5 from .common
import InfoExtractor
14 class QQMusicIE(InfoExtractor
):
17 _VALID_URL
= r
'https?://y\.qq\.com/n/yqq/song/(?P<id>[0-9A-Za-z]+)\.html'
19 'url': 'https://y.qq.com/n/yqq/song/004295Et37taLD.html',
20 'md5': '5f1e6cea39e182857da7ffc5ef5e6bb8',
22 'id': '004295Et37taLD',
25 'release_date': '20141227',
27 'description': 'md5:d85afb3051952ecc50a1ee8a286d1eac',
28 'thumbnail': r
're:^https?://.*\.jpg$',
31 'note': 'There is no mp3-320 version of this song.',
32 'url': 'https://y.qq.com/n/yqq/song/004MsGEo3DdNxV.html',
33 'md5': 'fa3926f0c585cda0af8fa4f796482e3e',
35 'id': '004MsGEo3DdNxV',
38 'release_date': '20050626',
40 'description': 'md5:46857d5ed62bc4ba84607a805dccf437',
41 'thumbnail': r
're:^https?://.*\.jpg$',
44 'note': 'lyrics not in .lrc format',
45 'url': 'https://y.qq.com/n/yqq/song/001JyApY11tIp6.html',
47 'id': '001JyApY11tIp6',
49 'title': 'Shadows Over Transylvania',
50 'release_date': '19970225',
51 'creator': 'Dark Funeral',
52 'description': 'md5:c9b20210587cbcd6836a1c597bab4525',
53 'thumbnail': r
're:^https?://.*\.jpg$',
56 'skip_download': True,
61 'mp3-320': {'prefix': 'M800', 'ext': 'mp3', 'preference': 40, 'abr': 320}
,
62 'mp3-128': {'prefix': 'M500', 'ext': 'mp3', 'preference': 30, 'abr': 128}
,
63 'm4a': {'prefix': 'C200', 'ext': 'm4a', 'preference': 10}
66 # Reference: m_r_GetRUin() in top_player.js
67 # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
70 curMs
= int(time
.time() * 1000) % 1000
71 return int(round(random
.random() * 2147483647) * curMs
% 1E10
)
73 def _real_extract(self
, url
):
74 mid
= self
._match
_id
(url
)
76 detail_info_page
= self
._download
_webpage
(
77 'http://s.plcloud.music.qq.com/fcgi-bin/fcg_yqq_song_detail_info.fcg?songmid=%s&play=0' % mid
,
78 mid
, note
='Download song detail info',
79 errnote
='Unable to get song detail info', encoding
='gbk')
81 song_name
= self
._html
_search
_regex
(
82 r
"songname:\s*'([^']+)'", detail_info_page
, 'song name')
84 publish_time
= self
._html
_search
_regex
(
85 r
'发行时间:(\d{4}-\d{2}-\d{2})', detail_info_page
,
86 'publish time', default
=None)
88 publish_time
= publish_time
.replace('-', '')
90 singer
= self
._html
_search
_regex
(
91 r
"singer:\s*'([^']+)", detail_info_page
, 'singer', default
=None)
93 lrc_content
= self
._html
_search
_regex
(
94 r
'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>',
95 detail_info_page
, 'LRC lyrics', default
=None)
97 lrc_content
= lrc_content
.replace('\\n', '\n')
100 albummid
= self
._search
_regex
(
101 [r
'albummid:\'([0-9a
-zA
-Z
]+)\'', r'"albummid":"([0-9a-zA-Z]+)"'],
102 detail_info_page, 'album mid
', default=None)
104 thumbnail_url = 'http
://i
.gtimg
.cn
/music
/photo
/mid_album_500
/%s/%s/%s.jpg
' \
105 % (albummid[-2:-1], albummid[-1], albummid)
107 guid = self.m_r_get_ruin()
109 vkey = self._download_json(
110 'http
://base
.music
.qq
.com
/fcgi
-bin
/fcg_musicexpress
.fcg?json
=3&guid
=%s' % guid,
111 mid, note='Retrieve vkey
', errnote='Unable to get vkey
',
112 transform_source=strip_jsonp)['key
']
115 for format_id, details in self._FORMATS.items():
117 'url
': 'http
://cc
.stream
.qqmusic
.qq
.com
/%s%s.%s?vkey
=%s&guid
=%s&fromtag
=0'
118 % (details['prefix
'], mid, details['ext
'], vkey, guid),
120 'format_id
': format_id,
121 'quality
': details['preference
'],
122 'abr
': details.get('abr
'),
124 self._check_formats(formats, mid)
126 actual_lrc_lyrics = ''.join(
127 line + '\n' for line in re.findall(
128 r'(?m
)^
(\
[[0-9]{2}
:[0-9]{2}
(?
