]>
Commit | Line | Data |
---|---|---|
1 | import re | |
2 | ||
3 | from .common import InfoExtractor | |
4 | from ..compat import compat_urlparse | |
5 | from ..utils import ( | |
6 | get_element_by_id, | |
7 | clean_html, | |
8 | ExtractorError, | |
9 | InAdvancePagedList, | |
10 | remove_start, | |
11 | ) | |
12 | ||
13 | ||
14 | class KuwoBaseIE(InfoExtractor): | |
15 | _FORMATS = [ | |
16 | {'format': 'ape', 'ext': 'ape', 'preference': 100}, | |
17 | {'format': 'mp3-320', 'ext': 'mp3', 'br': '320kmp3', 'abr': 320, 'preference': 80}, | |
18 | {'format': 'mp3-192', 'ext': 'mp3', 'br': '192kmp3', 'abr': 192, 'preference': 70}, | |
19 | {'format': 'mp3-128', 'ext': 'mp3', 'br': '128kmp3', 'abr': 128, 'preference': 60}, | |
20 | {'format': 'wma', 'ext': 'wma', 'preference': 20}, | |
21 | {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10} | |
22 | ] | |
23 | ||
24 | def _get_formats(self, song_id, tolerate_ip_deny=False): | |
25 | formats = [] | |
26 | for file_format in self._FORMATS: | |
27 | query = { | |
28 | 'format': file_format['ext'], | |
29 | 'br': file_format.get('br', ''), | |
30 | 'rid': 'MUSIC_%s' % song_id, | |
31 | 'type': 'convert_url', | |
32 | 'response': 'url' | |
33 | } | |
34 | ||
35 | song_url = self._download_webpage( | |
36 | 'http://antiserver.kuwo.cn/anti.s', | |
37 | song_id, note='Download %s url info' % file_format['format'], | |
38 | query=query, headers=self.geo_verification_headers(), | |
39 | ) | |
40 | ||
41 | if song_url == 'IPDeny' and not tolerate_ip_deny: | |
42 | raise ExtractorError('This song is blocked in this region', expected=True) | |
43 | ||
44 | if song_url.startswith('http://') or song_url.startswith('https://'): | |
45 | formats.append({ | |
46 | 'url': song_url, | |
47 | 'format_id': file_format['format'], | |
48 | 'format': file_format['format'], | |
49 | 'quality': file_format['preference'], | |
50 | 'abr': file_format.get('abr'), | |
51 | }) | |
52 | ||
53 | return formats | |
54 | ||
55 | ||
56 | class KuwoIE(KuwoBaseIE): | |
57 | IE_NAME = 'kuwo:song' | |
58 | IE_DESC = '酷我音乐' | |
59 | _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/yinyue/(?P<id>\d+)' | |
60 | _TESTS = [{ | |
61 | 'url': 'http://www.kuwo.cn/yinyue/635632/', | |
62 | 'info_dict': { | |
63 | 'id': '635632', | |
64 | 'ext': 'ape', | |
65 | 'title': '爱我别走', | |
66 | 'creator': '张震岳', | |
67 | 'upload_date': '20080122', | |
68 | 'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c' | |
69 | }, | |
70 | 'skip': 'this song has been offline because of copyright issues', | |
71 | }, { | |
72 | 'url': 'http://www.kuwo.cn/yinyue/6446136/', | |
73 | 'info_dict': { | |
74 | 'id': '6446136', | |
75 | 'ext': 'mp3', | |
76 | 'title': '心', | |
77 | 'description': 'md5:5d0e947b242c35dc0eb1d2fce9fbf02c', | |
78 | 'creator': 'IU', | |
79 | 'upload_date': '20150518', | |
80 | }, | |
81 | 'params': { | |
82 | 'format': 'mp3-320', | |
83 | }, | |
84 | }, { | |
85 | 'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016', | |
86 | 'only_matching': True, | |
87 | }] | |
88 | ||
89 | def _real_extract(self, url): | |
90 | song_id = self._match_id(url) | |
91 | webpage, urlh = self._download_webpage_handle( | |
