2 from __future__ import unicode_literals
8 from .common import InfoExtractor
14 from ..compat import compat_urllib_request
17 class QQMusicIE(InfoExtractor):
18 _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
20 'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
21 'md5': 'bed90b6db2a7a7a7e11bc585f471f63a',
23 'id': '004295Et37taLD',
26 'upload_date': '20141227',
28 'description': 'md5:4348ff1dd24036906baa7b6f973f8d30',
32 # Reference: m_r_GetRUin() in top_player.js
33 # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
36 curMs = int(time.time() * 1000) % 1000
37 return int(round(random.random() * 2147483647) * curMs % 1E10)
39 def _real_extract(self, url):
40 mid = self._match_id(url)
42 detail_info_page = self._download_webpage(
43 'http://s.plcloud.music.qq.com/fcgi-bin/fcg_yqq_song_detail_info.fcg?songmid=%s&play=0' % mid,
44 mid, note='Download song detail info',
45 errnote='Unable to get song detail info', encoding='gbk')
47 song_name = self._html_search_regex(
48 r"songname:\s*'([^']+)'", detail_info_page, 'song name')
50 publish_time = self._html_search_regex(
51 r'发行时间:(\d{4}-\d{2}-\d{2})', detail_info_page,
52 'publish time', default=None)
54 publish_time = publish_time.replace('-', '')
56 singer = self._html_search_regex(
57 r"singer:\s*'([^']+)", detail_info_page, 'singer', default=None)
59 lrc_content = self._html_search_regex(
60 r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>',
61 detail_info_page, 'LRC lyrics', default=None)
63 guid = self.m_r_get_ruin()
65 vkey = self._download_json(
66 'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid,
67 mid, note='Retrieve vkey', errnote='Unable to get vkey',
68 transform_source=strip_jsonp)['key']
69 song_url = 'http://cc.stream.qqmusic.qq.com/C200%s.m4a?vkey=%s&guid=%s&fromtag=0' % (mid, vkey, guid)
75 'upload_date': publish_time,
77 'description': lrc_content,
81 class QQPlaylistBaseIE(InfoExtractor):
83 def qq_static_url(category, mid):
84 return 'http://y.qq.com/y/static/%s/%s/%s/%s.html' % (category, mid[-2], mid[-1], mid)
87 def get_entries_from_page(cls, page):
90 for item in re.findall(r'class="data"[^<>]*>([^<>]+)</', page):
91 song_mid = unescapeHTML(item).split('|')[-5]
92 entries.append(cls.url_result(
93 'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
99 class QQMusicSingerIE(QQPlaylistBaseIE):
100 _VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
102 'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
104 'id': '001BLpXF2DyJe2',
106 'description': 'md5:2a222d89ba4455a3af19940c0481bb78',
108 'playlist_count': 12,
111 def _real_extract(self, url):
112 mid = self._match_id(url)
114 singer_page = self._download_webpage(
115 self.qq_static_url('singer', mid), mid, 'Download singer page')
117 entries = self.get_entries_from_page(singer_page)
119 singer_name = self._html_search_regex(
120 r"singername\s*:\s*'([^']+)'", singer_page, 'singer name',
123 singer_id = self._html_search_regex(
124 r"singerid\s*:\s*'([0-9]+)'", singer_page, 'singer id',
130 req = compat_urllib_request.Request(
131 'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg?utf8=1&outCharset=utf-8&format=xml&singerid=%s' % singer_id)
133 'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html')
134 singer_desc_page = self._download_xml(
135 req, mid, 'Donwload singer description XML')
137 singer_desc = singer_desc_page.find('./data/info/desc').text
139 return self.playlist_result(entries, mid, singer_name, singer_desc)
142 class QQMusicAlbumIE(QQPlaylistBaseIE):
143 _VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
146 'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1&play=0',
148 'id': '000gXCTb2AhRR1',
149 'title': '我们都是这样长大的',
150 'description': 'md5:d216c55a2d4b3537fe4415b8767d74d6',
155 def _real_extract(self, url):
156 mid = self._match_id(url)
158 album_page = self._download_webpage(
159 self.qq_static_url('album', mid), mid, 'Download album page')
161 entries = self.get_entries_from_page(album_page)
163 album_name = self._html_search_regex(
164 r"albumname\s*:\s*'([^']+)',", album_page, 'album name',
167 album_detail = self._html_search_regex(
168 r'<div class="album_detail close_detail">\s*<p>((?:[^<>]+(?:<br />)?)+)</p>',
169 album_page, 'album details', default=None)
171 return self.playlist_result(entries, mid, album_name, album_detail)
174 class QQMusicToplistIE(QQPlaylistBaseIE):
175 _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
178 'url': 'http://y.qq.com/#type=toplist&p=global_12',
183 'playlist_count': 10,
185 'url': 'http://y.qq.com/#type=toplist&p=top_6',
188 'title': 'QQ音乐巅峰榜·欧美',
190 'playlist_count': 100,
194 def strip_qq_jsonp(code):
195 return js_to_json(re.sub(r'^MusicJsonCallback\((.*?)\)/\*.+?\*/$', r'\1', code))
197 def _real_extract(self, url):
198 list_id = self._match_id(url)
200 list_type = list_id.split("_")[0]
201 num_id = list_id.split("_")[1]
203 list_page = self._download_webpage("http://y.qq.com/y/static/toplist/index/%s.html" % list_id, list_id, 'Download toplist page')
205 if list_type == 'top':
206 list = self._download_json(
207 "http://y.qq.com/y/static/toplist/json/top/%s/1.js" % num_id,
208 list_id, note='Retrieve toplist json', errnote='Unable to get toplist json', transform_source=self.strip_qq_jsonp)
210 for song in list['l']:
212 song_mid = s.split("|")[20]
213 entries.append(self.url_result(
214 'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
217 elif list_type == 'global':
218 entries = self.get_entries_from_page(list_page)
220 list_name = self._html_search_regex(
221 r'<h2 id="top_name">([^\']+)</h2>', list_page, 'top list name',
225 return self.playlist_result(entries, list_id, list_name, list_desc)