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_handle(self, *args, **kwargs):
  13         webpage = super(XiamiBaseIE, self)._download_webpage_handle(*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, referer, typ=None):
  44         playlist = self._download_json(
  45             '%s/%s%s' % (self._API_BASE_URL, item_id, '/type/%s' % typ if typ else ''),
  46             item_id, headers={
  47                 'Referer': referer,
  48             })
  49         return [
  50             self._extract_track(track, item_id)
  51             for track in playlist['data']['trackList']]
  52
  53     @staticmethod
  54     def _decrypt(origin):
  55         n = int(origin[0])
  56         origin = origin[1:]
  57         short_lenth = len(origin) // n
  58         long_num = len(origin) - short_lenth * n
  59         l = tuple()
  60         for i in range(0, n):
  61             length = short_lenth
  62             if i < long_num:
  63                 length += 1
  64             l += (origin[0:length], )
  65             origin = origin[length:]
  66         ans = ''
  67         for i in range(0, short_lenth + 1):
  68             for j in range(0, n):
  69                 if len(l[j]) > i:
  70                     ans += l[j][i]
  71         return compat_urllib_parse_unquote(ans).replace('^', '0')
  72
  73
  74 class XiamiSongIE(XiamiBaseIE):
  75     IE_NAME = 'xiami:song'
  76     IE_DESC = '虾米音乐'
  77     _VALID_URL = r'https?://(?:www\.)?xiami\.com/song/(?P<id>[^/?#&]+)'
  78     _TESTS = [{
  79         'url': 'http://www.xiami.com/song/1775610518',
  80         'md5': '521dd6bea40fd5c9c69f913c232cb57e',
  81         'info_dict': {
  82             'id': '1775610518',
  83             'ext': 'mp3',
  84             'title': 'HONNE - Woman',
  85             'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
  86             'duration': 265,
  87             'creator': 'HONNE',
  88             'track': 'Woman',
  89             'album': 'Woman',
  90             'artist': 'HONNE',
  91             'subtitles': {
  92                 'origin': [{
  93                     'ext': 'lrc',
  94                 }],
  95             },
  96         },
  97         'skip': 'Georestricted',
  98     }, {
  99         'url': 'http://www.xiami.com/song/1775256504',
 100         'md5': '932a3abd45c6aa2b1fdbe028fcb4c4fc',
 101         'info_dict': {
 102             'id': '1775256504',
 103             'ext': 'mp3',
 104             'title': '戴荃 - 悟空',
 105             'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
 106             'duration': 200,
 107             'creator': '戴荃',
 108             'track': '悟空',
 109             'album': '悟空',
 110             'artist': '戴荃',
 111             'subtitles': {
 112                 'origin': [{
 113                     'ext': 'lrc',
 114                 }],
 115             },
 116         },
 117         'skip': 'Georestricted',
 118     }, {
 119         'url': 'http://www.xiami.com/song/1775953850',
 120         'info_dict': {
 121             'id': '1775953850',
 122             'ext': 'mp3',
 123             'title': 'До Скону - Чума Пожирает Землю',
 124             'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
 125             'duration': 683,
 126             'creator': 'До Скону',
 127             'track': 'Чума Пожирает Землю',
 128             'track_number': 7,
 129             'album': 'Ад',
 130             'artist': 'До Скону',
 131         },
 132         'params': {
 133             'skip_download': True,
 134         },
 135     }, {
 136         'url': 'http://www.xiami.com/song/xLHGwgd07a1',
 137         'only_matching': True,
 138     }]
 139
 140     def _real_extract(self, url):
 141         return self._extract_tracks(self._match_id(url), url)[0]
 142
 143
 144 class XiamiPlaylistBaseIE(XiamiBaseIE):
 145     def _real_extract(self, url):
 146         item_id = self._match_id(url)
 147         return self.playlist_result(self._extract_tracks(item_id, url, self._TYPE), item_id)
 148
 149
 150 class XiamiAlbumIE(XiamiPlaylistBaseIE):
 151     IE_NAME = 'xiami:album'
 152     IE_DESC = '虾米音乐 - 专辑'
 153     _VALID_URL = r'https?://(?:www\.)?xiami\.com/album/(?P<id>[^/?#&]+)'
 154     _TYPE = '1'
 155     _TESTS = [{
 156         'url': 'http://www.xiami.com/album/2100300444',
 157         'info_dict': {
 158             'id': '2100300444',
 159         },
 160         'playlist_count': 10,
 161         'skip': 'Georestricted',
 162     }, {
 163         'url': 'http://www.xiami.com/album/512288?spm=a1z1s.6843761.1110925389.6.hhE9p9',
 164         'only_matching': True,
 165     }, {
 166         'url': 'http://www.xiami.com/album/URVDji2a506',
 167         'only_matching': True,
 168     }]
 169
 170
 171 class XiamiArtistIE(XiamiPlaylistBaseIE):
 172     IE_NAME = 'xiami:artist'
 173     IE_DESC = '虾米音乐 - 歌手'
 174     _VALID_URL = r'https?://(?:www\.)?xiami\.com/artist/(?P<id>[^/?#&]+)'
 175     _TYPE = '2'
 176     _TESTS = [{
 177         'url': 'http://www.xiami.com/artist/2132?spm=0.0.0.0.dKaScp',
 178         'info_dict': {
 179             'id': '2132',
 180         },
 181         'playlist_count': 20,
 182         'skip': 'Georestricted',
 183     }, {
 184         'url': 'http://www.xiami.com/artist/bC5Tk2K6eb99',
 185         'only_matching': True,
 186     }]
 187
 188
 189 class XiamiCollectionIE(XiamiPlaylistBaseIE):
 190     IE_NAME = 'xiami:collection'
 191     IE_DESC = '虾米音乐 - 精选集'
 192     _VALID_URL = r'https?://(?:www\.)?xiami\.com/collect/(?P<id>[^/?#&]+)'
 193     _TYPE = '3'
 194     _TEST = {
 195         'url': 'http://www.xiami.com/collect/156527391?spm=a1z1s.2943601.6856193.12.4jpBnr',
 196         'info_dict': {
 197             'id': '156527391',
 198         },
 199         'playlist_mincount': 29,
 200         'skip': 'Georestricted',
 201     }