X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fyandexmusic.py;h=fd6268ba4119d02988172a4771514cc34603db1a;hb=103f8c8d36170d5cb489420db0e8fe383b1f93dc;hp=22050add3e87ce1660ca07c3f2ed8807d7d9c71c;hpb=e960c3c223acadb2fac81fb68595d902cf21e349;p=youtube-dl.git diff --git a/youtube_dl/extractor/yandexmusic.py b/youtube_dl/extractor/yandexmusic.py index 22050add3..fd6268ba4 100644 --- a/youtube_dl/extractor/yandexmusic.py +++ b/youtube_dl/extractor/yandexmusic.py @@ -10,8 +10,6 @@ from ..utils import ( ExtractorError, int_or_none, float_or_none, - sanitized_Request, - urlencode_postdata, ) @@ -22,18 +20,24 @@ class YandexMusicBaseIE(InfoExtractor): error = response.get('error') if error: raise ExtractorError(error, expected=True) + if response.get('type') == 'captcha' or 'captcha' in response: + YandexMusicBaseIE._raise_captcha() + + @staticmethod + def _raise_captcha(): + 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) 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) + self._raise_captcha() return webpage def _download_json(self, *args, **kwargs): @@ -71,6 +75,12 @@ class YandexMusicTrackIE(YandexMusicBaseIE): % storage_dir, track_id, 'Downloading track location JSON') + # Each string is now wrapped in a list, this is probably only temporarily thus + # supporting both scenarios (see https://github.com/rg3/youtube-dl/issues/10193) + for k, v in data.items(): + if v and isinstance(v, list): + data[k] = v[0] + key = hashlib.md5(('XGRlBW9FXlekgbPrRHuSiA' + data['path'][1:] + data['s']).encode('utf-8')).hexdigest() storage = storage_dir.split('.') @@ -196,7 +206,7 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE): 'id': '1036', 'title': 'Музыка 90-х', }, - 'playlist_count': 310, + 'playlist_mincount': 300, 'skip': 'Travis CI servers blocked by YandexMusic', }] @@ -224,31 +234,36 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE): 'overembed': 'false', })['playlist'] - tracks, track_ids = playlist['tracks'], playlist['trackIds'] + tracks, track_ids = playlist['tracks'], map(compat_str, playlist['trackIds']) # tracks dictionary shipped with playlist.jsx API is limited to 150 tracks, # missing tracks should be retrieved manually. if len(tracks) < len(track_ids): - present_track_ids = set([compat_str(track['id']) for track in tracks if track.get('id')]) - missing_track_ids = set(map(compat_str, track_ids)) - set(present_track_ids) - request = sanitized_Request( - 'https://music.yandex.ru/handlers/track-entries.jsx', - urlencode_postdata({ + present_track_ids = set([ + compat_str(track['id']) + for track in tracks if track.get('id')]) + missing_track_ids = [ + track_id for track_id in track_ids + if track_id not in present_track_ids] + missing_tracks = self._download_json( + 'https://music.yandex.%s/handlers/track-entries.jsx' % tld, + playlist_id, 'Downloading missing tracks JSON', + fatal=False, + headers={ + 'Referer': url, + 'X-Requested-With': 'XMLHttpRequest', + }, + query={ 'entries': ','.join(missing_track_ids), 'lang': tld, 'external-domain': 'music.yandex.%s' % tld, 'overembed': 'false', 'strict': 'true', - })) - request.add_header('Referer', url) - request.add_header('X-Requested-With', 'XMLHttpRequest') - - missing_tracks = self._download_json( - request, playlist_id, 'Downloading missing tracks JSON', fatal=False) + }) if missing_tracks: tracks.extend(missing_tracks) return self.playlist_result( self._build_playlist(tracks), compat_str(playlist_id), - playlist['title'], playlist.get('description')) + playlist.get('title'), playlist.get('description'))