X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fyandexmusic.py;h=ce3723b55032915a216e23f4daa902a42ca314cf;hb=9d186afac818645490122aa7457f247c31c601bf;hp=158f3ea680c786844f3bf4a457ea4bfbc12e4a44;hpb=15707c7e024f1f29e7abd8ddaa362196ef2d4af6;p=youtube-dl.git

diff --git a/youtube_dl/extractor/yandexmusic.py b/youtube_dl/extractor/yandexmusic.py
index 158f3ea68..ce3723b55 100644
--- a/youtube_dl/extractor/yandexmusic.py
+++ b/youtube_dl/extractor/yandexmusic.py
@@ -5,24 +5,36 @@ import re
 import hashlib
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_str,
-    compat_urllib_parse_urlencode,
-)
+from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     int_or_none,
     float_or_none,
     sanitized_Request,
+    urlencode_postdata,
 )
 
 
 class YandexMusicBaseIE(InfoExtractor):
     @staticmethod
     def _handle_error(response):
-        error = response.get('error')
-        if error:
-            raise ExtractorError(error, expected=True)
+        if isinstance(response, dict):
+            error = response.get('error')
+            if error:
+                raise ExtractorError(error, expected=True)
+
+    def _download_webpage(self, *args, **kwargs):
+        webpage = super(YandexMusicBaseIE, self)._download_webpage(*args, **kwargs)
+        if 'Нам очень жаль, но Ð·Ð°Ð¿Ñ€Ð¾ÑÑ‹, поступившие с Ð²Ð°ÑˆÐµÐ³Ð¾ IP-адреса, похожи на Ð°Ð²Ñ‚оматические.' in webpage:
+            raise ExtractorError(
+                'YandexMusic has considered youtube-dl requests automated and '
+                'asks you to solve a CAPTCHA. You can either wait for some '
+                'time until unblocked and optionally use --sleep-interval '
+                'in future or alternatively you can go to https://music.yandex.ru/ '
+                'solve CAPTCHA, then export cookies and pass cookie file to '
+                'youtube-dl with --cookies',
+                expected=True)
+        return webpage
 
     def _download_json(self, *args, **kwargs):
         response = super(YandexMusicBaseIE, self)._download_json(*args, **kwargs)
@@ -41,10 +53,16 @@ class YandexMusicTrackIE(YandexMusicBaseIE):
         'info_dict': {
             'id': '4878838',
             'ext': 'mp3',
-            'title': 'Carlo Ambrosio - Gypsy Eyes 1',
+            'title': 'Carlo Ambrosio & Fabio Di Bari, Carlo Ambrosio - Gypsy Eyes 1',
             'filesize': 4628061,
             'duration': 193.04,
-        }
+            'track': 'Gypsy Eyes 1',
+            'album': 'Gypsy Soul',
+            'album_artist': 'Carlo Ambrosio',
+            'artist': 'Carlo Ambrosio & Fabio Di Bari, Carlo Ambrosio',
+            'release_year': '2009',
+        },
+        'skip': 'Travis CI servers blocked by YandexMusic',
     }
 
     def _get_track_url(self, storage_dir, track_id):
@@ -66,16 +84,45 @@ class YandexMusicTrackIE(YandexMusicBaseIE):
             thumbnail = cover_uri.replace('%%', 'orig')
             if not thumbnail.startswith('http'):
                 thumbnail = 'http://' + thumbnail
-        return {
+
+        track_title = track['title']
+        track_info = {
             'id': track['id'],
             'ext': 'mp3',
             'url': self._get_track_url(track['storageDir'], track['id']),
-            'title': '%s - %s' % (track['artists'][0]['name'], track['title']),
             'filesize': int_or_none(track.get('fileSize')),
             'duration': float_or_none(track.get('durationMs'), 1000),
             'thumbnail': thumbnail,
+            'track': track_title,
         }
 
+        def extract_artist(artist_list):
+            if artist_list and isinstance(artist_list, list):
+                artists_names = [a['name'] for a in artist_list if a.get('name')]
+                if artists_names:
+                    return ', '.join(artists_names)
+
+        albums = track.get('albums')
+        if albums and isinstance(albums, list):
+            album = albums[0]
+            if isinstance(album, dict):
+                year = album.get('year')
+                track_info.update({
+                    'album': album.get('title'),
+                    'album_artist': extract_artist(album.get('artists')),
+                    'release_year': compat_str(year) if year else None,
+                })
+
+        track_artist = extract_artist(track.get('artists'))
+        if track_artist:
+            track_info.update({
+                'artist': track_artist,
+                'title': '%s - %s' % (track_artist, track_title),
+            })
+        else:
+            track_info['title'] = track_title
+        return track_info
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         album_id, track_id = mobj.group('album_id'), mobj.group('id')
@@ -107,6 +154,7 @@ class YandexMusicAlbumIE(YandexMusicPlaylistBaseIE):
             'title': 'Carlo Ambrosio - Gypsy Soul (2009)',
         },
         'playlist_count': 50,
+        'skip': 'Travis CI servers blocked by YandexMusic',
     }
 
     def _real_extract(self, url):
@@ -139,6 +187,7 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
             'description': 'md5:3b9f27b0efbe53f2ee1e844d07155cc9',
         },
         'playlist_count': 6,
+        'skip': 'Travis CI servers blocked by YandexMusic',
     }, {
         # playlist exceeding the limit of 150 tracks shipped with webpage (see
         # https://github.com/rg3/youtube-dl/issues/6666)
@@ -148,6 +197,7 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
             'title': 'Музыка 90-х',
         },
         'playlist_count': 310,
+        'skip': 'Travis CI servers blocked by YandexMusic',
     }]
 
     def _real_extract(self, url):
@@ -170,14 +220,14 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
             missing_track_ids = set(map(compat_str, track_ids)) - set(present_track_ids)
             request = sanitized_Request(
                 'https://music.yandex.ru/handlers/track-entries.jsx',
-                compat_urllib_parse_urlencode({
+                urlencode_postdata({
                     'entries': ','.join(missing_track_ids),
                     'lang': mu.get('settings', {}).get('lang', 'en'),
                     'external-domain': 'music.yandex.ru',
                     'overembed': 'false',
                     'sign': mu.get('authData', {}).get('user', {}).get('sign'),
                     'strict': 'true',
-                }).encode('utf-8'))
+                }))
             request.add_header('Referer', url)
             request.add_header('X-Requested-With', 'XMLHttpRequest')