2 from __future__ import unicode_literals
7 from .common import InfoExtractor
16 class KuwoIE(InfoExtractor):
18 _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P<id>[0-9]+?)/'
20 'url': 'http://www.kuwo.cn/yinyue/635632/',
26 'upload_date': '20080122',
27 'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c'
30 'url': 'http://www.kuwo.cn/yinyue/6446136/',
36 'upload_date': '20150518',
43 {'format': 'ape', 'ext': 'ape', 'preference': 100},
44 {'format': 'mp3-320', 'ext': 'mp3', 'br': '320kmp3', 'abr': 320, 'preference': 80},
45 {'format': 'mp3-192', 'ext': 'mp3', 'br': '192kmp3', 'abr': 192, 'preference': 70},
46 {'format': 'mp3-128', 'ext': 'mp3', 'br': '128kmp3', 'abr': 128, 'preference': 60},
47 {'format': 'wma', 'ext': 'wma', 'preference': 20},
48 {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10}
51 def _get_formats(self, song_id):
53 for file_format in self._FORMATS:
54 song_url = self._download_webpage(
55 "http://antiserver.kuwo.cn/anti.s?format=%s&br=%s&rid=MUSIC_%s&type=convert_url&response=url" %
56 (file_format['ext'], file_format.get('br', ''), song_id),
57 song_id, note="Download %s url info" % file_format["format"],
59 if song_url.startswith('http://') or song_url.startswith('https://'):
62 'format_id': file_format['format'],
63 'format': file_format['format'],
64 'preference': file_format['preference'],
65 'abr': file_format.get('abr'),
67 self._sort_formats(formats)
70 def _real_extract(self, url):
71 song_id = self._match_id(url)
72 webpage = self._download_webpage(
73 url, song_id, note='Download song detail info',
74 errnote='Unable to get song detail info')
76 song_name = self._html_search_regex(
77 r'<h1[^>]+title="([^"]+)">', webpage, 'song name')
78 singer_name = self._html_search_regex(
79 r'<div[^>]+class="s_img">\s*<a[^>]+title="([^>]+)"',
80 webpage, 'singer name', default=None)
81 lrc_content = clean_html(get_element_by_id("lrcContent", webpage))
82 if lrc_content == '暂无': # indicates no lyrics
85 formats = self._get_formats(song_id)
87 album_id = self._html_search_regex(
88 r'<p[^>]+class="album"[^<]+<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
89 webpage, 'album id', default=None, fatal=False)
92 if album_id is not None:
93 album_info_page = self._download_webpage(
94 "http://www.kuwo.cn/album/%s/" % album_id, song_id,
95 note='Download album detail info',
96 errnote='Unable to get album detail info')
98 publish_time = self._html_search_regex(
99 r'发行时间:(\d{4}-\d{2}-\d{2})', album_info_page,
100 'publish time', default=None)
102 publish_time = publish_time.replace('-', '')
107 'creator': singer_name,
108 'upload_date': publish_time,
109 'description': lrc_content,
114 class KuwoAlbumIE(InfoExtractor):
115 IE_NAME = 'kuwo:album'
116 _VALID_URL = r'http://www\.kuwo\.cn/album/(?P<id>[0-9]+?)/'
118 'url': 'http://www.kuwo.cn/album/502294/',
122 'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c',
127 def _real_extract(self, url):
128 album_id = self._match_id(url)
130 webpage = self._download_webpage(
131 url, album_id, note='Download album info',
132 errnote='Unable to get album info')
134 album_name = self._html_search_regex(
135 r'<div[^>]+class="comm"[^<]+<h1[^>]+title="([^"]+)"', webpage,
137 album_intro = remove_start(
138 clean_html(get_element_by_id("intro", webpage)),
139 '%s简介:' % album_name)
142 self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id)
143 for song_id in re.findall(
144 r'<p[^>]+class="listen"><a[^>]+href="http://www\.kuwo\.cn/yinyue/(\d+)/"',
147 return self.playlist_result(entries, album_id, album_name, album_intro)
150 class KuwoChartIE(InfoExtractor):
151 IE_NAME = 'kuwo:chart'
152 _VALID_URL = r'http://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
154 'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
