]>
Commit | Line | Data |
---|---|---|
1 | # coding: utf-8 | |
2 | from __future__ import unicode_literals | |
3 | ||
4 | import random | |
5 | import re | |
6 | import time | |
7 | ||
8 | from .common import InfoExtractor | |
9 | from ..utils import ( | |
10 | sanitized_Request, | |
11 | strip_jsonp, | |
12 | unescapeHTML, | |
13 | clean_html, | |
14 | ExtractorError, | |
15 | ) | |
16 | ||
17 | ||
18 | class QQMusicIE(InfoExtractor): | |
19 | IE_NAME = 'qqmusic' | |
20 | IE_DESC = 'QQ音乐' | |
21 | _VALID_URL = r'https?://y\.qq\.com/n/yqq/song/(?P<id>[0-9A-Za-z]+)\.html' | |
22 | _TESTS = [{ | |
23 | 'url': 'https://y.qq.com/n/yqq/song/004295Et37taLD.html', | |
24 | 'md5': '9ce1c1c8445f561506d2e3cfb0255705', | |
25 | 'info_dict': { | |
26 | 'id': '004295Et37taLD', | |
27 | 'ext': 'mp3', | |
28 | 'title': '可惜没如果', | |
29 | 'release_date': '20141227', | |
30 | 'creator': '林俊杰', | |
31 | 'description': 'md5:d327722d0361576fde558f1ac68a7065', | |
32 | 'thumbnail': r're:^https?://.*\.jpg$', | |
33 | } | |
34 | }, { | |
35 | 'note': 'There is no mp3-320 version of this song.', | |
36 | 'url': 'https://y.qq.com/n/yqq/song/004MsGEo3DdNxV.html', | |
37 | 'md5': 'fa3926f0c585cda0af8fa4f796482e3e', | |
38 | 'info_dict': { | |
39 | 'id': '004MsGEo3DdNxV', | |
40 | 'ext': 'mp3', | |
41 | 'title': '如果', | |
42 | 'release_date': '20050626', | |
43 | 'creator': '李季美', | |
44 | 'description': 'md5:46857d5ed62bc4ba84607a805dccf437', | |
45 | 'thumbnail': r're:^https?://.*\.jpg$', | |
46 | } | |
47 | }, { | |
48 | 'note': 'lyrics not in .lrc format', | |
49 | 'url': 'https://y.qq.com/n/yqq/song/001JyApY11tIp6.html', | |
50 | 'info_dict': { | |
51 | 'id': '001JyApY11tIp6', | |
52 | 'ext': 'mp3', | |
53 | 'title': 'Shadows Over Transylvania', | |
54 | 'release_date': '19970225', | |
55 | 'creator': 'Dark Funeral', | |
56 | 'description': 'md5:ed14d5bd7ecec19609108052c25b2c11', | |
57 | 'thumbnail': r're:^https?://.*\.jpg$', | |
58 | }, | |
59 | 'params': { | |
60 | 'skip_download': True, | |
61 | }, | |
62 | }] | |
63 | ||
64 | _FORMATS = { | |
65 | 'mp3-320': {'prefix': 'M800', 'ext': 'mp3', 'preference': 40, 'abr': 320}, | |
66 | 'mp3-128': {'prefix': 'M500', 'ext': 'mp3', 'preference': 30, 'abr': 128}, | |
67 | 'm4a': {'prefix': 'C200', 'ext': 'm4a', 'preference': 10} | |
68 | } | |
69 | ||
70 | # Reference: m_r_GetRUin() in top_player.js | |
71 | # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js | |
72 | @staticmethod | |
73 | def m_r_get_ruin(): | |
74 | curMs = int(time.time() * 1000) % 1000 | |
75 | return int(round(random.random() * 2147483647) * curMs % 1E10) | |
76 | ||
77 | def _real_extract(self, url): | |
78 | mid = self._match_id(url) | |
79 | ||
80 | detail_info_page = self._download_webpage( | |
81 | 'http://s.plcloud.music.qq.com/fcgi-bin/fcg_yqq_song_detail_info.fcg?songmid=%s&play=0' % mid, | |
82 | mid, note='Download song detail info', | |
83 | errnote='Unable to get song detail info', encoding='gbk') | |
84 | ||
85 | song_name = self._html_search_regex( | |
86 | r"songname:\s*'([^']+)'", detail_info_page, 'song name') | |
87 | ||
88 | publish_time = self._html_search_regex( | |
89 | r'发行时间:(\d{4}-\d{2}-\d{2})', detail_info_page, | |
90 | 'publish time', default=None) | |
91 | if publish_time: | |
92 | publish_time = publish_time.replace('-', '') | |
93 | ||
94 | singer = self._html_search_regex( | |
