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 ..utils import (
   8     get_element_by_id,
   9     clean_html,
  10     ExtractorError,
  11     InAdvancePagedList,
  12     remove_start,
  13 )
  14
  15
  16 class KuwoBaseIE(InfoExtractor):
  17     _FORMATS = [
  18         {'format': 'ape', 'ext': 'ape', 'preference': 100},
  19         {'format': 'mp3-320', 'ext': 'mp3', 'br': '320kmp3', 'abr': 320, 'preference': 80},
  20         {'format': 'mp3-192', 'ext': 'mp3', 'br': '192kmp3', 'abr': 192, 'preference': 70},
  21         {'format': 'mp3-128', 'ext': 'mp3', 'br': '128kmp3', 'abr': 128, 'preference': 60},
  22         {'format': 'wma', 'ext': 'wma', 'preference': 20},
  23         {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10}
  24     ]
  25
  26     def _get_formats(self, song_id, tolerate_ip_deny=False):
  27         formats = []
  28         for file_format in self._FORMATS:
  29             headers = {}
  30             cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
  31             if cn_verification_proxy:
  32                 headers['Ytdl-request-proxy'] = cn_verification_proxy
  33
  34             query = {
  35                 'format': file_format['ext'],
  36                 'br': file_format.get('br', ''),
  37                 'rid': 'MUSIC_%s' % song_id,
  38                 'type': 'convert_url',
  39                 'response': 'url'
  40             }
  41
  42             song_url = self._download_webpage(
  43                 'http://antiserver.kuwo.cn/anti.s',
  44                 song_id, note='Download %s url info' % file_format['format'],
  45                 query=query, headers=headers,
  46             )
  47
  48             if song_url == 'IPDeny' and not tolerate_ip_deny:
  49                 raise ExtractorError('This song is blocked in this region', expected=True)
  50
  51             if song_url.startswith('http://') or song_url.startswith('https://'):
  52                 formats.append({
  53                     'url': song_url,
  54                     'format_id': file_format['format'],
  55                     'format': file_format['format'],
  56                     'preference': file_format['preference'],
  57                     'abr': file_format.get('abr'),
  58                 })
  59
  60         return formats
  61
  62
  63 class KuwoIE(KuwoBaseIE):
  64     IE_NAME = 'kuwo:song'
  65     IE_DESC = '酷我音乐'
  66     _VALID_URL = r'https?://www\.kuwo\.cn/yinyue/(?P<id>\d+)'
  67     _TESTS = [{
  68         'url': 'http://www.kuwo.cn/yinyue/635632/',
  69         'info_dict': {
  70             'id': '635632',
  71             'ext': 'ape',
  72             'title': '爱我别走',
  73             'creator': '张震岳',
  74             'upload_date': '20080122',
  75             'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c'
  76         },
  77         'skip': 'this song has been offline because of copyright issues',
  78     }, {
  79         'url': 'http://www.kuwo.cn/yinyue/6446136/',
  80         'info_dict': {
  81             'id': '6446136',
  82             'ext': 'mp3',
  83             'title': '心',
  84             'description': 'md5:5d0e947b242c35dc0eb1d2fce9fbf02c',
  85             'creator': 'IU',
  86             'upload_date': '20150518',
  87         },
  88         'params': {
  89             'format': 'mp3-320'
  90         },
  91     }, {
  92         'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016',
  93         'only_matching': True,
  94     }]
  95
  96     def _real_extract(self, url):
  97         song_id = self._match_id(url)
  98         webpage = self._download_webpage(
  99             url, song_id, note='Download song detail info',
 100             errnote='Unable to get song detail info')
 101         if '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:
 102             raise ExtractorError('this song has been offline because of copyright issues', expected=True)
 103
 104         song_name = self._html_search_regex(
 105             r'<p[^>]+id="lrcName">([^<]+)</p>', webpage, 'song name')
 106         singer_name = remove_start(self._html_search_regex(
 107             r'<a[^>]+href="http://www\.kuwo\.cn/artist/content\?name=([^"]+)">',
 108             webpage, 'singer name', fatal=False), '歌手')
 109         lrc_content = clean_html(get_element_by_id('lrcContent', webpage))
 110         if lrc_content == '暂无':     # indicates no lyrics
 111             lrc_content = None
 112
 113         formats = self._get_formats(song_id)
 114         self._sort_formats(formats)
 115
 116         album_id = self._html_search_regex(
 117             r'<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