92 | url, song_id, note='Download song detail info', | |
93 | errnote='Unable to get song detail info') | |
94 | if song_id not in urlh.geturl() or '对不起,该歌曲由于版权问题已被下线,将返回网站首页' in webpage: | |
95 | raise ExtractorError('this song has been offline because of copyright issues', expected=True) | |
96 | ||
97 | song_name = self._html_search_regex( | |
98 | r'<p[^>]+id="lrcName">([^<]+)</p>', webpage, 'song name') | |
99 | singer_name = remove_start(self._html_search_regex( | |
100 | r'<a[^>]+href="http://www\.kuwo\.cn/artist/content\?name=([^"]+)">', | |
101 | webpage, 'singer name', fatal=False), '歌手') | |
102 | lrc_content = clean_html(get_element_by_id('lrcContent', webpage)) | |
103 | if lrc_content == '暂无': # indicates no lyrics | |
104 | lrc_content = None | |
105 | ||
106 | formats = self._get_formats(song_id) | |
107 | ||
108 | album_id = self._html_search_regex( | |
109 | r'<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"', | |
110 | webpage, 'album id', fatal=False) | |
111 | ||
112 | publish_time = None | |
113 | if album_id is not None: | |
114 | album_info_page = self._download_webpage( | |
115 | 'http://www.kuwo.cn/album/%s/' % album_id, song_id, | |
116 | note='Download album detail info', | |
117 | errnote='Unable to get album detail info') | |
118 | ||
119 | publish_time = self._html_search_regex( | |
120 | r'发行时间:(\d{4}-\d{2}-\d{2})', album_info_page, | |
121 | 'publish time', fatal=False) | |
122 | if publish_time: | |
123 | publish_time = publish_time.replace('-', '') | |
124 | ||
125 | return { | |
126 | 'id': song_id, | |
127 | 'title': song_name, | |
128 | 'creator': singer_name, | |
129 | 'upload_date': publish_time, | |
130 | 'description': lrc_content, | |
131 | 'formats': formats, | |
132 | } | |
133 | ||
134 | ||
135 | class KuwoAlbumIE(InfoExtractor): | |
136 | IE_NAME = 'kuwo:album' | |
137 | IE_DESC = '酷我音乐 - 专辑' | |
138 | _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/album/(?P<id>\d+?)/' | |
139 | _TEST = { | |
140 | 'url': 'http://www.kuwo.cn/album/502294/', | |
141 | 'info_dict': { | |
142 | 'id': '502294', | |
143 | 'title': 'Made\xa0Series\xa0《M》', | |
144 | 'description': 'md5:d463f0d8a0ff3c3ea3d6ed7452a9483f', | |
145 | }, | |
146 | 'playlist_count': 2, | |
147 | } | |
148 | ||
149 | def _real_extract(self, url): | |
150 | album_id = self._match_id(url) | |
151 | ||
152 | webpage = self._download_webpage( | |
153 | url, album_id, note='Download album info', | |
154 | errnote='Unable to get album info') | |
155 | ||
156 | album_name = self._html_search_regex( | |
157 | r'<div[^>]+class="comm"[^<]+<h1[^>]+title="([^"]+)"', webpage, | |
158 | 'album name') | |
159 | album_intro = remove_start( | |
160 | clean_html(get_element_by_id('intro', webpage)), | |
161 | '%s简介:' % album_name) | |
162 | ||
163 | entries = [ | |
164 | self.url_result(song_url, 'Kuwo') for song_url in re.findall( | |
165 | r'<p[^>]+class="listen"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"', | |
166 | webpage) | |
167 | ] | |
168 | return self.playlist_result(entries, album_id, album_name, album_intro) | |
169 | ||
170 | ||
171 | class KuwoChartIE(InfoExtractor): | |
172 | IE_NAME = 'kuwo:chart' | |
173 | IE_DESC = '酷我音乐 - 排行榜' | |
