail_url in video_data.get('thumbnail', {}).items():
-            thumbnails.append({
-                'id': thumbnail_id,
-                'url': thumbnail_url,
-                'preference': q(thumbnail_id),
-            })
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': video_data.get('description'),
-            'duration': int_or_none(try_get(video_data, lambda x: x['duration']['seconds'])),
-            'formats': formats,
-            'subtitles': subtitles,
-            'thumbnails': thumbnails,
-            'timestamp': unified_timestamp(video_data.get('created_at')),
-            'view_count': int_or_none(video_data.get('plays_count')),
-        }
+        config_url = self._parse_json(self._search_regex(
+            r'window\.OTTData\s*=\s*({.+})', webpage,
+            'ott data'), video_id, js_to_json)['config_url']
+        config = self._download_json(config_url, video_id)
+        info = self._parse_config(config, video_id)
+        self._vimeo_sort_formats(info['formats'])
+        return info