95 | r"singer:\s*'([^']+)", detail_info_page, 'singer', default=None) | |
96 | ||
97 | lrc_content = self._html_search_regex( | |
98 | r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>', | |
99 | detail_info_page, 'LRC lyrics', default=None) | |
100 | if lrc_content: | |
101 | lrc_content = lrc_content.replace('\\n', '\n') | |
102 | ||
103 | thumbnail_url = None | |
104 | albummid = self._search_regex( | |
105 | [r'albummid:\'([0-9a-zA-Z]+)\'', r'"albummid":"([0-9a-zA-Z]+)"'], | |
106 | detail_info_page, 'album mid', default=None) | |
107 | if albummid: | |
108 | thumbnail_url = "http://i.gtimg.cn/music/photo/mid_album_500/%s/%s/%s.jpg" \ | |
109 | % (albummid[-2:-1], albummid[-1], albummid) | |
110 | ||
111 | guid = self.m_r_get_ruin() | |
112 | ||
113 | vkey = self._download_json( | |
114 | 'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid, | |
115 | mid, note='Retrieve vkey', errnote='Unable to get vkey', | |
116 | transform_source=strip_jsonp)['key'] | |
117 | ||
118 | formats = [] | |
119 | for format_id, details in self._FORMATS.items(): | |
120 | formats.append({ | |
121 | 'url': 'http://cc.stream.qqmusic.qq.com/%s%s.%s?vkey=%s&guid=%s&fromtag=0' | |
122 | % (details['prefix'], mid, details['ext'], vkey, guid), | |
123 | 'format': format_id, | |
124 | 'format_id': format_id, | |
125 | 'preference': details['preference'], | |
126 | 'abr': details.get('abr'), | |
127 | }) | |
128 | self._check_formats(formats, mid) | |
129 | self._sort_formats(formats) | |
130 | ||
131 | actual_lrc_lyrics = ''.join( | |
132 | line + '\n' for line in re.findall( | |
133 | r'(?m)^(\[[0-9]{2}:[0-9]{2}(?:\.[0-9]{2,})?\][^\n]*|\[[^\]]*\])', lrc_content)) | |
134 | ||
135 | info_dict = { | |
136 | 'id': mid, | |
137 | 'formats': formats, | |
138 | 'title': song_name, | |
139 | 'release_date': publish_time, | |
140 | 'creator': singer, | |
141 | 'description': lrc_content, | |
142 | 'thumbnail': thumbnail_url | |
143 | } | |
144 | if actual_lrc_lyrics: | |
145 | info_dict['subtitles'] = { | |
146 | 'origin': [{ | |
147 | 'ext': 'lrc', | |
148 | 'data': actual_lrc_lyrics, | |
149 | }] | |
150 | } | |
151 | return info_dict | |
152 | ||
153 | ||
154 | class QQPlaylistBaseIE(InfoExtractor): | |
155 | @staticmethod | |
156 | def qq_static_url(category, mid): | |
157 | return 'http://y.qq.com/y/static/%s/%s/%s/%s.html' % (category, mid[-2], mid[-1], mid) | |
158 | ||
159 | @classmethod | |
160 | def get_entries_from_page(cls, page): | |
161 | entries = [] | |
162 | ||
163 | for item in re.findall(r'class="data"[^<>]*>([^<>]+)</', page): | |
164 | song_mid = unescapeHTML(item).split('|')[-5] | |
165 | entries.append(cls.url_result( | |
166 | # https://y.qq.com/n/yqq/song/004Dbsoo1yCbNZ.html | |
167 | 'https://y.qq.com/n/yqq/song/' + song_mid + ".html", 'QQMusic', | |
168 | song_mid)) | |
169 | ||
170 | return entries | |
171 | ||
172 | ||
173 | class QQMusicSingerIE(QQPlaylistBaseIE): | |
174 | IE_NAME = 'qqmusic:singer' | |
175 | IE_DESC = 'QQ音乐 - 歌手' | |
176 | _VALID_URL = r'https?://y\.qq\.com/n/yqq/singer/(?P<id>[0-9A-Za-z]+)\.html' | |
177 | _TEST = { | |
178 | 'url': 'https://y.qq.com/n/yqq/singer/001BLpXF2DyJe2.html', | |
179 | 'info_dict': { | |
180 | 'id': '001BLpXF2DyJe2', | |
181 | 'title': '林俊杰', | |
182 | 'description': 'md5:870ec08f7d8547c29c93010899103751', | |
183 | }, | |
