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