yt_dlp/extractor/kuwo.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_urlparse
   5 from ..utils import (
   6     get_element_by_id,
   7     clean_html,
   8     ExtractorError,
   9     InAdvancePagedList,
  10     remove_start,
  11 )
  12
  13
  14 class KuwoBaseIE(InfoExtractor):
  15     _FORMATS = [
  16         {'format': 'ape', 'ext': 'ape', 'preference': 100},
  17         {'format': 'mp3-320', 'ext': 'mp3', 'br': '320kmp3', 'abr': 320, 'preference': 80},
  18         {'format': 'mp3-192', 'ext': 'mp3', 'br': '192kmp3', 'abr': 192, 'preference': 70},
  19         {'format': 'mp3-128', 'ext': 'mp3', 'br': '128kmp3', 'abr': 128, 'preference': 60},
  20         {'format': 'wma', 'ext': 'wma', 'preference': 20},
  21         {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10}
  22     ]
  23
  24     def _get_formats(self, song_id, tolerate_ip_deny=False):
  25         formats = []
  26         for file_format in self._FORMATS:
  27             query = {
  28                 'format': file_format['ext'],
  29                 'br': file_format.get('br', ''),
  30                 'rid': 'MUSIC_%s' % song_id,
  31                 'type': 'convert_url',
  32                 'response': 'url'
  33             }
  34
  35             song_url = self._download_webpage(
  36                 'http://antiserver.kuwo.cn/anti.s',
  37                 song_id, note='Download %s url info' % file_format['format'],
  38                 query=query, headers=self.geo_verification_headers(),
  39             )
  40
  41             if song_url == 'IPDeny' and not tolerate_ip_deny:
  42                 raise ExtractorError('This song is blocked in this region', expected=True)
  43
  44             if song_url.startswith('http://') or song_url.startswith('https://'):
  45                 formats.append({
  46                     'url': song_url,
  47                     'format_id': file_format['format'],
  48                     'format': file_format['format'],
  49                     'quality': file_format['preference'],
  50                     'abr': file_format.get('abr'),
  51                 })
  52
  53         return formats
  54
  55
  56 class KuwoIE(KuwoBaseIE):
  57     _WORKING = False
  58     IE_NAME = 'kuwo:song'
  59     IE_DESC = '酷我音乐'
  60     _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/yinyue/(?P<id>\d+)'
  61     _TESTS = [{
  62         'url': 'http://www.kuwo.cn/yinyue/635632/',
  63         'info_dict': {
  64             'id': '635632',
  65             'ext': 'ape',
  66             'title': '爱我别走',
  67             'creator': '张震岳',
  68             'upload_date': '20080122',
  69             'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c'
  70         },
  71         'skip': 'this song has been offline because of copyright issues',
  72     }, {
  73         'url': 'http://www.kuwo.cn/yinyue/6446136/',
  74         'info_dict': {
  75             'id': '6446136',
  76             'ext': 'mp3',
  77             'title': '心',
  78             'description': 'md5:5d0e947b242c35dc0eb1d2fce9fbf02c',
  79             'creator': 'IU',
  80             'upload_date': '20150518',
  81         },
  82         'params': {
  83             'format': 'mp3-320',
  84         },
  85     }, {
  86         'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016',
  87         'only_matching': True,
  88     }]
  89
  90     def _real_extract(self, url):
  91         song_id = self._match_id(url)
  92         webpage, urlh = self._download_webpage_handle(
  93             url, song_id, note='Download song detail info',
  94             errnote='Unable to get song detail info')
  95         if song_id not in urlh.url or '对不起，该歌曲由于版权问题已被下线，将返回网站首页' in webpage:
  96             raise ExtractorError('this song has been offline because of copyright issues', expected=True)
  97
  98         song_name = self._html_search_regex(
  99             r'<p[^>]+id="lrcName">([^<]+)</p>', webpage, 'song name')
 100         singer_name = remove_start(self._html_search_regex(
 101             r'<a[^>]+href="http://www\.kuwo\.cn/artist/content\?name=([^"]+)">',
 102             webpage, 'singer name', fatal=False), '歌手')
 103         lrc_content = clean_html(get_element_by_id('lrcContent', webpage))
 104         if lrc_content == '暂无':     # indicates no lyrics
 105             lrc_content = None
 106
 107         formats = self._get_formats(song_id)
 108
 109         album_id = self._html_search_regex(
 110             r'<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
 111             webpage, 'album id', fatal=False)
 112
 113         publish_time = None