 118             webpage, 'album id', fatal=False)
 119
 120         publish_time = None
 121         if album_id is not None:
 122             album_info_page = self._download_webpage(
 123                 'http://www.kuwo.cn/album/%s/' % album_id, song_id,
 124                 note='Download album detail info',
 125                 errnote='Unable to get album detail info')
 126
 127             publish_time = self._html_search_regex(
 128                 r'发行时间：(\d{4}-\d{2}-\d{2})', album_info_page,
 129                 'publish time', fatal=False)
 130             if publish_time:
 131                 publish_time = publish_time.replace('-', '')
 132
 133         return {
 134             'id': song_id,
 135             'title': song_name,
 136             'creator': singer_name,
 137             'upload_date': publish_time,
 138             'description': lrc_content,
 139             'formats': formats,
 140         }
 141
 142
 143 class KuwoAlbumIE(InfoExtractor):
 144     IE_NAME = 'kuwo:album'
 145     IE_DESC = '酷我音乐 - 专辑'
 146     _VALID_URL = r'https?://www\.kuwo\.cn/album/(?P<id>\d+?)/'
 147     _TEST = {
 148         'url': 'http://www.kuwo.cn/album/502294/',
 149         'info_dict': {
 150             'id': '502294',
 151             'title': 'Made\xa0Series\xa0《M》',
 152             'description': 'md5:d463f0d8a0ff3c3ea3d6ed7452a9483f',
 153         },
 154         'playlist_count': 2,
 155     }
 156
 157     def _real_extract(self, url):
 158         album_id = self._match_id(url)
 159
 160         webpage = self._download_webpage(
 161             url, album_id, note='Download album info',
 162             errnote='Unable to get album info')
 163
 164         album_name = self._html_search_regex(
 165             r'<div[^>]+class="comm"[^<]+<h1[^>]+title="([^"]+)"', webpage,
 166             'album name')
 167         album_intro = remove_start(
 168             clean_html(get_element_by_id('intro', webpage)),
 169             '%s简介：' % album_name)
 170
 171         entries = [
 172             self.url_result(song_url, 'Kuwo') for song_url in re.findall(
 173                 r'<p[^>]+class="listen"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"',
 174                 webpage)
 175         ]
 176         return self.playlist_result(entries, album_id, album_name, album_intro)
 177
 178
 179 class KuwoChartIE(InfoExtractor):
 180     IE_NAME = 'kuwo:chart'
 181     IE_DESC = '酷我音乐 - 排行榜'
 182     _VALID_URL = r'https?://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
 183     _TEST = {
 184         'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
 185         'info_dict': {
 186             'id': '香港中文龙虎榜',
 187         },
 188         'playlist_mincount': 10,
 189     }
 190
 191     def _real_extract(self, url):
 192         chart_id = self._match_id(url)
 193         webpage = self._download_webpage(
 194             url, chart_id, note='Download chart info',
 195             errnote='Unable to get chart info')
 196
 197         entries = [
 198             self.url_result(song_url, 'Kuwo') for song_url in re.findall(
 199                 r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)', webpage)
 200         ]
 201         return self.playlist_result(entries, chart_id)
 202
 203
 204 class KuwoSingerIE(InfoExtractor):
 205     IE_NAME = 'kuwo:singer'
 206     IE_DESC = '酷我音乐 - 歌手'
 207     _VALID_URL = r'https?://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
 208     _TESTS = [{
 209         'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
 210         'info_dict': {
 211             'id': 'bruno+mars',
 212             'title': 'Bruno\xa0Mars',
 213         },
 214         'playlist_mincount': 329,
 215     }, {
 216         'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
 217         'info_dict': {
 218             'id': 'Ali',
 219             'title': 'Ali',
 220         },
 221         'playlist_mincount': 95,
 222         'skip': 'Regularly stalls travis build',  # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540
 223     }]
 224
 225     PAGE_SIZE = 15
 226
 227     def _real_extract(self, url):
 228         singer_id = self._match_id(url)
 229         webpage = self._download_webpage(
 230             url, singer_id, note='Download singer info',
 231             errnote='Unable to get singer info')
 232
 233         singer_name = self._html_search_regex(
 234             r'<h1>([^<]+)</h1>', webpage, 'singer name')
 235
 236         artist_id = self._html_search_regex(
 237             r'data-artistid="(\d+)"', webpage, 'artist id')
 238
 239         page_count = int(self._html_search_regex(
