yt-dlp/youtube_dl/extractor/yandexmusic.py

240 lines
9 KiB
Python
Raw Normal View History

# coding: utf-8
2015-03-09 13:06:49 +00:00
from __future__ import unicode_literals
import re
import hashlib
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
int_or_none,
float_or_none,
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 16:18:17 +00:00
sanitized_Request,
urlencode_postdata,
)
2015-03-09 13:06:49 +00:00
class YandexMusicBaseIE(InfoExtractor):
@staticmethod
def _handle_error(response):
2016-04-28 15:37:34 +00:00
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 запросы, поступившие с вашего IP-адреса, похожи на автоматические.' in webpage:
2016-04-28 15:45:33 +00:00
raise ExtractorError(
'YandexMusic asks you to solve a CAPTCHA: go to '
'https://music.yandex.ru/ and solve it, 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)
self._handle_error(response)
return response
class YandexMusicTrackIE(YandexMusicBaseIE):
IE_NAME = 'yandexmusic:track'
IE_DESC = 'Яндекс.Музыка - Трек'
_VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<album_id>\d+)/track/(?P<id>\d+)'
_TEST = {
'url': 'http://music.yandex.ru/album/540508/track/4878838',
'md5': 'f496818aa2f60b6c0062980d2e00dc20',
'info_dict': {
'id': '4878838',
'ext': 'mp3',
'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',
}
2015-03-09 13:06:49 +00:00
def _get_track_url(self, storage_dir, track_id):
data = self._download_json(
'http://music.yandex.ru/api/v1.5/handlers/api-jsonp.jsx?action=getTrackSrc&p=download-info/%s'
% storage_dir,
track_id, 'Downloading track location JSON')
2015-03-09 13:06:49 +00:00
key = hashlib.md5(('XGRlBW9FXlekgbPrRHuSiA' + data['path'][1:] + data['s']).encode('utf-8')).hexdigest()
2015-03-09 13:06:49 +00:00
storage = storage_dir.split('.')
return ('http://%s/get-mp3/%s/%s?track-id=%s&from=service-10-track&similarities-experiment=default'
% (data['host'], key, data['ts'] + data['path'], storage[1]))
2015-03-09 13:06:49 +00:00
def _get_track_info(self, track):
thumbnail = None
cover_uri = track.get('albums', [{}])[0].get('coverUri')
if cover_uri:
thumbnail = cover_uri.replace('%%', 'orig')
if not thumbnail.startswith('http'):
thumbnail = 'http://' + thumbnail
track_title = track['title']
track_info = {
'id': track['id'],
'ext': 'mp3',
'url': self._get_track_url(track['storageDir'], track['id']),
'filesize': int_or_none(track.get('fileSize')),
'duration': float_or_none(track.get('durationMs'), 1000),
'thumbnail': thumbnail,
'track': track_title,
}
2015-03-09 13:06:49 +00:00
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
2015-03-09 13:06:49 +00:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
album_id, track_id = mobj.group('album_id'), mobj.group('id')
2015-03-09 13:06:49 +00:00
track = self._download_json(
'http://music.yandex.ru/handlers/track.jsx?track=%s:%s' % (track_id, album_id),
track_id, 'Downloading track JSON')['track']
2015-03-09 13:06:49 +00:00
return self._get_track_info(track)
2015-03-09 13:06:49 +00:00
class YandexMusicPlaylistBaseIE(YandexMusicBaseIE):
def _build_playlist(self, tracks):
return [
self.url_result(
'http://music.yandex.ru/album/%s/track/%s' % (track['albums'][0]['id'], track['id']))
for track in tracks if track.get('albums') and isinstance(track.get('albums'), list)]
class YandexMusicAlbumIE(YandexMusicPlaylistBaseIE):
IE_NAME = 'yandexmusic:album'
IE_DESC = 'Яндекс.Музыка - Альбом'
2015-03-14 07:56:04 +00:00
_VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<id>\d+)/?(\?|$)'
2015-03-09 13:06:49 +00:00
_TEST = {
'url': 'http://music.yandex.ru/album/540508',
'info_dict': {
'id': '540508',
'title': 'Carlo Ambrosio - Gypsy Soul (2009)',
},
'playlist_count': 50,
'skip': 'Travis CI servers blocked by YandexMusic',
}
2015-03-09 13:06:49 +00:00
def _real_extract(self, url):
album_id = self._match_id(url)
2015-03-09 13:06:49 +00:00
album = self._download_json(
'http://music.yandex.ru/handlers/album.jsx?album=%s' % album_id,
album_id, 'Downloading album JSON')
2015-03-09 13:06:49 +00:00
entries = self._build_playlist(album['volumes'][0])
title = '%s - %s' % (album['artists'][0]['name'], album['title'])
year = album.get('year')
if year:
title += ' (%s)' % year
return self.playlist_result(entries, compat_str(album['id']), title)
2015-03-09 13:06:49 +00:00
class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
IE_NAME = 'yandexmusic:playlist'
IE_DESC = 'Яндекс.Музыка - Плейлист'
2015-03-14 07:56:04 +00:00
_VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/users/[^/]+/playlists/(?P<id>\d+)'
_TESTS = [{
'url': 'http://music.yandex.ru/users/music.partners/playlists/1245',
2015-03-09 13:06:49 +00:00
'info_dict': {
'id': '1245',
'title': 'Что слушают Enter Shikari',
'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)
'url': 'https://music.yandex.ru/users/ya.playlist/playlists/1036',
'info_dict': {
'id': '1036',
'title': 'Музыка 90-х',
},
'playlist_count': 310,
'skip': 'Travis CI servers blocked by YandexMusic',
}]
2015-03-09 13:06:49 +00:00
def _real_extract(self, url):
playlist_id = self._match_id(url)
2015-03-09 13:06:49 +00:00
webpage = self._download_webpage(url, playlist_id)
2015-03-09 13:06:49 +00:00
mu = self._parse_json(
self._search_regex(
r'var\s+Mu\s*=\s*({.+?});\s*</script>', webpage, 'player'),
playlist_id)
playlist = mu['pageData']['playlist']
tracks, track_ids = playlist['tracks'], playlist['trackIds']
# tracks dictionary shipped with webpage 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)
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 16:18:17 +00:00
request = sanitized_Request(
'https://music.yandex.ru/handlers/track-entries.jsx',
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',
}))
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'))