Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/xiami.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urllib_parse_unquote
   6 from ..utils import int_or_none
   7
   8
   9 class XiamiBaseIE(InfoExtractor):
  10     _API_BASE_URL = 'http://www.xiami.com/song/playlist/cat/json/id'
  11
  12     def _download_webpage(self, *args, **kwargs):
  13         webpage = super(XiamiBaseIE, self)._download_webpage(*args, **kwargs)
  14         if '>Xiami is currently not available in your country.<' in webpage:
  15             self.raise_geo_restricted('Xiami is currently not available in your country')
  16         return webpage
  17
  18     def _extract_track(self, track, track_id=None):
  19         track_name = track.get('songName') or track.get('name') or track['subName']
  20         artist = track.get('artist') or track.get('artist_name') or track.get('singers')
  21         title = '%s - %s' % (artist, track_name) if artist else track_name
  22         track_url = self._decrypt(track['location'])
  23
  24         subtitles = {}
  25         lyrics_url = track.get('lyric_url') or track.get('lyric')
  26         if lyrics_url and lyrics_url.startswith('http'):
  27             subtitles['origin'] = [{'url': lyrics_url}]
  28
  29         return {
  30             'id': track.get('song_id') or track_id,
  31             'url': track_url,
  32             'title': title,
  33             'thumbnail': track.get('pic') or track.get('album_pic'),
  34             'duration': int_or_none(track.get('length')),
  35             'creator': track.get('artist', '').split(';')[0],
  36             'track': track_name,
  37             'track_number': int_or_none(track.get('track')),
  38             'album': track.get('album_name') or track.get('title'),
  39             'artist': artist,
  40             'subtitles': subtitles,
  41         }
  42
  43     def _extract_tracks(self, item_id, typ=None):
  44         playlist = self._download_json(
  45             '%s/%s%s' % (self._API_BASE_URL, item_id, '/type/%s' % typ if typ else ''), item_id)
  46         return [
  47             self._extract_track(track, item_id)
  48             for track in playlist['data']['trackList']]
  49
  50     @staticmethod
  51     def _decrypt(origin):
  52         n = int(origin[0])
  53         origin = origin[1:]
  54         short_lenth = len(origin) // n
  55         long_num = len(origin) - short_lenth * n
  56         l = tuple()
  57         for i in range(0, n):
  58             length = short_lenth
  59             if i < long_num:
  60                 length += 1
  61             l += (origin[0:length], )
  62             origin = origin[length:]
  63         ans = ''
  64         for i in range(0, short_lenth + 1):
  65             for j in range(0, n):
  66                 if len(l[j]) > i:
  67                     ans += l[j][i]
  68         return compat_urllib_parse_unquote(ans).replace('^', '0')
  69
  70
  71 class XiamiSongIE(XiamiBaseIE):
  72     IE_NAME = 'xiami:song'
  73     IE_DESC = '虾米音乐'
  74     _VALID_URL = r'https?://(?:www\.)?xiami\.com/song/(?P<id>[^/?#&]+)'
  75     _TESTS = [{
  76         'url': 'http://www.xiami.com/song/1775610518',
  77         'md5': '521dd6bea40fd5c9c69f913c232cb57e',
  78         'info_dict': {
  79             'id': '1775610518',
  80             'ext': 'mp3',
  81             'title': 'HONNE - Woman',
  82             'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
  83             'duration': 265,
  84             'creator': 'HONNE',
  85             'track': 'Woman',
  86             'album': 'Woman',
  87             'artist': 'HONNE',
  88             'subtitles': {
  89                 'origin': [{
  90                     'ext': 'lrc',
