]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/qqmusic.py
[qqmusic:album] Strip description
[yt-dlp.git] / youtube_dl / extractor / qqmusic.py
CommitLineData
5d98908b
YCH
1# coding: utf-8
2from __future__ import unicode_literals
3
a2043572
YCH
4import random
5import time
8afff9f8 6import re
a2043572 7
5d98908b 8from .common import InfoExtractor
5edea45f
YCH
9from ..utils import (
10 strip_jsonp,
11 unescapeHTML,
0d0d5d37 12 clean_html,
5edea45f 13)
8afff9f8 14from ..compat import compat_urllib_request
5d98908b 15
5d98908b
YCH
16
17class QQMusicIE(InfoExtractor):
7ec676bb 18 IE_NAME = 'qqmusic'
5d98908b
YCH
19 _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
20 _TESTS = [{
21 'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
55e5841f 22 'md5': '9ce1c1c8445f561506d2e3cfb0255705',
5d98908b
YCH
23 'info_dict': {
24 'id': '004295Et37taLD',
55e5841f 25 'ext': 'mp3',
5d98908b
YCH
26 'title': '可惜没如果',
27 'upload_date': '20141227',
28 'creator': '林俊杰',
b813d8ca 29 'description': 'md5:d327722d0361576fde558f1ac68a7065',
5d98908b
YCH
30 }
31 }]
32
55e5841f 33 _FORMATS = {
8b8cde21 34 'mp3-320': {'prefix': 'M800', 'ext': 'mp3', 'preference': 40, 'abr': 320},
35 'mp3-128': {'prefix': 'M500', 'ext': 'mp3', 'preference': 30, 'abr': 128},
55e5841f 36 'm4a': {'prefix': 'C200', 'ext': 'm4a', 'preference': 10}
37 }
38
a2043572
YCH
39 # Reference: m_r_GetRUin() in top_player.js
40 # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
41 @staticmethod
42 def m_r_get_ruin():
43 curMs = int(time.time() * 1000) % 1000
44 return int(round(random.random() * 2147483647) * curMs % 1E10)
45
5d98908b
YCH
46 def _real_extract(self, url):
47 mid = self._match_id(url)
48
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,
8afff9f8 51 mid, note='Download song detail info',
c9a77969 52 errnote='Unable to get song detail info', encoding='gbk')
5d98908b
YCH
53
54 song_name = self._html_search_regex(
55 r"songname:\s*'([^']+)'", detail_info_page, 'song name')
56
57 publish_time = self._html_search_regex(
58 r'发行时间:(\d{4}-\d{2}-\d{2})', detail_info_page,
a685ae51
YCH
59 'publish time', default=None)
60 if publish_time:
61 publish_time = publish_time.replace('-', '')
5d98908b
YCH
62
63 singer = self._html_search_regex(
a685ae51
YCH
64 r"singer:\s*'([^']+)", detail_info_page, 'singer', default=None)
65
66 lrc_content = self._html_search_regex(
67 r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>',
68 detail_info_page, 'LRC lyrics', default=None)
b813d8ca
YCH
69 if lrc_content:
70 lrc_content = lrc_content.replace('\\n', '\n')
5d98908b 71
a2043572
YCH
72 guid = self.m_r_get_ruin()
73
5d98908b
YCH
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']
55e5841f 78
79 formats = []
e8ac61e8 80 for format_id, details in self._FORMATS.items():
55e5841f 81 formats.append({
82 'url': 'http://cc.stream.qqmusic.qq.com/%s%s.%s?vkey=%s&guid=%s&fromtag=0'
e8ac61e8
YCH
83 % (details['prefix'], mid, details['ext'], vkey, guid),
84 'format': format_id,
85 'format_id': format_id,
86 'preference': details['preference'],
87 'abr': details.get('abr'),
55e5841f 88 })
89 self._sort_formats(formats)
5d98908b
YCH
90
91 return {
92 'id': mid,
55e5841f 93 'formats': formats,
5d98908b
YCH
94 'title': song_name,
95 'upload_date': publish_time,
96 'creator': singer,
a685ae51 97 'description': lrc_content,
5d98908b 98 }
8afff9f8
YCH
99
100
5edea45f
YCH
101class QQPlaylistBaseIE(InfoExtractor):
102 @staticmethod
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)
105
5edea45f
YCH
106 @classmethod
107 def get_entries_from_page(cls, page):
108 entries = []
109
110 for item in re.findall(r'class="data"[^<>]*>([^<>]+)</', page):
111 song_mid = unescapeHTML(item).split('|')[-5]
112 entries.append(cls.url_result(
a685ae51
YCH
113 'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
114 song_mid))
5edea45f
YCH
115
116 return entries
117
118
119class QQMusicSingerIE(QQPlaylistBaseIE):
7ec676bb 120 IE_NAME = 'qqmusic:singer'
8afff9f8
YCH
121 _VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
122 _TEST = {
123 'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
124 'info_dict': {
125 'id': '001BLpXF2DyJe2',
126 'title': '林俊杰',
127 'description': 'md5:2a222d89ba4455a3af19940c0481bb78',
128 },
129 'playlist_count': 12,
130 }
131
132 def _real_extract(self, url):
133 mid = self._match_id(url)
134
135 singer_page = self._download_webpage(
5edea45f 136 self.qq_static_url('singer', mid), mid, 'Download singer page')
8afff9f8 137
5edea45f 138 entries = self.get_entries_from_page(singer_page)
8afff9f8
YCH
139
140 singer_name = self._html_search_regex(
141 r"singername\s*:\s*'([^']+)'", singer_page, 'singer name',
142 default=None)
143
144 singer_id = self._html_search_regex(
145 r"singerid\s*:\s*'([0-9]+)'", singer_page, 'singer id',
