]>
Commit | Line | Data |
---|---|---|
8f73e89c | 1 | # coding: utf-8 |
2 | from __future__ import unicode_literals | |
3 | ||
4 | import re | |
5 | import itertools | |
6 | ||
7 | from .common import InfoExtractor | |
8 | from ..utils import ( | |
9 | get_element_by_id, | |
10 | clean_html, | |
11 | ExtractorError, | |
12 | ) | |
13 | ||
14 | ||
15 | class KuwoIE(InfoExtractor): | |
16 | IE_NAME = 'kuwo:song' | |
17 | _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P<id>[0-9]+?)/' | |
18 | _TESTS = [{ | |
19 | 'url': 'http://www.kuwo.cn/yinyue/635632/', | |
20 | 'info_dict': { | |
21 | 'id': '635632', | |
22 | 'ext': 'ape', | |
23 | 'title': '爱我别走', | |
24 | 'creator': '张震岳', | |
25 | 'upload_date': '20080122', | |
26 | 'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c' | |
27 | }, | |
28 | }, { | |
29 | 'url': 'http://www.kuwo.cn/yinyue/6446136/', | |
30 | 'info_dict': { | |
31 | 'id': '6446136', | |
32 | 'ext': 'mp3', | |
33 | 'title': '心', | |
34 | 'creator': 'IU', | |
35 | 'upload_date': '20150518', | |
36 | }, | |
37 | 'params': { | |
38 | 'format': 'mp3-320' | |
39 | }, | |
40 | }] | |
41 | _FORMATS = [ | |
42 | {'format': 'ape', 'ext': 'ape', 'preference': 100}, | |
43 | {'format': 'mp3-320', 'ext': 'mp3', 'br': '320kmp3', 'abr': 320, 'preference': 80}, | |
44 | {'format': 'mp3-192', 'ext': 'mp3', 'br': '192kmp3', 'abr': 192, 'preference': 70}, | |
45 | {'format': 'mp3-128', 'ext': 'mp3', 'br': '128kmp3', 'abr': 128, 'preference': 60}, | |
46 | {'format': 'wma', 'ext': 'wma', 'preference': 20}, | |
47 | {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10} | |
48 | ] | |
49 | ||
50 | def _get_formats(self, song_id): | |
51 | formats = [] | |
52 | for file_format in self._FORMATS: | |
53 | song_url = self._download_webpage( | |
54 | "http://antiserver.kuwo.cn/anti.s?format=%s&br=%s&rid=MUSIC_%s&type=convert_url&response=url" % | |
55 | (file_format['ext'], file_format.get('br', ''), song_id), | |
56 | song_id, note="Download %s url info" % file_format["format"], | |
57 | ) | |
58 | if song_url.startswith('http://') or song_url.startswith('https://'): | |
59 | formats.append({ | |
60 | 'url': song_url, | |
61 | 'format_id': file_format['format'], | |
62 | 'format': file_format['format'], | |
63 | 'preference': file_format['preference'], | |
64 | 'abr': file_format.get('abr'), | |
65 | }) | |
66 | self._sort_formats(formats) | |
67 | return formats | |
68 | ||
69 | def _real_extract(self, url): | |
70 | song_id = self._match_id(url) | |
71 | webpage = self._download_webpage( | |
72 | url, song_id, note='Download song detail info', | |
73 | errnote='Unable to get song detail info') | |
74 | ||
75 | song_name = self._html_search_regex( | |
76 | r'<h1 title="(.+?)">', webpage, 'song name') | |
77 | singer_name = self._html_search_regex( | |
78 | r'<div class="s_img">.+?title="(.+?)".+?</div>', webpage, 'singer name', | |
79 | flags=re.DOTALL, default=None) | |
80 | lrc_content = clean_html(get_element_by_id("lrcContent", webpage)) | |
81 | if lrc_content == '暂无': # indicates no lyrics | |
82 | lrc_content = None | |
83 | ||
84 | formats = self._get_formats(song_id) | |
85 | ||
86 | album_id = self._html_search_regex( | |
87 | r'<p class="album" title=".+?">.+?<a href="http://www\.kuwo\.cn/album/([0-9]+)/" ', | |
88 | webpage, 'album id', default=None, fatal=False) | |
89 | ||
90 | publish_time = None | |
91 | if album_id is not None: | |
92 | album_info_page = self._download_webpage( | |
93 | "http://www.kuwo.cn/album/%s/" % album_id, song_id, | |
94 | note='Download album detail info', | |
95 | errnote='Unable to get album detail info') | |
96 | ||
97 | publish_time = self._html_search_regex( | |
98 | r'发行时间:(\d{4}-\d{2}-\d{2})', album_info_page, | |
99 | 'publish time', default=None) | |
100 | if publish_time: | |
101 | publish_time = publish_time.replace('-', '') | |
102 | ||
103 | return { | |
104 | 'id': song_id, | |
105 | 'title': song_name, | |
106 | 'creator': singer_name, | |
107 | 'upload_date': publish_time, | |
