1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
|
# coding: utf-8
from __future__ import unicode_literals
import random
import time
import re
from .common import InfoExtractor
from ..utils import (
strip_jsonp,
unescapeHTML,
js_to_json,
)
from ..compat import compat_urllib_request
class QQMusicIE(InfoExtractor):
_VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
_TESTS = [{
'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
'md5': 'bed90b6db2a7a7a7e11bc585f471f63a',
'info_dict': {
'id': '004295Et37taLD',
'ext': 'm4a',
'title': '可惜没如果',
'upload_date': '20141227',
'creator': '林俊杰',
'description': 'md5:4348ff1dd24036906baa7b6f973f8d30',
}
}]
# Reference: m_r_GetRUin() in top_player.js
# http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
@staticmethod
def m_r_get_ruin():
curMs = int(time.time() * 1000) % 1000
return int(round(random.random() * 2147483647) * curMs % 1E10)
def _real_extract(self, url):
mid = self._match_id(url)
detail_info_page = self._download_webpage(
'http://s.plcloud.music.qq.com/fcgi-bin/fcg_yqq_song_detail_info.fcg?songmid=%s&play=0' % mid,
mid, note='Download song detail info',
errnote='Unable to get song detail info', encoding='gbk')
song_name = self._html_search_regex(
r"songname:\s*'([^']+)'", detail_info_page, 'song name')
publish_time = self._html_search_regex(
r'发行时间:(\d{4}-\d{2}-\d{2})', detail_info_page,
'publish time', default=None)
if publish_time:
publish_time = publish_time.replace('-', '')
singer = self._html_search_regex(
r"singer:\s*'([^']+)", detail_info_page, 'singer', default=None)
lrc_content = self._html_search_regex(
r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>',
detail_info_page, 'LRC lyrics', default=None)
guid = self.m_r_get_ruin()
vkey = self._download_json(
'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid,
mid, note='Retrieve vkey', errnote='Unable to get vkey',
transform_source=strip_jsonp)['key']
song_url = 'http://cc.stream.qqmusic.qq.com/C200%s.m4a?vkey=%s&guid=%s&fromtag=0' % (mid, vkey, guid)
return {
'id': mid,
'url': song_url,
'title': song_name,
'upload_date': publish_time,
'creator': singer,
'description': lrc_content,
}
class QQPlaylistBaseIE(InfoExtractor):
@staticmethod
def qq_static_url(category, mid):
return 'http://y.qq.com/y/static/%s/%s/%s/%s.html' % (category, mid[-2], mid[-1], mid)
@classmethod
def get_entries_from_page(cls, page):
entries = []
for item in re.findall(r'class="data"[^<>]*>([^<>]+)</', page):
song_mid = unescapeHTML(item).split('|')[-5]
entries.append(cls.url_result(
'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
song_mid))
return entries
class QQMusicSingerIE(QQPlaylistBaseIE):
_VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
_TEST = {
'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
'info_dict': {
'id': '001BLpXF2DyJe2',
'title': '林俊杰',
'description': 'md5:2a222d89ba4455a3af19940c0481bb78',
},
'playlist_count': 12,
}
def _real_extract(self, url):
mid = self._match_id(url)
singer_page = self._download_webpage(
self.qq_static_url('singer', mid), mid, 'Download singer page')
entries = self.get_entries_from_page(singer_page)
singer_name = self._html_search_regex(
r"singername\s*:\s*'([^']+)'", singer_page, 'singer name',
default=None)
singer_id = self._html_search_regex(
r"singerid\s*:\s*'([0-9]+)'", singer_page, 'singer id',
default=None)
singer_desc = None
if singer_id:
req = compat_urllib_request.Request(
'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg?utf8=1&outCharset=utf-8&format=xml&singerid=%s' % singer_id)
req.add_header(
'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html')
singer_desc_page = self._download_xml(
req, mid, 'Donwload singer description XML')
singer_desc = singer_desc_page.find('./data/info/desc').text
return self.playlist_result(entries, mid, singer_name, singer_desc)
class QQMusicAlbumIE(QQPlaylistBaseIE):
_VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
_TEST = {
'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1&play=0',
'info_dict': {
'id': '000gXCTb2AhRR1',
'title': '我们都是这样长大的',
'description': 'md5:d216c55a2d4b3537fe4415b8767d74d6',
},
'playlist_count': 4,
}
def _real_extract(self, url):
mid = self._match_id(url)
album_page = self._download_webpage(
self.qq_static_url('album', mid), mid, 'Download album page')
entries = self.get_entries_from_page(album_page)
album_name = self._html_search_regex(
r"albumname\s*:\s*'([^']+)',", album_page, 'album name',
default=None)
album_detail = self._html_search_regex(
r'<div class="album_detail close_detail">\s*<p>((?:[^<>]+(?:<br />)?)+)</p>',
album_page, 'album details', default=None)
return self.playlist_result(entries, mid, album_name, album_detail)
class QQMusicToplistIE(QQPlaylistBaseIE):
_VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
_TESTS = [{
'url': 'http://y.qq.com/#type=toplist&p=global_12',
'info_dict': {
'id': 'global_12',
'title': 'itunes榜',
},
'playlist_count': 10,
}, {
'url': 'http://y.qq.com/#type=toplist&p=top_6',
'info_dict': {
'id': 'top_6',
'title': 'QQ音乐巅峰榜·欧美',
},
'playlist_count': 100,
}]
@staticmethod
def strip_qq_jsonp(code):
return js_to_json(re.sub(r'^MusicJsonCallback\((.*?)\)/\*.+?\*/$', r'\1', code))
def _real_extract(self, url):
list_id = self._match_id(url)
list_type = list_id.split("_")[0]
num_id = list_id.split("_")[1]
list_page = self._download_webpage("http://y.qq.com/y/static/toplist/index/%s.html" % list_id, list_id, 'Download toplist page')
entries = []
if list_type == 'top':
list = self._download_json(
"http://y.qq.com/y/static/toplist/json/top/%s/1.js" % num_id,
list_id, note='Retrieve toplist json', errnote='Unable to get toplist json', transform_source=self.strip_qq_jsonp)
for song in list['l']:
s = song['s']
song_mid = s.split("|")[20]
entries.append(self.url_result(
'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
song_mid))
elif list_type == 'global':
entries = self.get_entries_from_page(list_page)
list_name = self._html_search_regex(
r'<h2 id="top_name">([^\']+)</h2>', list_page, 'top list name',
default=None)
list_desc = None
return self.playlist_result(entries, list_id, list_name, list_desc)
|