174 | _VALID_URL = r'https?://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm' | |
175 | _TEST = { | |
176 | 'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm', | |
177 | 'info_dict': { | |
178 | 'id': '香港中文龙虎榜', | |
179 | }, | |
180 | 'playlist_mincount': 7, | |
181 | } | |
182 | ||
183 | def _real_extract(self, url): | |
184 | chart_id = self._match_id(url) | |
185 | webpage = self._download_webpage( | |
186 | url, chart_id, note='Download chart info', | |
187 | errnote='Unable to get chart info') | |
188 | ||
189 | entries = [ | |
190 | self.url_result(song_url, 'Kuwo') for song_url in re.findall( | |
191 | r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)', webpage) | |
192 | ] | |
193 | return self.playlist_result(entries, chart_id) | |
194 | ||
195 | ||
196 | class KuwoSingerIE(InfoExtractor): | |
197 | IE_NAME = 'kuwo:singer' | |
198 | IE_DESC = '酷我音乐 - 歌手' | |
199 | _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mingxing/(?P<id>[^/]+)' | |
200 | _TESTS = [{ | |
201 | 'url': 'http://www.kuwo.cn/mingxing/bruno+mars/', | |
202 | 'info_dict': { | |
203 | 'id': 'bruno+mars', | |
204 | 'title': 'Bruno\xa0Mars', | |
205 | }, | |
206 | 'playlist_mincount': 329, | |
207 | }, { | |
208 | 'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm', | |
209 | 'info_dict': { | |
210 | 'id': 'Ali', | |
211 | 'title': 'Ali', | |
212 | }, | |
213 | 'playlist_mincount': 95, | |
214 | 'skip': 'Regularly stalls travis build', # See https://travis-ci.org/ytdl-org/youtube-dl/jobs/78878540 | |
215 | }] | |
216 | ||
217 | PAGE_SIZE = 15 | |
218 | ||
219 | def _real_extract(self, url): | |
220 | singer_id = self._match_id(url) | |
221 | webpage = self._download_webpage( | |
222 | url, singer_id, note='Download singer info', | |
223 | errnote='Unable to get singer info') | |
224 | ||
225 | singer_name = self._html_search_regex( | |
226 | r'<h1>([^<]+)</h1>', webpage, 'singer name') | |
227 | ||
228 | artist_id = self._html_search_regex( | |
229 | r'data-artistid="(\d+)"', webpage, 'artist id') | |
230 | ||
231 | page_count = int(self._html_search_regex( | |
232 | r'data-page="(\d+)"', webpage, 'page count')) | |
233 | ||
234 | def page_func(page_num): | |
235 | webpage = self._download_webpage( | |
236 | 'http://www.kuwo.cn/artist/contentMusicsAjax', | |
237 | singer_id, note='Download song list page #%d' % (page_num + 1), | |
238 | errnote='Unable to get song list page #%d' % (page_num + 1), | |
239 | query={'artistId': artist_id, 'pn': page_num, 'rn': self.PAGE_SIZE}) | |
240 | ||
241 | return [ | |
242 | self.url_result(compat_urlparse.urljoin(url, song_url), 'Kuwo') | |
243 | for song_url in re.findall( | |
244 | r'<div[^>]+class="name"><a[^>]+href="(/yinyue/\d+)', | |
245 | webpage) | |
246 | ] | |
247 | ||
248 | entries = InAdvancePagedList(page_func, page_count, self.PAGE_SIZE) | |
249 | ||
250 | return self.playlist_result(entries, singer_id, singer_name) | |
251 | ||
252 | ||
253 | class KuwoCategoryIE(InfoExtractor): | |
254 | IE_NAME = 'kuwo:category' | |
255 | IE_DESC = '酷我音乐 - 分类' | |
256 | _VALID_URL = r'https?://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm' | |
257 | _TEST = { | |
