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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_urlparse
   8 from ..utils import (
   9     get_element_by_id,
  10     clean_html,
  11     ExtractorError,
  12     InAdvancePagedList,
  13     remove_start,
  14 )
  15
  16
  17 class KuwoBaseIE(InfoExtractor):
  18     _FORMATS = [
  19         {'format': 'ape', 'ext': 'ape', 'preference': 100},
  20         {'format': 'mp3-320', 'ext': 'mp3', 'br': '320kmp3', 'abr': 320, 'preference': 80},
  21         {'format': 'mp3-192', 'ext': 'mp3', 'br': '192kmp3', 'abr': 192, 'preference': 70},
  22         {'format': 'mp3-128', 'ext': 'mp3', 'br': '128kmp3', 'abr': 128, 'preference': 60},
  23         {'format': 'wma', 'ext': 'wma', 'preference': 20},
  24         {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10}
  25     ]
  26
  27     def _get_formats(self, song_id, tolerate_ip_deny=False):
  28         formats = []
  29         for file_format in self._FORMATS:
  30             query = {
  31                 'format': file_format['ext'],
  32                 'br': file_format.get('br', ''),
  33                 'rid': 'MUSIC_%s' % song_id,
  34                 'type': 'convert_url',
  35                 'response': 'url'
  36             }
  37
  38             song_url = self._download_webpage(
  39                 'http://antiserver.kuwo.cn/anti.s',
  40                 song_id, note='Download %s url info' % file_format['format'],
  41                 query=query, headers=self.geo_verification_headers(),
  42             )
  43
  44             if song_url == 'IPDeny' and not tolerate_ip_deny:
  45                 raise ExtractorError('This song is blocked in this region', expected=True)
  46
  47             if song_url.startswith('http://') or song_url.startswith('https://'):
  48                 formats.append({
  49                     'url': song_url,
  50                     'format_id': file_format['format'],
  51                     'format': file_format['format'],
  52                     'preference': file_format['preference'],
  53                     'abr': file_format.get('abr'),
  54                 })
  55
  56         return formats
  57
  58
  59 class KuwoIE(KuwoBaseIE):
  60     IE_NAME = 'kuwo:song'
  61     IE_DESC = '酷我音乐'
  62     _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/yinyue/(?P<id>\d+)'
  63     _TESTS = [{
  64         'url': 'http://www.kuwo.cn/yinyue/635632/',
  65         'info_dict': {
  66             'id': '635632',
  67             'ext': 'ape',
  68             'title': '爱我别走',
  69             'creator': '张震岳',
  70             'upload_date': '20080122',
  71             'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c'
  72         },
  73         'skip': 'this song has been offline because of copyright issues',
  74     }, {
  75         'url': 'http://www.kuwo.cn/yinyue/6446136/',
  76         'info_dict': {
  77             'id': '6446136',
  78             'ext': 'mp3',
  79             'title': '心',
  80             'description': 'md5:5d0e947b242c35dc0eb1d2fce9fbf02c',
  81             'creator': 'IU',
  82             'upload_date': '20150518',
  83         },
  84         'params': {
  85             'format': 'mp3-320',
  86         },
  87     }, {
  88         'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016',
  89         'only_matching': True,
  90     }]
  91
  92     def _real_extract(self, url):
  93         song_id = self._match_id(url)
  94         webpage, urlh = self._download_webpage_handle(
  95             url, song_id, note='Download song detail info',
  96             errnote='Unable to get song detail info')
  97         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:
  98             raise ExtractorError('this song has been offline because of copyright issues', expected=True)
  99
 100         song_name = self._html_search_regex(
 101             r'<p[^>]+id="lrcName">([^<]+)</p>', webpage, 'song name')
 102         singer_name = remove_start(self._html_search_regex(
 103             r'<a[^>]+href="http://www\.kuwo\.cn/artist/content\?name=([^"]+)">',
 104             webpage, 'singer name', fatal=False), '歌手')
 105         lrc_content = clean_html(get_element_by_id('lrcContent', webpage))
 106         if lrc_content == '暂无':     # indicates no lyrics
 107             lrc_content = None
 108
 109         formats = self._get_formats(song_id)
 110         self._sort_formats(formats)
 111
 112         album_id = self._html_search_regex(
 113             r'<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
 114             webpage, 'album id', fatal=False)
 115
 116         publish_time = None
 117         if album_id is not None:
 118             album_info_page = self._download_webpage(
 119                 'http://www.kuwo.cn/album/%s/' % album_id, song_id,
 120                 note='Download album detail info',
 121                 errnote='Unable to get album detail info')
 122
 123             publish_time = self._html_search_regex(
 124                 r'发行时间：(\d{4}-\d{2}-\d{2})', album_info_page,
 125                 'publish time', fatal=False)
 126             if publish_time:
 127                 publish_time = publish_time.replace('-', '')
 128
 129         return {
 130             'id': song_id,
 131             'title': song_name,
 132             'creator': singer_name,
 133             'upload_date': publish_time,
 134             'description': lrc_content,
 135             'formats': formats,
 136         }
 137
 138
 139 class KuwoAlbumIE(InfoExtractor):
 140     IE_NAME = 'kuwo:album'
 141     IE_DESC = '酷我音乐 - 专辑'
 142     _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/album/(?P<id>\d+?)/'
 143     _TEST = {
 144         'url': 'http://www.kuwo.cn/album/502294/',
 145         'info_dict': {
 146             'id': '502294',
