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