158 'description': 're:[0-9]{4}第[0-9]{2}期',
160 'playlist_mincount': 10,
163 def _real_extract(self, url):
164 chart_id = self._match_id(url)
165 webpage = self._download_webpage(
166 url, chart_id, note='Download chart info',
167 errnote='Unable to get chart info')
169 chart_name = self._html_search_regex(
170 r'<h1[^>]+class="unDis">([^<]+)</h1>', webpage, 'chart name')
172 chart_desc = self._html_search_regex(
173 r'<p[^>]+class="tabDef">(\d{4}第\d{2}期)</p>', webpage, 'chart desc')
176 self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id)
177 for song_id in re.findall(
178 r'<a[^>]+href="http://www\.kuwo\.cn/yinyue/(\d+)/"', webpage)
180 return self.playlist_result(entries, chart_id, chart_name, chart_desc)
183 class KuwoSingerIE(InfoExtractor):
184 IE_NAME = 'kuwo:singer'
185 _VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
187 'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
190 'title': 'Bruno Mars',
192 'playlist_count': 10,
194 'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
199 'playlist_mincount': 95,
202 def _real_extract(self, url):
203 singer_id = self._match_id(url)
204 webpage = self._download_webpage(
205 url, singer_id, note='Download singer info',
206 errnote='Unable to get singer info')
208 singer_name = self._html_search_regex(
209 r'<div class="title clearfix">\s*<h1>([^<]+)<span', webpage, 'singer name'
213 first_page_only = False if re.search(r'/music(?:_[0-9]+)?\.htm', url) else True
214 for page_num in itertools.count(1):
215 webpage = self._download_webpage(
216 'http://www.kuwo.cn/mingxing/%s/music_%d.htm' % (singer_id, page_num),
217 singer_id, note='Download song list page #%d' % page_num,
218 errnote='Unable to get song list page #%d' % page_num)
221 self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id)
222 for song_id in re.findall(
223 r'<p[^>]+class="m_name"><a[^>]+href="http://www\.kuwo\.cn/yinyue/([0-9]+)/',
225 ][:10 if first_page_only else None])
227 if first_page_only or not re.search(r'<a[^>]+href="[^"]+">下一页</a>', webpage):
230 return self.playlist_result(entries, singer_id, singer_name)
233 class KuwoCategoryIE(InfoExtractor):
234 IE_NAME = 'kuwo:category'
235 _VALID_URL = r'http://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>[0-9]+?).htm'
237 'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
241 'description': '这些都是属于八十年代的回忆!',
243 'playlist_count': 30,
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')
252 category_name = self._html_search_regex(
253 r'<h1[^>]+title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name')
255 category_desc = remove_start(
256 get_element_by_id("intro", webpage).strip(),
257 '%s简介:' % category_name)
259 jsonm = self._parse_json(self._html_search_regex(
260 r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)
264 "http://www.kuwo.cn/yinyue/%s/" % song['musicrid'],
265 'Kuwo', song['musicrid'])
266 for song in jsonm['musiclist']
268 return self.playlist_result(entries, category_id, category_name, category_desc)
271 class KuwoMvIE(KuwoIE):
273 _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P<id>[0-9]+?)/'
275 'url': 'http://www.kuwo.cn/mv/6480076/',
283 _FORMATS = KuwoIE._FORMATS + [
284 {'format': 'mkv', 'ext': 'mkv', 'preference': 250},
285 {'format': 'mp4', 'ext': 'mp4', 'preference': 200},
288 def _real_extract(self, url):
289 song_id = self._match_id(url)
290 webpage = self._download_webpage(
291 url, song_id, note='Download mv detail info: %s' % song_id,
292 errnote='Unable to get mv detail info: %s' % song_id)
295 r'<h1[^>]+title="(?P<song>[^"]+)">[^<]+<span[^>]+title="(?P<singer>[^"]+)"',
298 song_name = mobj.group('song')
299 singer_name = mobj.group('singer')
301 raise ExtractorError("Unable to find song or singer names")
303 formats = self._get_formats(song_id)
308 'creator': singer_name,