2 from __future__ import unicode_literals
7 from .common import InfoExtractor
16 class KuwoBaseIE(InfoExtractor):
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}
26 def _get_formats(self, song_id):
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'],
34 if song_url.startswith('http://') or song_url.startswith('https://'):
37 'format_id': file_format['format'],
38 'format': file_format['format'],
39 'preference': file_format['preference'],
40 'abr': file_format.get('abr'),
42 self._sort_formats(formats)
46 class KuwoIE(KuwoBaseIE):
49 _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P<id>\d+?)/'
51 'url': 'http://www.kuwo.cn/yinyue/635632/',
57 'upload_date': '20080122',
58 'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c'
61 'url': 'http://www.kuwo.cn/yinyue/6446136/',
67 'upload_date': '20150518',
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')
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
89 formats = self._get_formats(song_id)
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)
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')
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)
106 publish_time = publish_time.replace('-', '')
111 'creator': singer_name,
112 'upload_date': publish_time,
113 'description': lrc_content,
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+?)/'
123 'url': 'http://www.kuwo.cn/album/502294/',
127 'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c',
132 def _real_extract(self, url):
133 album_id = self._match_id(url)
135 webpage = self._download_webpage(
136 url, album_id, note='Download album info',
137 errnote='Unable to get album info')
139 album_name = self._html_search_regex(
140 r'<div[^>]+class="comm"[^<]+<h1[^>]+title="([^"]+)"', webpage,
142 album_intro = remove_start(
143 clean_html(get_element_by_id('intro', webpage)),
144 '%s简介:' % album_name)
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+/)"',
151 return self.playlist_result(entries, album_id, album_name, album_intro)
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'
159 'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
163 'description': 're:\d{4}第\d{2}期',
165 'playlist_mincount': 10,
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')
174 chart_name = self._html_search_regex(
175 r'<h1[^>]+class="unDis">([^<]+)</h1>', webpage, 'chart name')
177 chart_desc = self._html_search_regex(
178 r'<p[^>]+class="tabDef">(\d{4}第\d{2}期)</p>', webpage, 'chart desc')
181 self.url_result(song_url, 'Kuwo') for song_url in re.findall(
182 r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/"', webpage)
184 return self.playlist_result(entries, chart_id, chart_name, chart_desc)
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>[^/]+)'
192 'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
195 'title': 'Bruno Mars',
197 'playlist_count': 10,
199 'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
204 'playlist_mincount': 95,
205 'skip': 'Regularly stalls travis build', # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540
208 def _real_extract(self, url):
209 singer_id = self._match_id(url)
210 webpage = self._download_webpage(
211 url, singer_id, note='Download singer info',
212 errnote='Unable to get singer info')
214 singer_name = self._html_search_regex(
215 r'<div class="title clearfix">\s*<h1>([^<]+)<span', webpage, 'singer name'
219 first_page_only = False if re.search(r'/music(?:_\d+)?\.htm', url) else True
220 for page_num in itertools.count(1):
221 webpage = self._download_webpage(
222 'http://www.kuwo.cn/mingxing/%s/music_%d.htm' % (singer_id, page_num),
223 singer_id, note='Download song list page #%d' % page_num,
224 errnote='Unable to get song list page #%d' % page_num)
227 self.url_result(song_url, 'Kuwo') for song_url in re.findall(
228 r'<p[^>]+class="m_name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/',
230 ][:10 if first_page_only else None])
232 if first_page_only or not re.search(r'<a[^>]+href="[^"]+">下一页</a>', webpage):
235 return self.playlist_result(entries, singer_id, singer_name)
238 class KuwoCategoryIE(InfoExtractor):
239 IE_NAME = 'kuwo:category'
240 IE_DESC = '酷我音乐 - 分类'
241 _VALID_URL = r'http://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
243 'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
247 'description': '这些都是属于八十年代的回忆!',
249 'playlist_count': 30,
252 def _real_extract(self, url):
253 category_id = self._match_id(url)
254 webpage = self._download_webpage(
255 url, category_id, note='Download category info',
256 errnote='Unable to get category info')
258 category_name = self._html_search_regex(
259 r'<h1[^>]+title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name')
261 category_desc = remove_start(
262 get_element_by_id('intro', webpage).strip(),
263 '%s简介:' % category_name)
265 jsonm = self._parse_json(self._html_search_regex(
266 r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)
269 self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo')
270 for song in jsonm['musiclist']
272 return self.playlist_result(entries, category_id, category_name, category_desc)
275 class KuwoMvIE(KuwoBaseIE):
277 IE_DESC = '酷我音乐 - MV'
278 _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
280 'url': 'http://www.kuwo.cn/mv/6480076/',
288 _FORMATS = KuwoBaseIE._FORMATS + [
289 {'format': 'mkv', 'ext': 'mkv', 'preference': 250},
290 {'format': 'mp4', 'ext': 'mp4', 'preference': 200},
293 def _real_extract(self, url):
294 song_id = self._match_id(url)
295 webpage = self._download_webpage(
296 url, song_id, note='Download mv detail info: %s' % song_id,
297 errnote='Unable to get mv detail info: %s' % song_id)
300 r'<h1[^>]+title="(?P<song>[^"]+)">[^<]+<span[^>]+title="(?P<singer>[^"]+)"',
303 song_name = mobj.group('song')
304 singer_name = mobj.group('singer')
306 raise ExtractorError('Unable to find song or singer names')
308 formats = self._get_formats(song_id)
313 'creator': singer_name,