 147             'title': 'Made\xa0Series\xa0《M》',
 148             'description': 'md5:d463f0d8a0ff3c3ea3d6ed7452a9483f',
 149         },
 150         'playlist_count': 2,
 151     }
 152
 153     def _real_extract(self, url):
 154         album_id = self._match_id(url)
 155
 156         webpage = self._download_webpage(
 157             url, album_id, note='Download album info',
 158             errnote='Unable to get album info')
 159
 160         album_name = self._html_search_regex(
 161             r'<div[^>]+class="comm"[^<]+<h1[^>]+title="([^"]+)"', webpage,
 162             'album name')
 163         album_intro = remove_start(
 164             clean_html(get_element_by_id('intro', webpage)),
 165             '%s简介：' % album_name)
 166
 167         entries = [
 168             self.url_result(song_url, 'Kuwo') for song_url in re.findall(
 169                 r'<p[^>]+class="listen"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"',
 170                 webpage)
 171         ]
 172         return self.playlist_result(entries, album_id, album_name, album_intro)
 173
 174
 175 class KuwoChartIE(InfoExtractor):
 176     IE_NAME = 'kuwo:chart'
 177     IE_DESC = '酷我音乐 - 排行榜'
 178     _VALID_URL = r'https?://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
 179     _TEST = {
 180         'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
 181         'info_dict': {
 182             'id': '香港中文龙虎榜',
 183         },
 184         'playlist_mincount': 7,
 185     }
 186
 187     def _real_extract(self, url):
 188         chart_id = self._match_id(url)
 189         webpage = self._download_webpage(
 190             url, chart_id, note='Download chart info',
 191             errnote='Unable to get chart info')
 192
 193         entries = [
 194             self.url_result(song_url, 'Kuwo') for song_url in re.findall(
 195                 r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)', webpage)
 196         ]
 197         return self.playlist_result(entries, chart_id)
 198
 199
 200 class KuwoSingerIE(InfoExtractor):
 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/rg3/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     IE_NAME = 'kuwo:category'
 259     IE_DESC = '酷我音乐 - 分类'
 260     _VALID_URL = r'https?://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
 261     _TEST = {
 262         'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
 263         'info_dict': {
 264             'id': '86375',
 265             'title': '八十年代精选',
 266             'description': '这些都是属于八十年代的回忆！',
 267         },
 268         'playlist_mincount': 24,
 269     }
 270
 271     def _real_extract(self, url):
 272         category_id = self._match_id(url)
 273         webpage = self._download_webpage(
 274             url, category_id, note='Download category info',
 275             errnote='Unable to get category info')
 276
 277         category_name = self._html_search_regex(
 278             r'<h1[^>]+title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name')
 279
 280         category_desc = remove_start(
 281             get_element_by_id('intro', webpage).strip(),
 282             '%s简介：' % category_name)
 283         if category_desc == '暂无':
 284             category_desc = None
 285
 286         jsonm = self._parse_json(self._html_search_regex(
 287             r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)
 288
 289         entries = [
 290             self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo')
 291             for song in jsonm['musiclist']
 292         ]
 293         return self.playlist_result(entries, category_id, category_name, category_desc)
 294
 295
 296 class KuwoMvIE(KuwoBaseIE):
 297     IE_NAME = 'kuwo:mv'
 298     IE_DESC = '酷我音乐 - MV'
 299     _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mv/(?P<id>\d+?)/'
 300     _TEST = {
 301         'url': 'http://www.kuwo.cn/mv/6480076/',
 302         'info_dict': {
 303             'id': '6480076',
 304             'ext': 'mp4',
 305             'title': 'My HouseMV',
 306             'creator': '2PM',
 307         },
 308         # In this video, music URLs (anti.s) are blocked outside China and
 309         # USA, while the MV URL (mvurl) is available globally, so force the MV
 310         # URL for consistent results in different countries
 311         'params': {
 312             'format': 'mv',
 313         },
 314     }
 315     _FORMATS = KuwoBaseIE._FORMATS + [
 316         {'format': 'mkv', 'ext': 'mkv', 'preference': 250},
 317         {'format': 'mp4', 'ext': 'mp4', 'preference': 200},
 318     ]
 319
 320     def _real_extract(self, url):
 321         song_id = self._match_id(url)
 322         webpage = self._download_webpage(
 323             url, song_id, note='Download mv detail info: %s' % song_id,
 324             errnote='Unable to get mv detail info: %s' % song_id)
 325
 326         mobj = re.search(
 327             r'<h1[^>]+title="(?P<song>[^"]+)">[^<]+<span[^>]+title="(?P<singer>[^"]+)"',
 328             webpage)
 329         if mobj:
 330             song_name = mobj.group('song')
 331             singer_name = mobj.group('singer')
 332         else:
 333             raise ExtractorError('Unable to find song or singer names')
 334
 335         formats = self._get_formats(song_id, tolerate_ip_deny=True)
 336
 337         mv_url = self._download_webpage(
 338             'http://www.kuwo.cn/yy/st/mvurl?rid=MUSIC_%s' % song_id,
 339             song_id, note='Download %s MV URL' % song_id)
 340         formats.append({
 341             'url': mv_url,
 342             'format_id': 'mv',
 343         })
 344
 345         self._sort_formats(formats)
 346
 347         return {
 348             'id': song_id,
 349             'title': song_name,
 350             'creator': singer_name,
 351             'formats': formats,
 352         }