:\
.[0-9]{2,}
)?\
][^
\n]*|\
[[^\
]]*\
])', lrc_content))
134 'release_date
': publish_time,
136 'description
': lrc_content,
137 'thumbnail
': thumbnail_url
139 if actual_lrc_lyrics:
140 info_dict['subtitles
'] = {
143 'data
': actual_lrc_lyrics,
149 class QQPlaylistBaseIE(InfoExtractor):
151 def qq_static_url(category, mid):
152 return 'http
://y
.qq
.com
/y
/static
/%s/%s/%s/%s.html
' % (category, mid[-2], mid[-1], mid)
154 def get_singer_all_songs(self, singmid, num):
155 return self._download_webpage(
156 r'https
://c
.y
.qq
.com
/v8
/fcg
-bin
/fcg_v8_singer_track_cp
.fcg
', singmid,
160 'outCharset
': 'utf
-8',
163 'singermid
': singmid,
170 def get_entries_from_page(self, singmid):
174 json_text = self.get_singer_all_songs(singmid, default_num)
175 json_obj_all_songs = self._parse_json(json_text, singmid)
177 if json_obj_all_songs['code
'] == 0:
178 total = json_obj_all_songs['data
']['total
']
179 json_text = self.get_singer_all_songs(singmid, total)
180 json_obj_all_songs = self._parse_json(json_text, singmid)
182 for item in json_obj_all_songs['data
']['list']:
183 if item['musicData
'].get('songmid
') is not None:
184 songmid = item['musicData
']['songmid
']
185 entries.append(self.url_result(
186 r'https
://y
.qq
.com
/n
/yqq
/song
/%s.html
' % songmid, 'QQMusic
', songmid))
191 class QQMusicSingerIE(QQPlaylistBaseIE):
192 IE_NAME = 'qqmusic
:singer
'
193 IE_DESC = 'QQ音乐
- 歌手
'
194 _VALID_URL = r'https?
://y\
.qq\
.com
/n
/yqq
/singer
/(?P
<id>[0-9A
-Za
-z
]+)\
.html
'
196 'url
': 'https
://y
.qq
.com
/n
/yqq
/singer
/001BLpXF2DyJe2
.html
',
198 'id': '001BLpXF2DyJe2
',
200 'description
': 'md5
:870ec08f7d8547c29c93010899103751
',
202 'playlist_mincount
': 12,
205 def _real_extract(self, url):
206 mid = self._match_id(url)
208 entries = self.get_entries_from_page(mid)
209 singer_page = self._download_webpage(url, mid, 'Download singer page
')
210 singer_name = self._html_search_regex(
211 r"singername\s*:\s*'(.*?
)'", singer_page, 'singer name
', default=None)
215 singer_desc_page = self._download_xml(
216 'http
://s
.plcloud
.music
.qq
.com
/fcgi
-bin
/fcg_get_singer_desc
.fcg
', mid,
217 'Donwload singer description XML
',
218 query={'utf8': 1, 'outCharset': 'utf-8', 'format': 'xml', 'singermid': mid},
219 headers={'Referer': 'https://y.qq.com/n/yqq/singer/'})
221 singer_desc = singer_desc_page.find('./data
/info
/desc
').text
223 return self.playlist_result(entries, mid, singer_name, singer_desc)
226 class QQMusicAlbumIE(QQPlaylistBaseIE):
227 IE_NAME = 'qqmusic
:album
'
228 IE_DESC = 'QQ音乐
- 专辑
'
229 _VALID_URL = r'https?
://y\
.qq\
.com
/n
/yqq
/album
/(?P
<id>[0-9A
-Za
-z
]+)\
.html
'
232 'url
': 'https
://y
.qq
.com
/n
/yqq
/album
/000gXCTb2AhRR1
.html
',
234 'id': '000gXCTb2AhRR1
',
235 'title
': '我们都是这样长大的
',
236 'description
': 'md5
:179c5dce203a5931970d306aa9607ea6
',
240 'url
': 'https
://y
.qq
.com
/n
/yqq
/album
/002Y5a3b3AlCu3
.html
',
242 'id': '002Y5a3b3AlCu3
',
244 'description
': 'md5
:a48823755615508a95080e81b51ba729
',
249 def _real_extract(self, url):
250 mid = self._match_id(url)
252 album = self._download_json(
253 'http
://i
.y
.qq
.com
/v8
/fcg
-bin
/fcg_v8_album_info_cp
.fcg?albummid
=%s&format
=json
' % mid,
254 mid, 'Download album page
')['data
']
258 'https
://y
.qq
.com
/n
/yqq
/song
/' + song['songmid
'] + '.html
', 'QQMusic
', song['songmid
']
259 ) for song in album['list']
261 album_name = album.get('name
')
262 album_detail = album.get('desc
')
263 if album_detail is not None:
264 album_detail = album_detail.strip()
266 return self.playlist_result(entries, mid, album_name, album_detail)
269 class QQMusicToplistIE(QQPlaylistBaseIE):
270 IE_NAME = 'qqmusic
:toplist
'
271 IE_DESC = 'QQ音乐
- 排行榜
'
272 _VALID_URL = r'https?
