New upstream version 2020.03.24

[youtubedl] / youtube_dl / extractor / vevo.py

diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py
index c4e37f694426c175b1f33d7795ca01baf6f7547b..4ea9f1b4bc02d5fc19777124b1f7d5b6cc44abba 100644 (file)
--- a/youtube_dl/extractor/vevo.py
+++ b/youtube_dl/extractor/vevo.py
@@ -1,6 +1,7 @@
 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re

+import json

 
 from .common import InfoExtractor
 from ..compat import (
 
 from .common import InfoExtractor
 from ..compat import (


@@ -11,18 +12,17 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     int_or_none,
 from ..utils import (
     ExtractorError,
     int_or_none,

-    sanitized_Request,

     parse_iso8601,
 )
 
 
 class VevoBaseIE(InfoExtractor):
     parse_iso8601,
 )
 
 
 class VevoBaseIE(InfoExtractor):

-    def _extract_json(self, webpage, video_id, item):
+    def _extract_json(self, webpage, video_id):

         return self._parse_json(
             self._search_regex(
                 r'window\.__INITIAL_STORE__\s*=\s*({.+?});\s*</script>',
                 webpage, 'initial store'),
         return self._parse_json(
             self._search_regex(
                 r'window\.__INITIAL_STORE__\s*=\s*({.+?});\s*</script>',
                 webpage, 'initial store'),

-            video_id)['default'][item]
+            video_id)

 
 
 class VevoIE(VevoBaseIE):
 
 
 class VevoIE(VevoBaseIE):


@@ -34,6 +34,7 @@ class VevoIE(VevoBaseIE):
         (?:https?://(?:www\.)?vevo\.com/watch/(?!playlist|genre)(?:[^/]+/(?:[^/]+/)?)?|
            https?://cache\.vevo\.com/m/html/embed\.html\?video=|
            https?://videoplayer\.vevo\.com/embed/embedded\?videoId=|
         (?:https?://(?:www\.)?vevo\.com/watch/(?!playlist|genre)(?:[^/]+/(?:[^/]+/)?)?|
            https?://cache\.vevo\.com/m/html/embed\.html\?video=|
            https?://videoplayer\.vevo\.com/embed/embedded\?videoId=|

+           https?://embed\.vevo\.com/.*?[?&]isrc=|

            vevo:)
         (?P<id>[^&?#]+)'''
 
            vevo:)
         (?P<id>[^&?#]+)'''
 


@@ -139,6 +140,14 @@ class VevoIE(VevoBaseIE):
         # no genres available
         'url': 'http://www.vevo.com/watch/INS171400764',
         'only_matching': True,
         # no genres available
         'url': 'http://www.vevo.com/watch/INS171400764',
         'only_matching': True,

+    }, {
+        # Another case available only via the webpage; using streams/streamsV3 formats
+        # Geo-restricted to Netherlands/Germany
+        'url': 'http://www.vevo.com/watch/boostee/pop-corn-clip-officiel/FR1A91600909',
+        'only_matching': True,
+    }, {
+        'url': 'https://embed.vevo.com/?isrc=USH5V1923499&partnerId=4d61b777-8023-4191-9ede-497ed6c24647&partnerAdCode=',
+        'only_matching': True,

     }]
     _VERSIONS = {
         0: 'youtube',  # only in AuthenticateVideo videoVersions
     }]
     _VERSIONS = {
         0: 'youtube',  # only in AuthenticateVideo videoVersions


@@ -149,19 +158,24 @@ class VevoIE(VevoBaseIE):
     }
 
     def _initialize_api(self, video_id):
     }
 
     def _initialize_api(self, video_id):

-        req = sanitized_Request(
-            'http://www.vevo.com/auth', data=b'')

