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': '9ce1c1c8445f561506d2e3cfb0255705',
24 'id': '004295Et37taLD',
27 'upload_date': '20141227',
29 'description': 'md5:d327722d0361576fde558f1ac68a7065',
34 'mp3-320': {'prefix': 'M800', 'ext': 'mp3', 'preference': 40, 'abr': 320}
,
35 'mp3-128': {'prefix': 'M500', 'ext': 'mp3', 'preference': 30, 'abr': 128}
,
36 'm4a': {'prefix': 'C200', 'ext': 'm4a', 'preference': 10}
39 # Reference: m_r_GetRUin() in top_player.js
40 # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
43 curMs
= int(time
.time() * 1000) % 1000
44 return int(round(random
.random() * 2147483647) * curMs
% 1E10
)
46 def _real_extract(self
, url
):
47 mid
= self
._match
_id
(url
)
49 detail_info_page
= self
._download
_webpage
(
50 'http://s.plcloud.music.qq.com/fcgi-bin/fcg_yqq_song_detail_info.fcg?songmid=%s&play=0' % mid
,
51 mid
, note
='Download song detail info',
52 errnote
='Unable to get song detail info', encoding
='gbk')
54 song_name
= self
._html
_search
_regex
(
55 r
"songname:\s*'([^']+)'", detail_info_page
, 'song name')
57 publish_time
= self
._html
_search
_regex
(
58 r
'发行时间:(\d{4}-\d{2}-\d{2})', detail_info_page
,
59 'publish time', default
=None)
61 publish_time
= publish_time
.replace('-', '')
63 singer
= self
._html
_search
_regex
(
64 r
"singer:\s*'([^']+)", detail_info_page
, 'singer', default
=None)
66 lrc_content
= self
._html
_search
_regex
(
67 r
'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>',
68 detail_info_page
, 'LRC lyrics', default
=None)
70 lrc_content
= lrc_content
.replace('\\n', '\n')
72 guid
= self
.m_r_get_ruin()
74 vkey
= self
._download
_json
(
75 'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid
,
76 mid
, note
='Retrieve vkey', errnote
='Unable to get vkey',
77 transform_source
=strip_jsonp
)['key']
80 for format_id
, details
in self
._FORMATS
.items():
82 'url': 'http://cc.stream.qqmusic.qq.com/%s%s.%s?vkey=%s&guid=%s&fromtag=0'
83 % (details
['prefix'], mid
, details
['ext'], vkey
, guid
),
85 'format_id': format_id
,
86 'preference': details
['preference'],
87 'abr': details
.get('abr'),
89 self
._sort
_formats
(formats
)
95 'upload_date': publish_time
,
97 'description': lrc_content
,
101 class QQPlaylistBaseIE(InfoExtractor
):
103 def qq_static_url(category
, mid
):
104 return 'http://y.qq.com/y/static/%s/%s/%s/%s.html' % (category
, mid
[-2], mid
[-1], mid
)
107 def get_entries_from_page(cls
, page
):
110 for item
in re
.findall(r
'class="data"[^<>]*>([^<>]+)</', page
):
111 song_mid
= unescapeHTML(item
).split('|')[-5]
112 entries
.append(cls
.url_result(
113 'http://y.qq.com/#type=song&mid=' + song_mid
, 'QQMusic',
119 class QQMusicSingerIE(QQPlaylistBaseIE
):
120 IE_NAME
= 'qqmusic:singer'
121 _VALID_URL
= r
'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
123 'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
125 'id': '001BLpXF2DyJe2',
127 'description': 'md5:2a222d89ba4455a3af19940c0481bb78',
129 'playlist_count': 12,
132 def _real_extract(self
, url
):
133 mid
= self
._match
_id
(url
)
135 singer_page
= self
._download
_webpage
(
136 self
.qq_static_url('singer', mid
), mid
, 'Download singer page')
138 entries
= self
.get_entries_from_page(singer_page
)
140 singer_name
= self
._html
_search
_regex
(
141 r
"singername\s*:\s*'([^']+)'", singer_page
, 'singer name',
144 singer_id
= self
._html
_search
_regex
(
145 r
"singerid\s*:\s*'([0-9]+)'", singer_page
, 'singer id',
151 req
= compat_urllib_request
.Request(
152 'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg?utf8=1&outCharset=utf-8&format=xml&singerid=%s' % singer_id