184 | 'playlist_count': 12, | |
185 | } | |
186 | ||
187 | def _real_extract(self, url): | |
188 | mid = self._match_id(url) | |
189 | ||
190 | singer_page = self._download_webpage( | |
191 | self.qq_static_url('singer', mid), mid, 'Download singer page') | |
192 | ||
193 | entries = self.get_entries_from_page(singer_page) | |
194 | ||
195 | singer_name = self._html_search_regex( | |
196 | r"singername\s*:\s*'([^']+)'", singer_page, 'singer name', | |
197 | default=None) | |
198 | ||
199 | singer_id = self._html_search_regex( | |
200 | r"singerid\s*:\s*'([0-9]+)'", singer_page, 'singer id', | |
201 | default=None) | |
202 | ||
203 | singer_desc = None | |
204 | ||
205 | if singer_id: | |
206 | req = sanitized_Request( | |
207 | 'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg?utf8=1&outCharset=utf-8&format=xml&singerid=%s' % singer_id) | |
208 | req.add_header( | |
209 | 'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html') | |
210 | singer_desc_page = self._download_xml( | |
211 | req, mid, 'Donwload singer description XML') | |
212 | ||
213 | singer_desc = singer_desc_page.find('./data/info/desc').text | |
214 | ||
215 | return self.playlist_result(entries, mid, singer_name, singer_desc) | |
216 | ||
217 | ||
218 | class QQMusicAlbumIE(QQPlaylistBaseIE): | |
219 | IE_NAME = 'qqmusic:album' | |
220 | IE_DESC = 'QQ音乐 - 专辑' | |
221 | _VALID_URL = r'https?://y\.qq\.com/n/yqq/album/(?P<id>[0-9A-Za-z]+)\.html' | |
222 | ||
223 | _TESTS = [{ | |
224 | 'url': 'https://y.qq.com/n/yqq/album/000gXCTb2AhRR1.html', | |
225 | 'info_dict': { | |
226 | 'id': '000gXCTb2AhRR1', | |
227 | 'title': '我们都是这样长大的', | |
228 | 'description': 'md5:179c5dce203a5931970d306aa9607ea6', | |
229 | }, | |
230 | 'playlist_count': 4, | |
231 | }, { | |
232 | 'url': 'https://y.qq.com/n/yqq/album/002Y5a3b3AlCu3.html', | |
233 | 'info_dict': { | |
234 | 'id': '002Y5a3b3AlCu3', | |
235 | 'title': '그리고...', | |
236 | 'description': 'md5:a48823755615508a95080e81b51ba729', | |
237 | }, | |
238 | 'playlist_count': 8, | |
239 | }] | |
240 | ||
241 | def _real_extract(self, url): | |
242 | mid = self._match_id(url) | |
243 | ||
244 | album = self._download_json( | |
245 | 'http://i.y.qq.com/v8/fcg-bin/fcg_v8_album_info_cp.fcg?albummid=%s&format=json' % mid, | |
246 | mid, 'Download album page')['data'] | |
247 | ||
248 | entries = [ | |
249 | self.url_result( | |
250 | 'https://y.qq.com/n/yqq/song/' + song['songmid'] + ".html", 'QQMusic', song['songmid'] | |
251 | ) for song in album['list'] | |
252 | ] | |
253 | album_name = album.get('name') | |
254 | album_detail = album.get('desc') | |
255 | if album_detail is not None: | |
256 | album_detail = album_detail.strip() | |
257 | ||
258 | return self.playlist_result(entries, mid, album_name, album_detail) | |
259 | ||
260 | ||
261 | class QQMusicToplistIE(QQPlaylistBaseIE): | |
262 | IE_NAME = 'qqmusic:toplist' | |
263 | IE_DESC = 'QQ音乐 - 排行榜' | |
264 | _VALID_URL = r'https?://y\.qq\.com/n/yqq/toplist/(?P<id>[0-9]+)\.html' | |
265 | ||
266 | _TESTS = [{ | |
267 | 'url': 'https://y.qq.com/n/yqq/toplist/123.html', | |
268 | 'info_dict': { | |
269 | 'id': 'global_123', | |
270 | 'title': '美国iTunes榜', | |
271 | }, | |
272 | 'playlist_count': 10, | |
273 | }, { | |
274 | 'url': 'https://y.qq.com/n/yqq/toplist/3.html', | |
275 | 'info_dict': { | |
276 | 'id': 'top_3', | |