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

-            req, None,
+            'https://accounts.vevo.com/token', None,

             note='Retrieving oauth token',
             note='Retrieving oauth token',

-            errnote='Unable to retrieve oauth token')
+            errnote='Unable to retrieve oauth token',
+            data=json.dumps({
+                'client_id': 'SPupX1tvqFEopQ1YS6SS',
+                'grant_type': 'urn:vevo:params:oauth:grant-type:anonymous',
+            }).encode('utf-8'),
+            headers={
+                'Content-Type': 'application/json',
+            })

 
         if re.search(r'(?i)THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION', webpage):
             self.raise_geo_restricted(
                 '%s said: This page is currently unavailable in your region' % self.IE_NAME)
 
         auth_info = self._parse_json(webpage, video_id)
 
         if re.search(r'(?i)THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION', webpage):
             self.raise_geo_restricted(
                 '%s said: This page is currently unavailable in your region' % self.IE_NAME)
 
         auth_info = self._parse_json(webpage, video_id)

-        self._api_url_template = self.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info['access_token']
+        self._api_url_template = self.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info['legacy_token']

 
     def _call_api(self, path, *args, **kwargs):
         try:
 
     def _call_api(self, path, *args, **kwargs):
         try:


@@ -190,10 +204,17 @@ class VevoIE(VevoBaseIE):
             fatal=False)
 
         # Some videos are only available via webpage (e.g.
             fatal=False)
 
         # Some videos are only available via webpage (e.g.

-        # https://github.com/rg3/youtube-dl/issues/9366)
+        # https://github.com/ytdl-org/youtube-dl/issues/9366)

         if not video_versions:
             webpage = self._download_webpage(url, video_id)
         if not video_versions:
             webpage = self._download_webpage(url, video_id)

-            video_versions = self._extract_json(webpage, video_id, 'streams')[video_id][0]
+            json_data = self._extract_json(webpage, video_id)
+            if 'streams' in json_data.get('default', {}):
+                video_versions = json_data['default']['streams'][video_id][0]
+            else:
+                video_versions = [
+                    value
+                    for key, value in json_data['apollo']['data'].items()
+                    if key.startswith('%s.streams' % video_id)]

 
         uploader = None
         artist = None
 
         uploader = None
         artist = None


@@ -207,7 +228,7 @@ class VevoIE(VevoBaseIE):
 
         formats = []
         for video_version in video_versions:
 
         formats = []
         for video_version in video_versions:

-            version = self._VERSIONS.get(video_version['version'])
+            version = self._VERSIONS.get(video_version.get('version'), 'generic')

             version_url = video_version.get('url')
             if not version_url:
                 continue
             version_url = video_version.get('url')
             if not version_url:
                 continue


@@ -258,8 +279,8 @@ class VevoIE(VevoBaseIE):
 
         genres = video_info.get('genres')
         genre = (
 
         genres = video_info.get('genres')
         genre = (

-            genres[0] if genres and isinstance(genres, list) and
-            isinstance(genres[0], compat_str) else None)
+            genres[0] if genres and isinstance(genres, list)
+            and isinstance(genres[0], compat_str) else None)

 
         is_explicit = video_info.get('isExplicit')
         if is_explicit is True:
 
         is_explicit = video_info.get('isExplicit')
         if is_explicit is True:


@@ -339,7 +360,7 @@ class VevoPlaylistIE(VevoBaseIE):
             if video_id:
                 return self.url_result('vevo:%s' % video_id, VevoIE.ie_key())
 
             if video_id:
                 return self.url_result('vevo:%s' % video_id, VevoIE.ie_key())
 

-        playlists = self._extract_json(webpage, playlist_id, '%ss' % playlist_kind)
+        playlists = self._extract_json(webpage, playlist_id)['default']['%ss' % playlist_kind]

 
         playlist = (list(playlists.values())[0]
                     if playlist_kind == 'playlist' else playlists[playlist_id])
 
         playlist = (list(playlists.values())[0]
                     if playlist_kind == 'playlist' else playlists[playlist_id])