)
154 'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html')
155 singer_desc_page
= self
._download
_xml
(
156 req
, mid
, 'Donwload singer description XML')
158 singer_desc
= singer_desc_page
.find('./data/info/desc').text
160 return self
.playlist_result(entries
, mid
, singer_name
, singer_desc
)
163 class QQMusicAlbumIE(QQPlaylistBaseIE
):
164 IE_NAME
= 'qqmusic:album'
165 _VALID_URL
= r
'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
168 'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1&play=0',
170 'id': '000gXCTb2AhRR1',
171 'title': '我们都是这样长大的',
172 'description': 'md5:d216c55a2d4b3537fe4415b8767d74d6',
177 def _real_extract(self
, url
):
178 mid
= self
._match
_id
(url
)
180 album_page
= self
._download
_webpage
(
181 self
.qq_static_url('album', mid
), mid
, 'Download album page')
183 entries
= self
.get_entries_from_page(album_page
)
185 album_name
= self
._html
_search
_regex
(
186 r
"albumname\s*:\s*'([^']+)',", album_page
, 'album name',
189 album_detail
= self
._html
_search
_regex
(
190 r
'<div class="album_detail close_detail">\s*<p>((?:[^<>]+(?:<br />)?)+)</p>',
191 album_page
, 'album details', default
=None)
193 return self
.playlist_result(entries
, mid
, album_name
, album_detail
)
196 class QQMusicToplistIE(QQPlaylistBaseIE
):
197 IE_NAME
= 'qqmusic:toplist'
198 _VALID_URL
= r
'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
201 'url': 'http://y.qq.com/#type=toplist&p=global_123',
204 'title': '美国iTunes榜',
206 'playlist_count': 10,
208 'url': 'http://y.qq.com/#type=toplist&p=top_3',
211 'title': 'QQ音乐巅峰榜·欧美',
212 'description': 'QQ音乐巅峰榜·欧美根据用户收听行为自动生成,集结当下最流行的欧美新歌!:更新时间:每周四22点|统'
213 '计周期:一周(上周四至本周三)|统计对象:三个月内发行的欧美歌曲|统计数量:100首|统计算法:根据'
214 '歌曲在一周内的有效播放次数,由高到低取前100名(同一歌手最多允许5首歌曲同时上榜)|有效播放次数:'
215 '登录用户完整播放一首歌曲,记为一次有效播放;同一用户收听同一首歌曲,每天记录为1次有效播放'
217 'playlist_count': 100,
219 'url': 'http://y.qq.com/#type=toplist&p=global_106',
224 'playlist_count': 50,
227 def _real_extract(self
, url
):
228 list_id
= self
._match
_id
(url
)
230 list_type
, num_id
= list_id
.split("_")
232 toplist_json
= self
._download
_json
(
233 'http://i.y.qq.com/v8/fcg-bin/fcg_v8_toplist_cp.fcg?type=%s&topid=%s&format=json'
234 % (list_type
, num_id
),
235 list_id
, 'Download toplist page')
239 'http://y.qq.com/#type=song&mid=' + song
['data']['songmid'], 'QQMusic', song
['data']['songmid']
240 ) for song
in toplist_json
['songlist']
243 topinfo
= toplist_json
.get('topinfo', {})
244 list_name
= topinfo
.get('ListName')
245 list_description
= topinfo
.get('info')
246 return self
.playlist_result(entries
, list_id
, list_name
, list_description
)
249 class QQMusicPlaylistIE(QQPlaylistBaseIE
):
250 IE_NAME
= 'qqmusic:playlist'
251 _VALID_URL
= r
'http://y\.qq\.com/#type=taoge&id=(?P<id>[0-9]+)'
254 'url': 'http://y.qq.com/#type=taoge&id=3462654915',
257 'title': '韩国5月新歌精选下旬',
258 'description': 'md5:d2c9d758a96b9888cf4fe82f603121d4',
260 'playlist_count': 40,
263 def _real_extract(self
, url
):
264 list_id
= self
._match
_id
(url
)
266 list_json
= self
._download
_json
(
267 'http://i.y.qq.com/qzone-music/fcg-bin/fcg_ucc_getcdinfo_byids_cp.fcg?type=1&json=1&utf8=1&onlysong=0&disstid=%s'
268 % list_id
, list_id
, 'Download list page',
269 transform_source
=strip_jsonp
)['cdlist'][0]
273 'http://y.qq.com/#type=song&mid=' + song
['songmid'], 'QQMusic', song
['songmid']
274 ) for song
in list_json
['songlist']
277 list_name
= list_json
.get('dissname')
278 list_description
= clean_html(unescapeHTML(list_json
.get('desc')))
279 return self
.playlist_result(entries
, list_id
, list_name
, list_description
)