 240             r'data-page="(\d+)"', webpage, 'page count'))
 241
 242         def page_func(page_num):
 243             webpage = self._download_webpage(
 244                 'http://www.kuwo.cn/artist/contentMusicsAjax',
 245                 singer_id, note='Download song list page #%d' % (page_num + 1),
 246                 errnote='Unable to get song list page #%d' % (page_num + 1),
 247                 query={'artistId': artist_id, 'pn': page_num, 'rn': self.PAGE_SIZE})
 248
 249             return [
 250                 self.url_result(song_url, 'Kuwo') for song_url in re.findall(
 251                     r'<div[^>]+class="name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)',
 252                     webpage)
 253             ]
 254
 255         entries = InAdvancePagedList(page_func, page_count, self.PAGE_SIZE)
 256
 257         return self.playlist_result(entries, singer_id, singer_name)
 258
 259
 260 class KuwoCategoryIE(InfoExtractor):
 261     IE_NAME = 'kuwo:category'
 262     IE_DESC = '酷我音乐 - 分类'
 263     _VALID_URL = r'https?://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
 264     _TEST = {
 265         'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
 266         'info_dict': {
 267             'id': '86375',
 268             'title': '八十年代精选',
 269             'description': '这些都是属于八十年代的回忆！',
 270         },
 271         'playlist_mincount': 24,
 272     }
 273
 274     def _real_extract(self, url):
 275         category_id = self._match_id(url)
 276         webpage = self._download_webpage(
 277             url, category_id, note='Download category info',
 278             errnote='Unable to get category info')
 279
 280         category_name = self._html_search_regex(
 281             r'<h1[^>]+title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name')
 282
 283         category_desc = remove_start(
 284             get_element_by_id('intro', webpage).strip(),
 285             '%s简介：' % category_name)
 286         if category_desc == '暂无':
 287             category_desc = None
 288
 289         jsonm = self._parse_json(self._html_search_regex(
 290             r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)
 291
 292         entries = [
 293             self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo')
 294             for song in jsonm['musiclist']
 295         ]
 296         return self.playlist_result(entries, category_id, category_name, category_desc)
 297
 298
 299 class KuwoMvIE(KuwoBaseIE):
 300     IE_NAME = 'kuwo:mv'
 301     IE_DESC = '酷我音乐 - MV'
 302     _VALID_URL = r'https?://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
 303     _TEST = {
 304         'url': 'http://www.kuwo.cn/mv/6480076/',
 305         'info_dict': {
 306             'id': '6480076',
 307             'ext': 'mp4',
 308             'title': 'My HouseMV',
 309             'creator': 'PM02:00',
 310         },
 311         # In this video, music URLs (anti.s) are blocked outside China and
 312         # USA, while the MV URL (mvurl) is available globally, so force the MV
 313         # URL for consistent results in different countries
 314         'params': {
 315             'format': 'mv',
 316         },
 317     }
 318     _FORMATS = KuwoBaseIE._FORMATS + [
 319         {'format': 'mkv', 'ext': 'mkv', 'preference': 250},
 320         {'format': 'mp4', 'ext': 'mp4', 'preference': 200},
 321     ]
 322
 323     def _real_extract(self, url):
 324         song_id = self._match_id(url)
 325         webpage = self._download_webpage(
 326             url, song_id, note='Download mv detail info: %s' % song_id,
 327             errnote='Unable to get mv detail info: %s' % song_id)
 328
 329         mobj = re.search(
 330             r'<h1[^>]+title="(?P<song>[^"]+)">[^<]+<span[^>]+title="(?P<singer>[^"]+)"',
 331             webpage)
 332         if mobj:
 333             song_name = mobj.group('song')
 334             singer_name = mobj.group('singer')
 335         else:
 336             raise ExtractorError('Unable to find song or singer names')
 337
 338         formats = self._get_formats(song_id, tolerate_ip_deny=True)
 339
 340         mv_url = self._download_webpage(
 341             'http://www.kuwo.cn/yy/st/mvurl?rid=MUSIC_%s' % song_id,
 342             song_id, note='Download %s MV URL' % song_id)
 343         formats.append({
 344             'url': mv_url,
 345             'format_id': 'mv',
 346         })
 347
 348         self._sort_formats(formats)
 349
 350         return {
 351             'id': song_id,
 352             'title': song_name,
 353             'creator': singer_name,
 354             'formats': formats,
 355         }