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