108 | 'description': lrc_content, | |
109 | 'formats': formats, | |
110 | } | |
111 | ||
112 | ||
113 | class KuwoAlbumIE(InfoExtractor): | |
114 | IE_NAME = 'kuwo:album' | |
115 | _VALID_URL = r'http://www\.kuwo\.cn/album/(?P<id>[0-9]+?)/' | |
116 | _TEST = { | |
117 | 'url': 'http://www.kuwo.cn/album/502294/', | |
118 | 'info_dict': { | |
119 | 'id': '502294', | |
120 | 'title': 'M', | |
121 | 'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c', | |
122 | }, | |
123 | 'playlist_count': 2, | |
124 | } | |
125 | ||
126 | def _real_extract(self, url): | |
127 | album_id = self._match_id(url) | |
128 | ||
129 | webpage = self._download_webpage( | |
130 | url, album_id, note='Download album info', | |
131 | errnote='Unable to get album info') | |
132 | ||
133 | album_name = self._html_search_regex( | |
134 | r'<div class="comm".+?<h1 title="(.+?)">.+?</h1>', webpage, | |
135 | 'album name', flags=re.DOTALL) | |
136 | album_intro = clean_html( | |
137 | re.sub(r'^.+简介:', '', get_element_by_id("intro", webpage).strip())) | |
138 | ||
139 | entries = [ | |
140 | self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id) | |
141 | for song_id in re.findall( | |
142 | r'<p class="listen"><a href="http://www\.kuwo\.cn/yinyue/([0-9]+)/" target="_blank" title="试听.*?"></a></p>', | |
143 | webpage) | |
144 | ] | |
145 | return self.playlist_result(entries, album_id, album_name, album_intro) | |
146 | ||
147 | ||
148 | class KuwoChartIE(InfoExtractor): | |
149 | IE_NAME = 'kuwo:chart' | |
150 | _VALID_URL = r'http://yinyue\.kuwo\.cn/billboard_(?P<id>.+?).htm' | |
151 | _TEST = { | |
152 | 'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm', | |
153 | 'info_dict': { | |
154 | 'id': '香港中文龙虎榜', | |
155 | 'title': '香港中文龙虎榜', | |
156 | 'description': 're:[0-9]{4}第[0-9]{2}期', | |
157 | }, | |
158 | 'playlist_mincount': 10, | |
159 | } | |
160 | ||
161 | def _real_extract(self, url): | |
162 | chart_id = self._match_id(url) | |
163 | webpage = self._download_webpage( | |
164 | url, chart_id, note='Download chart info', | |
165 | errnote='Unable to get chart info') | |
166 | ||
167 | chart_name = self._html_search_regex( | |
168 | r'<h1 class="unDis">(.+?)</h1>', webpage, 'chart name') | |
169 | ||
170 | chart_desc = self._html_search_regex( | |
171 | r'<p class="tabDef">([0-9]{4}第[0-9]{2}期)</p>', webpage, 'chart desc') | |
172 | ||
173 | entries = [ | |
174 | self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id) | |
175 | for song_id in re.findall( | |
176 | r'<a href="http://www\.kuwo\.cn/yinyue/([0-9]+)/" .+?>.+?</a>', webpage) | |
177 | ] | |
178 | return self.playlist_result(entries, chart_id, chart_name, chart_desc) | |
179 | ||
180 | ||
181 | class KuwoSingerIE(InfoExtractor): | |
182 | IE_NAME = 'kuwo:singer' | |
183 | _VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P<id>[^/]+?)/$' | |
184 | _TEST = { | |
185 | 'url': 'http://www.kuwo.cn/mingxing/bruno+mars/', | |
186 | 'info_dict': { | |
187 | 'id': 'bruno+mars', | |
188 | 'title': 'Bruno Mars', | |
189 | }, | |
190 | 'playlist_count': 10, | |
191 | } | |
192 | ||
193 | def _real_extract(self, url): | |
194 | singer_id = self._match_id(url) | |
195 | webpage = self._download_webpage( | |
196 | url, singer_id, note='Download singer info', | |
197 | errnote='Unable to get singer info') | |
198 | ||
199 | singer_name = self._html_search_regex( | |
200 | r'姓名:<span>(.+?)</span>', webpage, 'singer name') | |
201 | ||
202 | entries = [ | |
203 | self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id) | |
204 | for song_id in re.findall( | |
205 | r'<a href="http://www\.kuwo\.cn/yinyue/([0-9]+)/" .+?>.+?</a>', | |
206 | webpage, flags=re.DOTALL) | |
207 | ] | |
208 | return self.playlist_result(entries, singer_id, singer_name) | |
209 | ||
210 | ||
211 | class KuwoSingerMusicIE(InfoExtractor): | |
212 | IE_NAME = 'kuwo:singermusic' | |
213 | _VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P<id>[^/]+?)/music(_[0-9]+)?.htm' | |
214 | _TEST = { | |
