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 import itertools
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     get_element_by_id,
  10     clean_html,
  11     ExtractorError,
  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):
  27         formats = []
  28         for file_format in self._FORMATS:
  29             song_url = self._download_webpage(
  30                 'http://antiserver.kuwo.cn/anti.s?format=%s&br=%s&rid=MUSIC_%s&type=convert_url&response=url' %
  31                 (file_format['ext'], file_format.get('br', ''), song_id),
  32                 song_id, note='Download %s url info' % file_format['format'],
  33             )
  34
  35             if song_url == 'IPDeny':
  36                 raise ExtractorError('This song is blocked in this region', expected=True)
  37
  38             if song_url.startswith('http://') or song_url.startswith('https://'):
  39                 formats.append({
  40                     'url': song_url,
  41                     'format_id': file_format['format'],
  42                     'format': file_format['format'],
  43                     'preference': file_format['preference'],
  44                     'abr': file_format.get('abr'),
  45                 })
  46         self._sort_formats(formats)
  47         return formats
  48
  49
  50 class KuwoIE(KuwoBaseIE):
  51     IE_NAME = 'kuwo:song'
  52     IE_DESC = '酷我音乐'
  53     _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P<id>\d+?)/'
  54     _TESTS = [{
  55         'url': 'http://www.kuwo.cn/yinyue/635632/',
  56         'info_dict': {
  57             'id': '635632',
  58             'ext': 'ape',
  59             'title': '爱我别走',
  60             'creator': '张震岳',
  61             'upload_date': '20080122',
  62             'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c'
  63         },
  64         'skip': 'this song has been offline because of copyright issues',
  65     }, {
  66         'url': 'http://www.kuwo.cn/yinyue/6446136/',
  67         'info_dict': {
  68             'id': '6446136',
  69             'ext': 'mp3',
  70             'title': '心',
  71             'creator': 'IU',
  72             'upload_date': '20150518',
  73         },
  74         'params': {
  75             'format': 'mp3-320'
  76         },
  77     }]
  78
  79     def _real_extract(self, url):
  80         song_id = self._match_id(url)
  81         webpage = self._download_webpage(
  82             url, song_id, note='Download song detail info',
  83             errnote='Unable to get song detail info')
  84         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:
  85             raise ExtractorError('this song has been offline because of copyright issues', expected=True)
  86
  87         song_name = self._html_search_regex(
  88             r'(?s)class="(?:[^"\s]+\s+)*title(?:\s+[^"\s]+)*".*?<h1[^>]+title="([^"]+)"', webpage, 'song name')
  89         singer_name = self._html_search_regex(
  90             r'<div[^>]+class="s_img">\s*<a[^>]+title="([^>]+)"',
  91             webpage, 'singer name', fatal=False)
  92         lrc_content = clean_html(get_element_by_id('lrcContent', webpage))
  93         if lrc_content == '暂无':     # indicates no lyrics
  94             lrc_content = None
  95
  96         formats = self._get_formats(song_id)
  97
  98         album_id = self._html_search_regex(
  99             r'<p[^>]+class="album"[^<]+<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
 100             webpage, 'album id', fatal=False)
 101
 102         publish_time = None
 103         if album_id is not None:
 104             album_info_page = self._download_webpage(
 105                 'http://www.kuwo.cn/album/%s/' % album_id, song_id,
 106                 note='Download album detail info',
 107                 errnote='Unable to get album detail info')
 108
 109             publish_time = self._html_search_regex(
 110                 r'发行时间：(\d{4}-\d{2}-\d{2})', album_info_page,
 111                 'publish time', fatal=False)
 112             if publish_time:
 113                 publish_time = publish_time.replace('-', '')
 114
 115         return {
 116             'id': song_id,
 117             'title': song_name,
 118             'creator': singer_name,
 119             'upload_date': publish_time,
 120             'description': lrc_content,
 121             'formats': formats,
 122         }
 123
 124
 125 class KuwoAlbumIE(InfoExtractor):
 126     IE_NAME = 'kuwo:album'
 127     IE_DESC = '酷我音乐 - 专辑'
 128     _VALID_URL = r'http://www\.kuwo\.cn/album/(?P<id>\d+?)/'
 129     _TEST = {
 130         'url': 'http://www.kuwo.cn/album/502294/',
 131         'info_dict': {
 132             'id': '502294',
 133             'title': 'M',
 134             'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c',
 135         },
 136         'playlist_count': 2,
 137     }
 138
 139     def _real_extract(self, url):
 140         album_id = self._match_id(url)
 141
 142         webpage = self._download_webpage(
 143             url, album_id, note='Download album info',
 144             errnote='Unable to get album info')
 145
 146         album_name = self._html_search_regex(
 147             r'<div[^>]+class="comm"[^<]+<h1[^>]+title="([^"]+)"', webpage,
 148             'album name')
 149         album_intro = remove_start(
 150             clean_html(get_element_by_id('intro', webpage)),
 151             '%s简介：' % album_name)
 152
 153         entries = [
 154             self.url_result(song_url, 'Kuwo') for song_url in re.findall(
 155                 r'<p[^>]+class="listen"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"',
 156                 webpage)
 157         ]
 158         return self.playlist_result(entries, album_id, album_name, album_intro)
 159
 160
 161 class KuwoChartIE(InfoExtractor):
 162     IE_NAME = 'kuwo:chart'
 163     IE_DESC = '酷我音乐 - 排行榜'
 164     _VALID_URL = r'http://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
 165     _TEST = {
 166         'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
 167         'info_dict': {
