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