258 | 'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm', | |
259 | 'info_dict': { | |
260 | 'id': '86375', | |
261 | 'title': '八十年代精选', | |
262 | 'description': '这些都是属于八十年代的回忆!', | |
263 | }, | |
264 | 'playlist_mincount': 24, | |
265 | } | |
266 | ||
267 | def _real_extract(self, url): | |
268 | category_id = self._match_id(url) | |
269 | webpage = self._download_webpage( | |
270 | url, category_id, note='Download category info', | |
271 | errnote='Unable to get category info') | |
272 | ||
273 | category_name = self._html_search_regex( | |
274 | r'<h1[^>]+title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name') | |
275 | ||
276 | category_desc = remove_start( | |
277 | get_element_by_id('intro', webpage).strip(), | |
278 | '%s简介:' % category_name) | |
279 | if category_desc == '暂无': | |
280 | category_desc = None | |
281 | ||
282 | jsonm = self._parse_json(self._html_search_regex( | |
283 | r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id) | |
284 | ||
285 | entries = [ | |
286 | self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo') | |
287 | for song in jsonm['musiclist'] | |
288 | ] | |
289 | return self.playlist_result(entries, category_id, category_name, category_desc) | |
290 | ||
291 | ||
292 | class KuwoMvIE(KuwoBaseIE): | |
293 | IE_NAME = 'kuwo:mv' | |
294 | IE_DESC = '酷我音乐 - MV' | |
295 | _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mv/(?P<id>\d+?)/' | |
296 | _TEST = { | |
297 | 'url': 'http://www.kuwo.cn/mv/6480076/', | |
298 | 'info_dict': { | |
299 | 'id': '6480076', | |
300 | 'ext': 'mp4', | |
301 | 'title': 'My HouseMV', | |
302 | 'creator': '2PM', | |
303 | }, | |
304 | # In this video, music URLs (anti.s) are blocked outside China and | |
305 | # USA, while the MV URL (mvurl) is available globally, so force the MV | |
306 | # URL for consistent results in different countries | |
307 | 'params': { | |
308 | 'format': 'mv', | |
309 | }, | |
310 | } | |
311 | _FORMATS = KuwoBaseIE._FORMATS + [ | |
312 | {'format': 'mkv', 'ext': 'mkv', 'preference': 250}, | |
313 | {'format': 'mp4', 'ext': 'mp4', 'preference': 200}, | |
314 | ] | |
315 | ||
316 | def _real_extract(self, url): | |
317 | song_id = self._match_id(url) | |
318 | webpage = self._download_webpage( | |
319 | url, song_id, note='Download mv detail info: %s' % song_id, | |
320 | errnote='Unable to get mv detail info: %s' % song_id) | |
321 | ||
322 | mobj = re.search( | |
323 | r'<h1[^>]+title="(?P<song>[^"]+)">[^<]+<span[^>]+title="(?P<singer>[^"]+)"', | |
324 | webpage) | |
325 | if mobj: | |
326 | song_name = mobj.group('song') | |
327 | singer_name = mobj.group('singer') | |
328 | else: | |
329 | raise ExtractorError('Unable to find song or singer names') | |
330 | ||
331 | formats = self._get_formats(song_id, tolerate_ip_deny=True) | |
332 | ||
333 | mv_url = self._download_webpage( | |
334 | 'http://www.kuwo.cn/yy/st/mvurl?rid=MUSIC_%s' % song_id, | |
335 | song_id, note='Download %s MV URL' % song_id) | |
336 | formats.append({ | |
337 | 'url': mv_url, | |
338 | 'format_id': 'mv', | |
339 | }) | |
340 | ||
341 | return { | |
342 | 'id': song_id, | |
343 | 'title': song_name, | |
344 | 'creator': singer_name, | |
345 | 'formats': formats, | |
346 | } |