215 | 'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm', | |
216 | 'info_dict': { | |
217 | 'id': 'Ali', | |
218 | 'title': 'Ali的热门歌曲', | |
219 | }, | |
220 | 'playlist_mincount': 95, | |
221 | } | |
222 | ||
223 | def _real_extract(self, url): | |
224 | singer_id = self._match_id(url) | |
225 | ||
226 | list_name = None | |
227 | entries = [] | |
228 | for page_num in itertools.count(1): | |
229 | webpage = self._download_webpage( | |
230 | 'http://www.kuwo.cn/mingxing/%s/music_%d.htm' % (singer_id, page_num), | |
231 | singer_id, note='Download song list page #%d' % page_num, | |
232 | errnote='Unable to get song list page #%d' % page_num) | |
233 | ||
234 | if list_name is None: | |
235 | list_name = self._html_search_regex( | |
236 | r'<h1>([^<>]+)<span>', webpage, 'list name') | |
237 | ||
238 | entries.extend([ | |
239 | self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id) | |
240 | for song_id in re.findall( | |
241 | r'<p class="m_name"><a href="http://www\.kuwo\.cn/yinyue/([0-9]+)/', | |
242 | webpage) | |
243 | ]) | |
244 | if not re.search(r'<a href="[^"]+">下一页</a>', webpage): | |
245 | break | |
246 | ||
247 | return self.playlist_result(entries, singer_id, list_name) | |
248 | ||
249 | ||
250 | class KuwoCategoryIE(InfoExtractor): | |
251 | IE_NAME = 'kuwo:category' | |
252 | _VALID_URL = r'http://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>[0-9]+?).htm' | |
253 | _TEST = { | |
254 | 'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm', | |
255 | 'info_dict': { | |
256 | 'id': '86375', | |
257 | 'title': '八十年代精选', | |
258 | 'description': '这些都是属于八十年代的回忆!', | |
259 | }, | |
260 | 'playlist_count': 30, | |
261 | } | |
262 | ||
263 | def _real_extract(self, url): | |
264 | category_id = self._match_id(url) | |
265 | webpage = self._download_webpage( | |
266 | url, category_id, note='Download category info', | |
267 | errnote='Unable to get category info') | |
268 | ||
269 | category_name = self._html_search_regex( | |
270 | r'<h1 title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name') | |
271 | ||
272 | category_desc = re.sub( | |
273 | r'^.+简介:', '', get_element_by_id("intro", webpage).strip()) | |
274 | ||
275 | jsonm = self._parse_json(self._html_search_regex( | |
276 | r'var jsonm = (\{.+?\});', webpage, 'category songs'), category_id) | |
277 | ||
278 | entries = [ | |
279 | self.url_result( | |
280 | "http://www.kuwo.cn/yinyue/%s/" % song['musicrid'], | |
281 | 'Kuwo', song['musicrid']) | |
282 | for song in jsonm['musiclist'] | |
283 | ] | |
284 | return self.playlist_result(entries, category_id, category_name, category_desc) | |
285 | ||
286 | ||
287 | class KuwoMvIE(KuwoIE): | |
288 | IE_NAME = 'kuwo:mv' | |
289 | _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P<id>[0-9]+?)/' | |
290 | _TESTS = [{ | |
291 | 'url': 'http://www.kuwo.cn/mv/6480076/', | |
292 | 'info_dict': { | |
293 | 'id': '6480076', | |
294 | 'ext': 'mkv', | |
295 | 'title': '我们家MV', | |
296 | 'creator': '2PM', | |
297 | }, | |
298 | }] | |
299 | _FORMATS = KuwoIE._FORMATS + [ | |
300 | {'format': 'mkv', 'ext': 'mkv', 'preference': 250}, | |
301 | {'format': 'mp4', 'ext': 'mp4', 'preference': 200}, | |
302 | ] | |
303 | ||
304 | def _real_extract(self, url): | |
305 | song_id = self._match_id(url) | |
306 | webpage = self._download_webpage( | |
307 | url, song_id, note='Download mv detail info: %s' % song_id, | |
308 | errnote='Unable to get mv detail info: %s' % song_id) | |
309 | ||
310 | mobj = re.search( | |
311 | r'<h1 title="(?P<song>.+?)">[^<>]+<span .+?title="(?P<singer>.+?)".+?>[^<>]+</span></h1>', | |
312 | webpage) | |
313 | if mobj: | |
314 | song_name = mobj.group('song') | |
315 | singer_name = mobj.group('singer') | |
316 | else: | |
317 | raise ExtractorError("Unable to find song or singer names") | |
318 | ||
319 | formats = self._get_formats(song_id) | |
320 | ||
321 | return { | |
322 | 'id': song_id, | |
323 | 'title': song_name, | |
324 | 'creator': singer_name, | |
325 | 'formats': formats, | |
326 | } |