 168             'id': '香港中文龙虎榜',
 169             'title': '香港中文龙虎榜',
 170             'description': 're:\d{4}第\d{2}期',
 171         },
 172         'playlist_mincount': 10,
 173     }
 174
 175     def _real_extract(self, url):
 176         chart_id = self._match_id(url)
 177         webpage = self._download_webpage(
 178             url, chart_id, note='Download chart info',
 179             errnote='Unable to get chart info')
 180
 181         chart_name = self._html_search_regex(
 182             r'<h1[^>]+class="unDis">([^<]+)</h1>', webpage, 'chart name')
 183
 184         chart_desc = self._html_search_regex(
 185             r'<p[^>]+class="tabDef">(\d{4}第\d{2}期)</p>', webpage, 'chart desc')
 186
 187         entries = [
 188             self.url_result(song_url, 'Kuwo') for song_url in re.findall(
 189                 r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/"', webpage)
 190         ]
 191         return self.playlist_result(entries, chart_id, chart_name, chart_desc)
 192
 193
 194 class KuwoSingerIE(InfoExtractor):
 195     IE_NAME = 'kuwo:singer'
 196     IE_DESC = '酷我音乐 - 歌手'
 197     _VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
 198     _TESTS = [{
 199         'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
 200         'info_dict': {
 201             'id': 'bruno+mars',
 202             'title': 'Bruno Mars',
 203         },
 204         'playlist_count': 10,
 205     }, {
 206         'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
 207         'info_dict': {
 208             'id': 'Ali',
 209             'title': 'Ali',
 210         },
 211         'playlist_mincount': 95,
 212         'skip': 'Regularly stalls travis build',  # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540
 213     }]
 214
 215     def _real_extract(self, url):
 216         singer_id = self._match_id(url)
 217         webpage = self._download_webpage(
 218             url, singer_id, note='Download singer info',
 219             errnote='Unable to get singer info')
 220
 221         singer_name = self._html_search_regex(
 222             r'<div class="title clearfix">\s*<h1>([^<]+)<span', webpage, 'singer name'
 223         )
 224
 225         entries = []
 226         first_page_only = False if re.search(r'/music(?:_\d+)?\.htm', url) else True
 227         for page_num in itertools.count(1):
 228             webpage = self._download_webpage(
 229                 'http://www.kuwo.cn/mingxing/%s/music_%d.htm' % (singer_id, page_num),
 230                 singer_id, note='Download song list page #%d' % page_num,
 231                 errnote='Unable to get song list page #%d' % page_num)
 232
 233             entries.extend([
 234                 self.url_result(song_url, 'Kuwo') for song_url in re.findall(
 235                     r'<p[^>]+class="m_name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/',
 236                     webpage)
 237             ][:10 if first_page_only else None])
 238
 239             if first_page_only or not re.search(r'<a[^>]+href="[^"]+">下一页</a>', webpage):
 240                 break
 241
 242         return self.playlist_result(entries, singer_id, singer_name)
 243
 244
 245 class KuwoCategoryIE(InfoExtractor):
 246     IE_NAME = 'kuwo:category'
 247     IE_DESC = '酷我音乐 - 分类'
 248     _VALID_URL = r'http://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
 249     _TEST = {
 250         'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
 251         'info_dict': {
 252             'id': '86375',
 253             'title': '八十年代精选',
 254             'description': '这些都是属于八十年代的回忆！',
 255         },
 256         'playlist_count': 30,
 257     }
 258
 259     def _real_extract(self, url):
 260         category_id = self._match_id(url)
 261         webpage = self._download_webpage(
 262             url, category_id, note='Download category info',
 263             errnote='Unable to get category info')
 264
 265         category_name = self._html_search_regex(
 266             r'<h1[^>]+title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name')
 267
 268         category_desc = remove_start(
 269             get_element_by_id('intro', webpage).strip(),
 270             '%s简介：' % category_name)
 271
 272         jsonm = self._parse_json(self._html_search_regex(
 273             r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)
 274
 275         entries = [
 276             self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo')
 277             for song in jsonm['musiclist']
 278         ]
 279         return self.playlist_result(entries, category_id, category_name, category_desc)
 280
 281
 282 class KuwoMvIE(KuwoBaseIE):
 283     IE_NAME = 'kuwo:mv'
 284     IE_DESC = '酷我音乐 - MV'
 285     _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
 286     _TEST = {
 287         'url': 'http://www.kuwo.cn/mv/6480076/',
 288         'info_dict': {
 289             'id': '6480076',
 290             'ext': 'mkv',
 291             'title': '我们家MV',
 292             'creator': '2PM',
 293         },
 294     }
 295     _FORMATS = KuwoBaseIE._FORMATS + [
 296         {'format': 'mkv', 'ext': 'mkv', 'preference': 250},
 297         {'format': 'mp4', 'ext': 'mp4', 'preference': 200},
 298     ]
 299
 300     def _real_extract(self, url):
 301         song_id = self._match_id(url)
 302         webpage = self._download_webpage(
 303             url, song_id, note='Download mv detail info: %s' % song_id,
 304             errnote='Unable to get mv detail info: %s' % song_id)
 305
 306         mobj = re.search(
 307             r'<h1[^>]+title="(?P<song>[^"]+)">[^<]+<span[^>]+title="(?P<singer>[^"]+)"',
 308             webpage)
 309         if mobj:
 310             song_name = mobj.group('song')
 311             singer_name = mobj.group('singer')
 312         else:
 313             raise ExtractorError('Unable to find song or singer names')
 314
 315         formats = self._get_formats(song_id)
 316
 317         return {
 318             'id': song_id,
 319             'title': song_name,
 320             'creator': singer_name,
 321             'formats': formats,
 322         }