 114         if album_id is not None:
 115             album_info_page = self._download_webpage(
 116                 'http://www.kuwo.cn/album/%s/' % album_id, song_id,
 117                 note='Download album detail info',
 118                 errnote='Unable to get album detail info')
 119
 120             publish_time = self._html_search_regex(
 121                 r'发行时间：(\d{4}-\d{2}-\d{2})', album_info_page,
 122                 'publish time', fatal=False)
 123             if publish_time:
 124                 publish_time = publish_time.replace('-', '')
 125
 126         return {
 127             'id': song_id,
 128             'title': song_name,
 129             'creator': singer_name,
 130             'upload_date': publish_time,
 131             'description': lrc_content,
 132             'formats': formats,
 133         }
 134
 135
 136 class KuwoAlbumIE(InfoExtractor):
 137     _WORKING = False
 138     IE_NAME = 'kuwo:album'
 139     IE_DESC = '酷我音乐 - 专辑'
 140     _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/album/(?P<id>\d+?)/'
 141     _TEST = {
 142         'url': 'http://www.kuwo.cn/album/502294/',
 143         'info_dict': {
 144             'id': '502294',
 145             'title': 'Made\xa0Series\xa0《M》',
 146             'description': 'md5:d463f0d8a0ff3c3ea3d6ed7452a9483f',
 147         },
 148         'playlist_count': 2,
 149     }
 150
 151     def _real_extract(self, url):
 152         album_id = self._match_id(url)
 153
 154         webpage = self._download_webpage(
 155             url, album_id, note='Download album info',
 156             errnote='Unable to get album info')
 157
 158         album_name = self._html_search_regex(
 159             r'<div[^>]+class="comm"[^<]+<h1[^>]+title="([^"]+)"', webpage,
 160             'album name')
 161         album_intro = remove_start(
 162             clean_html(get_element_by_id('intro', webpage)),
 163             '%s简介：' % album_name)
 164
 165         entries = [
 166             self.url_result(song_url, 'Kuwo') for song_url in re.findall(
 167                 r'<p[^>]+class="listen"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"',
 168                 webpage)
 169         ]
 170         return self.playlist_result(entries, album_id, album_name, album_intro)
 171
 172
 173 class KuwoChartIE(InfoExtractor):
 174     _WORKING = False
 175     IE_NAME = 'kuwo:chart'
 176     IE_DESC = '酷我音乐 - 排行榜'
 177     _VALID_URL = r'https?://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
 178     _TEST = {
 179         'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
 180         'info_dict': {
 181             'id': '香港中文龙虎榜',
 182         },
 183         'playlist_mincount': 7,
 184     }
 185
 186     def _real_extract(self, url):
 187         chart_id = self._match_id(url)
 188         webpage = self._download_webpage(
 189             url, chart_id, note='Download chart info',
 190             errnote='Unable to get chart info')
 191
 192         entries = [
 193             self.url_result(song_url, 'Kuwo') for song_url in re.findall(
 194                 r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)', webpage)
 195         ]
 196         return self.playlist_result(entries, chart_id)
 197
 198
 199 class KuwoSingerIE(InfoExtractor):
 200     _WORKING = False
 201     IE_NAME = 'kuwo:singer'
 202     IE_DESC = '酷我音乐 - 歌手'
 203     _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mingxing/(?P<id>[^/]+)'
 204     _TESTS = [{
 205         'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
 206         'info_dict': {
 207             'id': 'bruno+mars',
 208             'title': 'Bruno\xa0Mars',
 209         },
 210         'playlist_mincount': 329,
 211     }, {
 212         'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
 213         'info_dict': {
 214             'id': 'Ali',
 215             'title': 'Ali',
 216         },
 217         'playlist_mincount': 95,
 218         'skip': 'Regularly stalls travis build',  # See https://travis-ci.org/ytdl-org/youtube-dl/jobs/78878540
 219     }]
 220
 221     PAGE_SIZE = 15
 222
 223     def _real_extract(self, url):
 224         singer_id = self._match_id(url)
 225         webpage = self._download_webpage(
 226             url, singer_id, note='Download singer info',
 227             errnote='Unable to get singer info')
 228
 229         singer_name = self._html_search_regex(
 230             r'<h1>([^<]+)</h1>', webpage, 'singer name')
 231
 232         artist_id = self._html_search_regex(
 233             r'data-artistid="(\d+)"', webpage, 'artist id')
 234
 235         page_count = int(self._html_search_regex(