146 default=None)
147
148 singer_desc = None
149
150 if 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)
153 req.add_header(
154 'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html')
155 singer_desc_page = self._download_xml(
5edea45f 156 req, mid, 'Donwload singer description XML')
8afff9f8
YCH
157
158 singer_desc = singer_desc_page.find('./data/info/desc').text
159
160 return self.playlist_result(entries, mid, singer_name, singer_desc)
5edea45f
YCH
161
162
163class QQMusicAlbumIE(QQPlaylistBaseIE):
7ec676bb 164 IE_NAME = 'qqmusic:album'
5edea45f
YCH
165 _VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
166
29b809de 167 _TESTS = [{
168 'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1',
5edea45f
YCH
169 'info_dict': {
170 'id': '000gXCTb2AhRR1',
171 'title': '我们都是这样长大的',
fc7ae675 172 'description': 'md5:179c5dce203a5931970d306aa9607ea6',
5edea45f
YCH
173 },
174 'playlist_count': 4,
29b809de 175 }, {
176 'url': 'http://y.qq.com/#type=album&mid=002Y5a3b3AlCu3',
177 'info_dict': {
178 'id': '002Y5a3b3AlCu3',
179 'title': '그리고...',
fc7ae675 180 'description': 'md5:a48823755615508a95080e81b51ba729',
29b809de 181 },
182 'playlist_count': 8,
183 }]
5edea45f
YCH
184
185 def _real_extract(self, url):
186 mid = self._match_id(url)
187
29b809de 188 album = self._download_json(
189 'http://i.y.qq.com/v8/fcg-bin/fcg_v8_album_info_cp.fcg?albummid=%s&format=json' % mid,
190 mid, 'Download album page')['data']
191
192 entries = [
193 self.url_result(
194 'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
195 ) for song in album['list']
196 ]
197 album_name = album['name']
198 album_detail = album.get('desc')
fc7ae675
YCH
199 if album_detail is not None:
200 album_detail = album_detail.strip()
5edea45f
YCH
201
202 return self.playlist_result(entries, mid, album_name, album_detail)
41333b97 203
204
205class QQMusicToplistIE(QQPlaylistBaseIE):
7ec676bb 206 IE_NAME = 'qqmusic:toplist'
41333b97 207 _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
54889739 208
41333b97 209 _TESTS = [{
eedda32e 210 'url': 'http://y.qq.com/#type=toplist&p=global_123',
41333b97 211 'info_dict': {
eedda32e 212 'id': 'global_123',
213 'title': '美国iTunes榜',
41333b97 214 },
215 'playlist_count': 10,
216 }, {
eedda32e 217 'url': 'http://y.qq.com/#type=toplist&p=top_3',
41333b97 218 'info_dict': {
eedda32e 219 'id': 'top_3',
41333b97 220 'title': 'QQ音乐巅峰榜·欧美',
eedda32e 221 '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'
222 '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'
223 '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:'
224 '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'
41333b97 225 },
226 'playlist_count': 100,
fd4eefed 227 }, {
eedda32e 228 'url': 'http://y.qq.com/#type=toplist&p=global_106',
fd4eefed 229 'info_dict': {
eedda32e 230 'id': 'global_106',
231 'title': '韩国Mnet榜',
fd4eefed 232 },
233 'playlist_count': 50,
41333b97 234 }]
235
41333b97 236 def _real_extract(self, url):
237 list_id = self._match_id(url)
238
29ea5728 239 list_type, num_id = list_id.split("_")
41333b97 240
29ea5728 241 toplist_json = self._download_json(
eedda32e 242 'http://i.y.qq.com/v8/fcg-bin/fcg_v8_toplist_cp.fcg?type=%s&topid=%s&format=json'
243 % (list_type, num_id),
244 list_id, 'Download toplist page')
41333b97 245
eedda32e 246 entries = [
247 self.url_result(
248 'http://y.qq.com/#type=song&mid=' + song['data']['songmid'], 'QQMusic', song['data']['songmid']
249 ) for song in toplist_json['songlist']
250 ]
41333b97 251
9d4f213f
YCH
252 topinfo = toplist_json.get('topinfo', {})
253 list_name = topinfo.get('ListName')
254 list_description = topinfo.get('info')
eedda32e 255 return self.playlist_result(entries, list_id, list_name, list_description)
0d0d5d37 256
257
258class QQMusicPlaylistIE(QQPlaylistBaseIE):
259 IE_NAME = 'qqmusic:playlist'
260 _VALID_URL = r'http://y\.qq\.com/#type=taoge&id=(?P<id>[0-9]+)'
261
262 _TEST = {
263 'url': 'http://y.qq.com/#type=taoge&id=3462654915',
264 'info_dict': {
265 'id': '3462654915',
266 'title': '韩国5月新歌精选下旬',
267 'description': 'md5:d2c9d758a96b9888cf4fe82f603121d4',
268 },
269 'playlist_count': 40,
270 }
271
272 def _real_extract(self, url):
273 list_id = self._match_id(url)
274
275 list_json = self._download_json(
276 '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'
277 % list_id, list_id, 'Download list page',
278 transform_source=strip_jsonp)['cdlist'][0]
279
280 entries = [
281 self.url_result(
282 'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
283 ) for song in list_json['songlist']
284 ]
285
e9d33454 286 list_name = list_json.get('dissname')
0d0d5d37 287 list_description = clean_html(unescapeHTML(list_json.get('desc')))
288 return self.playlist_result(entries, list_id, list_name, list_description)