2 from __future__ import unicode_literals
8 from .common import InfoExtractor
14 from ..compat import compat_urllib_request
17 class QQMusicIE(InfoExtractor):
19 _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
21 'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
22 'md5': 'bed90b6db2a7a7a7e11bc585f471f63a',
24 'id': '004295Et37taLD',
27 'upload_date': '20141227',
29 'description': 'md5:d327722d0361576fde558f1ac68a7065',
33 # Reference: m_r_GetRUin() in top_player.js
34 # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
37 curMs = int(time.time() * 1000) % 1000
38 return int(round(random.random() * 2147483647) * curMs % 1E10)
40 def _real_extract(self, url):
41 mid = self._match_id(url)
43 detail_info_page = self._download_webpage(
44 'http://s.plcloud.music.qq.com/fcgi-bin/fcg_yqq_song_detail_info.fcg?songmid=%s&play=0' % mid,
45 mid, note='Download song detail info',
46 errnote='Unable to get song detail info', encoding='gbk')
48 song_name = self._html_search_regex(
49 r"songname:\s*'([^']+)'", detail_info_page, 'song name')
51 publish_time = self._html_search_regex(
52 r'发行时间:(\d{4}-\d{2}-\d{2})', detail_info_page,
53 'publish time', default=None)
55 publish_time = publish_time.replace('-', '')
57 singer = self._html_search_regex(
58 r"singer:\s*'([^']+)", detail_info_page, 'singer', default=None)
60 lrc_content = self._html_search_regex(
61 r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>',
62 detail_info_page, 'LRC lyrics', default=None)
64 lrc_content = lrc_content.replace('\\n', '\n')
66 guid = self.m_r_get_ruin()
68 vkey = self._download_json(
69 'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid,
70 mid, note='Retrieve vkey', errnote='Unable to get vkey',
71 transform_source=strip_jsonp)['key']
72 song_url = 'http://cc.stream.qqmusic.qq.com/C200%s.m4a?vkey=%s&guid=%s&fromtag=0' % (mid, vkey, guid)
78 'upload_date': publish_time,
80 'description': lrc_content,
84 class QQPlaylistBaseIE(InfoExtractor):
86 def qq_static_url(category, mid):
87 return 'http://y.qq.com/y/static/%s/%s/%s/%s.html' % (category, mid[-2], mid[-1], mid)
90 def get_entries_from_page(cls, page):
93 for item in re.findall(r'class="data"[^<>]*>([^<>]+)</', page):
94 song_mid = unescapeHTML(item).split('|')[-5]
95 entries.append(cls.url_result(
96 'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
102 class QQMusicSingerIE(QQPlaylistBaseIE):
103 IE_NAME = 'qqmusic:singer'
104 _VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
106 'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
108 'id': '001BLpXF2DyJe2',
110 'description': 'md5:2a222d89ba4455a3af19940c0481bb78',
112 'playlist_count': 12,
115 def _real_extract(self, url):
116 mid = self._match_id(url)
118 singer_page = self._download_webpage(
119 self.qq_static_url('singer', mid), mid, 'Download singer page')
121 entries = self.get_entries_from_page(singer_page)
123 singer_name = self._html_search_regex(
124 r"singername\s*:\s*'([^']+)'", singer_page, 'singer name',
127 singer_id = self._html_search_regex(
128 r"singerid\s*:\s*'([0-9]+)'", singer_page, 'singer id',
134 req = compat_urllib_request.Request(
135 'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg?utf8=1&outCharset=utf-8&format=xml&singerid=%s' % singer_id)
137 'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html')
138 singer_desc_page = self._download_xml(
139 req, mid, 'Donwload singer description XML')
141 singer_desc = singer_desc_page.find('./data/info/desc').text
143 return self.playlist_result(entries, mid, singer_name, singer_desc)
146 class QQMusicAlbumIE(QQPlaylistBaseIE):
147 IE_NAME = 'qqmusic:album'
148 _VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
151 'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1&play=0',
153 'id': '000gXCTb2AhRR1',
154 'title': '我们都是这样长大的',
155 'description': 'md5:d216c55a2d4b3537fe4415b8767d74d6',
160 def _real_extract(self, url):
161 mid = self._match_id(url)
163 album_page = self._download_webpage(
164 self.qq_static_url('album', mid), mid, 'Download album page')
166 entries = self.get_entries_from_page(album_page)
168 album_name = self._html_search_regex(
169 r"albumname\s*:\s*'([^']+)',", album_page, 'album name',
172 album_detail = self._html_search_regex(
173 r'<div class="album_detail close_detail">\s*<p>((?:[^<>]+(?:<br />)?)+)</p>',
174 album_page, 'album details', default=None)
176 return self.playlist_result(entries, mid, album_name, album_detail)
179 class QQMusicToplistIE(QQPlaylistBaseIE):
180 IE_NAME = 'qqmusic:toplist'
181 _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
184 'url': 'http://y.qq.com/#type=toplist&p=global_12',
189 'playlist_count': 10,
191 'url': 'http://y.qq.com/#type=toplist&p=top_6',
194 'title': 'QQ音乐巅峰榜·欧美',
196 'playlist_count': 100,
198 'url': 'http://y.qq.com/#type=toplist&p=global_5',
201 'title': '韩国mnet排行榜',
203 'playlist_count': 50,
207 def strip_qq_jsonp(code):
208 return js_to_json(re.sub(r'^MusicJsonCallback\((.*?)\)/\*.+?\*/$', r'\1', code))
210 def _real_extract(self, url):
211 list_id = self._match_id(url)
213 list_type, num_id = list_id.split("_")
215 list_page = self._download_webpage(
216 "http://y.qq.com/y/static/toplist/index/%s.html" % list_id,
217 list_id, 'Download toplist page')
220 if list_type == 'top':
221 jsonp_url = "http://y.qq.com/y/static/toplist/json/top/%s/1.js" % num_id
223 jsonp_url = "http://y.qq.com/y/static/toplist/json/global/%s/1_1.js" % num_id
225 toplist_json = self._download_json(
226 jsonp_url, list_id, note='Retrieve toplist json',
227 errnote='Unable to get toplist json', transform_source=self.strip_qq_jsonp)
229 for song in toplist_json['l']:
231 song_mid = s.split("|")[20]
232 entries.append(self.url_result(
233 'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
236 list_name = self._html_search_regex(
237 r'<h2 id="top_name">([^\']+)</h2>', list_page, 'top list name',
240 return self.playlist_result(entries, list_id, list_name)