 236             r'data-page="(\d+)"', webpage, 'page count'))
 237
 238         def page_func(page_num):
 239             webpage = self._download_webpage(
 240                 'http://www.kuwo.cn/artist/contentMusicsAjax',
 241                 singer_id, note='Download song list page #%d' % (page_num + 1),
 242                 errnote='Unable to get song list page #%d' % (page_num + 1),
 243                 query={'artistId': artist_id, 'pn': page_num, 'rn': self.PAGE_SIZE})
 244
 245             return [
 246                 self.url_result(compat_urlparse.urljoin(url, song_url), 'Kuwo')
 247                 for song_url in re.findall(
 248                     r'<div[^>]+class="name"><a[^>]+href="(/yinyue/\d+)',
 249                     webpage)
 250             ]
 251
 252         entries = InAdvancePagedList(page_func, page_count, self.PAGE_SIZE)
 253
 254         return self.playlist_result(entries, singer_id, singer_name)
 255
 256
 257 class KuwoCategoryIE(InfoExtractor):
 258     _WORKING = False
 259     IE_NAME = 'kuwo:category'
 260     IE_DESC = '酷我音乐 - 分类'
 261     _VALID_URL = r'https?://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
 262     _TEST = {
 263         'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
 264         'info_dict': {
 265             'id': '86375',
 266             'title': '八十年代精选',
 267             'description': '这些都是属于八十年代的回忆！',
 268         },
 269         'playlist_mincount': 24,
 270     }
 271
 272     def _real_extract(self, url):
 273         category_id = self._match_id(url)
 274         webpage = self._download_webpage(
 275             url, category_id, note='Download category info',
 276             errnote='Unable to get category info')
 277
 278         category_name = self._html_search_regex(
 279             r'<h1[^>]+title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name')
 280
 281         category_desc = remove_start(
 282             get_element_by_id('intro', webpage).strip(),
 283             '%s简介：' % category_name)
 284         if category_desc == '暂无':
 285             category_desc = None
 286
 287         jsonm = self._parse_json(self._html_search_regex(
 288             r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)
 289
 290         entries = [
 291             self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo')
 292             for song in jsonm['musiclist']
 293         ]
 294         return self.playlist_result(entries, category_id, category_name, category_desc)
 295
 296
 297 class KuwoMvIE(KuwoBaseIE):
 298     _WORKING = False
 299     IE_NAME = 'kuwo:mv'
 300     IE_DESC = '酷我音乐 - MV'
 301     _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mv/(?P<id>\d+?)/'
 302     _TEST = {
 303         'url': 'http://www.kuwo.cn/mv/6480076/',
 304         'info_dict': {
 305             'id': '6480076',
 306             'ext': 'mp4',
 307             'title': 'My HouseMV',
 308             'creator': '2PM',
 309         },
 310         # In this video, music URLs (anti.s) are blocked outside China and
 311         # USA, while the MV URL (mvurl) is available globally, so force the MV
 312         # URL for consistent results in different countries
 313         'params': {
 314             'format': 'mv',
 315         },
 316     }
 317     _FORMATS = KuwoBaseIE._FORMATS + [
 318         {'format': 'mkv', 'ext': 'mkv', 'preference': 250},
 319         {'format': 'mp4', 'ext': 'mp4', 'preference': 200},
 320     ]
 321
 322     def _real_extract(self, url):
 323         song_id = self._match_id(url)
 324         webpage = self._download_webpage(
 325             url, song_id, note='Download mv detail info: %s' % song_id,
 326             errnote='Unable to get mv detail info: %s' % song_id)
 327
 328         mobj = re.search(
 329             r'<h1[^>]+title="(?P<song>[^"]+)">[^<]+<span[^>]+title="(?P<singer>[^"]+)"',
 330             webpage)
 331         if mobj:
 332             song_name = mobj.group('song')
 333             singer_name = mobj.group('singer')
 334         else:
 335             raise ExtractorError('Unable to find song or singer names')
 336
 337         formats = self._get_formats(song_id, tolerate_ip_deny=True)
 338
 339         mv_url = self._download_webpage(
 340             'http://www.kuwo.cn/yy/st/mvurl?rid=MUSIC_%s' % song_id,
 341             song_id, note='Download %s MV URL' % song_id)
 342         formats.append({
 343             'url': mv_url,
 344             'format_id': 'mv',
 345         })
 346
 347         return {
 348             'id': song_id,
 349             'title': song_name,
 350             'creator': singer_name,
 351             'formats': formats,
 352         }