277 | 'title': '巅峰榜·欧美', | |
278 | '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' | |
279 | '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' | |
280 | '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:' | |
281 | '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' | |
282 | }, | |
283 | 'playlist_count': 100, | |
284 | }, { | |
285 | 'url': 'https://y.qq.com/n/yqq/toplist/106.html', | |
286 | 'info_dict': { | |
287 | 'id': 'global_106', | |
288 | 'title': '韩国Mnet榜', | |
289 | }, | |
290 | 'playlist_count': 50, | |
291 | }] | |
292 | ||
293 | def _real_extract(self, url): | |
294 | list_id = self._match_id(url) | |
295 | ||
296 | # list_type, num_id = list_id.split("_") | |
297 | list_type = "toplist" | |
298 | num_id = list_id | |
299 | ||
300 | toplist_json = self._download_json( | |
301 | 'http://i.y.qq.com/v8/fcg-bin/fcg_v8_toplist_cp.fcg?type=%s&topid=%s&format=json' | |
302 | % (list_type, num_id), | |
303 | list_id, 'Download toplist page') | |
304 | ||
305 | entries = [ | |
306 | self.url_result( | |
307 | 'https://y.qq.com/n/yqq/song/' + song['data']['songmid'] + ".html", 'QQMusic', song['data']['songmid'] | |
308 | ) for song in toplist_json['songlist'] | |
309 | ] | |
310 | ||
311 | topinfo = toplist_json.get('topinfo', {}) | |
312 | list_name = topinfo.get('ListName') | |
313 | list_description = topinfo.get('info') | |
314 | return self.playlist_result(entries, list_id, list_name, list_description) | |
315 | ||
316 | ||
317 | class QQMusicPlaylistIE(QQPlaylistBaseIE): | |
318 | IE_NAME = 'qqmusic:playlist' | |
319 | IE_DESC = 'QQ音乐 - 歌单' | |
320 | _VALID_URL = r'https?://y\.qq\.com/n/yqq/playlist/(?P<id>[0-9]+)\.html' | |
321 | ||
322 | _TESTS = [{ | |
323 | 'url': 'http://y.qq.com/n/yqq/playlist/3462654915.html', | |
324 | 'info_dict': { | |
325 | 'id': '3462654915', | |
326 | 'title': '韩国5月新歌精选下旬', | |
327 | 'description': 'md5:d2c9d758a96b9888cf4fe82f603121d4', | |
328 | }, | |
329 | 'playlist_count': 40, | |
330 | 'skip': 'playlist gone', | |
331 | }, { | |
332 | 'url': 'https://y.qq.com/n/yqq/playlist/1374105607.html', | |
333 | 'info_dict': { | |
334 | 'id': '1374105607', | |
335 | 'title': '易入人心的华语民谣', | |
336 | '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。', | |
337 | }, | |
338 | 'playlist_count': 20, | |
339 | }] | |
340 | ||
341 | def _real_extract(self, url): | |
342 | list_id = self._match_id(url) | |
343 | ||
344 | list_json = self._download_json( | |
345 | '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' | |
346 | % list_id, list_id, 'Download list page', | |
347 | transform_source=strip_jsonp) | |
348 | if not len(list_json.get('cdlist', [])): | |
349 | if list_json.get('code'): | |
350 | raise ExtractorError( | |
351 | 'QQ Music said: error %d in fetching playlist info' % list_json['code'], | |
352 | expected=True) | |
353 | raise ExtractorError('Unable to get playlist info') | |
354 | ||
355 | cdlist = list_json['cdlist'][0] | |
356 | entries = [ | |
357 | self.url_result( | |
358 | 'https://y.qq.com/n/yqq/song/' + song['songmid'] + ".html", 'QQMusic', song['songmid'] | |
359 | ) for song in cdlist['songlist'] | |
360 | ] | |
361 | ||
362 | list_name = cdlist.get('dissname') | |
363 | list_description = clean_html(unescapeHTML(cdlist.get('desc'))) | |
364 | return self.playlist_result(entries, list_id, list_name, list_description) |