  91                 }],
  92             },
  93         },
  94         'skip': 'Georestricted',
  95     }, {
  96         'url': 'http://www.xiami.com/song/1775256504',
  97         'md5': '932a3abd45c6aa2b1fdbe028fcb4c4fc',
  98         'info_dict': {
  99             'id': '1775256504',
 100             'ext': 'mp3',
 101             'title': '戴荃 - 悟空',
 102             'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
 103             'duration': 200,
 104             'creator': '戴荃',
 105             'track': '悟空',
 106             'album': '悟空',
 107             'artist': '戴荃',
 108             'subtitles': {
 109                 'origin': [{
 110                     'ext': 'lrc',
 111                 }],
 112             },
 113         },
 114         'skip': 'Georestricted',
 115     }, {
 116         'url': 'http://www.xiami.com/song/1775953850',
 117         'info_dict': {
 118             'id': '1775953850',
 119             'ext': 'mp3',
 120             'title': 'До Скону - Чума Пожирает Землю',
 121             'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
 122             'duration': 683,
 123             'creator': 'До Скону',
 124             'track': 'Чума Пожирает Землю',
 125             'track_number': 7,
 126             'album': 'Ад',
 127             'artist': 'До Скону',
 128         },
 129         'params': {
 130             'skip_download': True,
 131         },
 132     }, {
 133         'url': 'http://www.xiami.com/song/xLHGwgd07a1',
 134         'only_matching': True,
 135     }]
 136
 137     def _real_extract(self, url):
 138         return self._extract_tracks(self._match_id(url))[0]
 139
 140
 141 class XiamiPlaylistBaseIE(XiamiBaseIE):
 142     def _real_extract(self, url):
 143         item_id = self._match_id(url)
 144         return self.playlist_result(self._extract_tracks(item_id, self._TYPE), item_id)
 145
 146
 147 class XiamiAlbumIE(XiamiPlaylistBaseIE):
 148     IE_NAME = 'xiami:album'
 149     IE_DESC = '虾米音乐 - 专辑'
 150     _VALID_URL = r'https?://(?:www\.)?xiami\.com/album/(?P<id>[^/?#&]+)'
 151     _TYPE = '1'
 152     _TESTS = [{
 153         'url': 'http://www.xiami.com/album/2100300444',
 154         'info_dict': {
 155             'id': '2100300444',
 156         },
 157         'playlist_count': 10,
 158         'skip': 'Georestricted',
 159     }, {
 160         'url': 'http://www.xiami.com/album/512288?spm=a1z1s.6843761.1110925389.6.hhE9p9',
 161         'only_matching': True,
 162     }, {
 163         'url': 'http://www.xiami.com/album/URVDji2a506',
 164         'only_matching': True,
 165     }]
 166
 167
 168 class XiamiArtistIE(XiamiPlaylistBaseIE):
 169     IE_NAME = 'xiami:artist'
 170     IE_DESC = '虾米音乐 - 歌手'
 171     _VALID_URL = r'https?://(?:www\.)?xiami\.com/artist/(?P<id>[^/?#&]+)'
 172     _TYPE = '2'
 173     _TESTS = [{
 174         'url': 'http://www.xiami.com/artist/2132?spm=0.0.0.0.dKaScp',
 175         'info_dict': {
 176             'id': '2132',
 177         },
 178         'playlist_count': 20,
 179         'skip': 'Georestricted',
 180     }, {
 181         'url': 'http://www.xiami.com/artist/bC5Tk2K6eb99',
 182         'only_matching': True,
 183     }]
 184
 185
 186 class XiamiCollectionIE(XiamiPlaylistBaseIE):
 187     IE_NAME = 'xiami:collection'
 188     IE_DESC = '虾米音乐 - 精选集'
 189     _VALID_URL = r'https?://(?:www\.)?xiami\.com/collect/(?P<id>[^/?#&]+)'
 190     _TYPE = '3'
 191     _TEST = {
 192         'url': 'http://www.xiami.com/collect/156527391?spm=a1z1s.2943601.6856193.12.4jpBnr',
 193         'info_dict': {
 194             'id': '156527391',
 195         },
 196         'playlist_mincount': 29,
 197         'skip': 'Georestricted',
 198     }