://y\
.qq\
.com
/n
/yqq
/toplist
/(?P
<id>[0-9]+)\
.html
'
275 'url
': 'https
://y
.qq
.com
/n
/yqq
/toplist
/123.html
',
278 'title
': '美国iTunes榜
',
279 'description
': 'md5
:89db2335fdbb10678dee2d43fe9aba08
',
281 'playlist_count
': 100,
283 'url
': 'https
://y
.qq
.com
/n
/yqq
/toplist
/3.html
',
287 'description
': 'md5
:5a600d42c01696b26b71f8c4d43407da
',
289 'playlist_count
': 100,
291 'url
': 'https
://y
.qq
.com
/n
/yqq
/toplist
/106.html
',
295 'description
': 'md5
:cb84b325215e1d21708c615cac82a6e7
',
297 'playlist_count
': 50,
300 def _real_extract(self, url):
301 list_id = self._match_id(url)
303 toplist_json = self._download_json(
304 'http
://i
.y
.qq
.com
/v8
/fcg
-bin
/fcg_v8_toplist_cp
.fcg
', list_id,
305 note='Download toplist page
',
306 query={'type': 'toplist', 'topid': list_id, 'format': 'json'})
308 entries = [self.url_result(
309 'https
://y
.qq
.com
/n
/yqq
/song
/' + song['data
']['songmid
'] + '.html
', 'QQMusic
',
310 song['data
']['songmid
'])
311 for song in toplist_json['songlist
']]
313 topinfo = toplist_json.get('topinfo
', {})
314 list_name = topinfo.get('ListName
')
315 list_description = topinfo.get('info
')
316 return self.playlist_result(entries, list_id, list_name, list_description)
319 class QQMusicPlaylistIE(QQPlaylistBaseIE):
320 IE_NAME = 'qqmusic
:playlist
'
321 IE_DESC = 'QQ音乐
- 歌单
'
322 _VALID_URL = r'https?
://y\
.qq\
.com
/n
/yqq
/playlist
/(?P
<id>[0-9]+)\
.html
'
325 'url
': 'http
://y
.qq
.com
/n
/yqq
/playlist
/3462654915.html
',
328 'title
': '韩国
5月新歌精选下旬
',
329 'description
': 'md5
:d2c9d758a96b9888cf4fe82f603121d4
',
331 'playlist_count
': 40,
332 'skip
': 'playlist gone
',
334 'url
': 'https
://y
.qq
.com
/n
/yqq
/playlist
/1374105607.html
',
337 'title
': '易入人心的华语民谣
',
338 'description
': '民谣的歌曲易于传唱、、歌词朗朗伤口、旋律简单温馨。属于那种才入耳孔。却上心头的感觉。没有太多的复杂情绪。简单而直接地表达乐者的情绪,就是这样的简单才易入人心。
',
340 'playlist_count
': 20,
343 def _real_extract(self, url):
344 list_id = self._match_id(url)
346 list_json = self._download_json(
347 'http
://i
.y
.qq
.com
/qzone
-music
/fcg
-bin
/fcg_ucc_getcdinfo_byids_cp
.fcg
',
348 list_id, 'Download
list page
',
349 query={'type': 1, 'json': 1, 'utf8': 1, 'onlysong': 0, 'disstid': list_id},
350 transform_source=strip_jsonp)
351 if not len(list_json.get('cdlist
', [])):
352 if list_json.get('code
'):
353 raise ExtractorError(
354 'QQ Music said
: error
%d in fetching playlist info
' % list_json['code
'],
356 raise ExtractorError('Unable to get playlist info
')
358 cdlist = list_json['cdlist
'][0]
359 entries = [self.url_result(
360 'https
://y
.qq
.com
/n
/yqq
/song
/' + song['songmid
'] + '.html
', 'QQMusic
', song['songmid
'])
361 for song in cdlist['songlist
']]
363 list_name = cdlist.get('dissname
')
364 list_description = clean_html(unescapeHTML(cdlist.get('desc
')))
365 return self.playlist_result(entries, list_id, list_name, list_description)