]>
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, | |
a31e3e7d | 12 | remove_start, |
8f73e89c | 13 | ) |
14 | ||
15 | ||
16 | class KuwoIE(InfoExtractor): | |
17 | IE_NAME = 'kuwo:song' | |
18 | _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P<id>[0-9]+?)/' | |
19 | _TESTS = [{ | |
20 | 'url': 'http://www.kuwo.cn/yinyue/635632/', | |
21 | 'info_dict': { | |
22 | 'id': '635632', | |
23 | 'ext': 'ape', | |
24 | 'title': '爱我别走', | |
25 | 'creator': '张震岳', | |
26 | 'upload_date': '20080122', | |
27 | 'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c' | |
28 | }, | |
29 | }, { | |
30 | 'url': 'http://www.kuwo.cn/yinyue/6446136/', | |
31 | 'info_dict': { | |
32 | 'id': '6446136', | |
33 | 'ext': 'mp3', | |
34 | 'title': '心', | |
35 | 'creator': 'IU', | |
36 | 'upload_date': '20150518', | |
37 | }, | |
38 | 'params': { | |
39 | 'format': 'mp3-320' | |
40 | }, | |
41 | }] | |
42 | _FORMATS = [ | |
43 | {'format': 'ape', 'ext': 'ape', 'preference': 100}, | |
44 | {'format': 'mp3-320', 'ext': 'mp3', 'br': '320kmp3', 'abr': 320, 'preference': 80}, | |
45 | {'format': 'mp3-192', 'ext': 'mp3', 'br': '192kmp3', 'abr': 192, 'preference': 70}, | |
46 | {'format': 'mp3-128', 'ext': 'mp3', 'br': '128kmp3', 'abr': 128, 'preference': 60}, | |
47 | {'format': 'wma', 'ext': 'wma', 'preference': 20}, | |
48 | {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10} | |
49 | ] | |
50 | ||
51 | def _get_formats(self, song_id): | |
52 | formats = [] | |
53 | for file_format in self._FORMATS: | |
54 | song_url = self._download_webpage( | |
55 | "http://antiserver.kuwo.cn/anti.s?format=%s&br=%s&rid=MUSIC_%s&type=convert_url&response=url" % | |
56 | (file_format['ext'], file_format.get('br', ''), song_id), | |
57 | song_id, note="Download %s url info" % file_format["format"], | |
58 | ) | |
59 | if song_url.startswith('http://') or song_url.startswith('https://'): | |
60 | formats.append({ | |
61 | 'url': song_url, | |
62 | 'format_id': file_format['format'], | |
63 | 'format': file_format['format'], | |
64 | 'preference': file_format['preference'], | |
65 | 'abr': file_format.get('abr'), | |
66 | }) | |
67 | self._sort_formats(formats) | |
68 | return formats | |
69 | ||
70 | def _real_extract(self, url): | |
71 | song_id = self._match_id(url) | |
72 | webpage = self._download_webpage( | |
73 | url, song_id, note='Download song detail info', | |
74 | errnote='Unable to get song detail info') | |
75 | ||
76 | song_name = self._html_search_regex( | |
a31e3e7d | 77 | r'<h1[^>]+title="([^"]+)">', webpage, 'song name') |
8f73e89c | 78 | singer_name = self._html_search_regex( |
a31e3e7d YCH |
79 | r'<div[^>]+class="s_img">\s*<a[^>]+title="([^>]+)"', |
80 | webpage, 'singer name', default=None) | |
8f73e89c | 81 | lrc_content = clean_html(get_element_by_id("lrcContent", webpage)) |
82 | if lrc_content == '暂无': # indicates no lyrics | |
83 | lrc_content = None | |
84 | ||
85 | formats = self._get_formats(song_id) | |
86 | ||
87 | album_id = self._html_search_regex( | |
a31e3e7d | 88 | r'<p[^>]+class="album"[^<]+<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"', |
8f73e89c | 89 | webpage, 'album id', default=None, fatal=False) |
90 | ||
91 | publish_time = None | |
92 | if album_id is not None: | |
93 | album_info_page = self._download_webpage( | |
94 | "http://www.kuwo.cn/album/%s/" % album_id, song_id, | |
95 | note='Download album detail info', | |
96 | errnote='Unable to get album detail info') | |
97 | ||
98 | publish_time = self._html_search_regex( | |
99 | r'发行时间:(\d{4}-\d{2}-\d{2})', album_info_page, | |
100 | 'publish time', default=None) | |
101 | if publish_time: | |
102 | publish_time = publish_time.replace('-', '') | |
103 | ||
104 | return { | |
105 | 'id': song_id, | |
106 | 'title': song_name, | |
107 | 'creator': singer_name, | |
108 | 'upload_date': publish_time, | |
109 | 'description': lrc_content, | |
110 | 'formats': formats, | |
111 | } | |
112 | ||
113 | ||
114 | class KuwoAlbumIE(InfoExtractor): | |
115 | IE_NAME = 'kuwo:album' | |
116 | _VALID_URL = r'http://www\.kuwo\.cn/album/(?P<id>[0-9]+?)/' | |
117 | _TEST = { | |
118 | 'url': 'http://www.kuwo.cn/album/502294/', | |
119 | 'info_dict': { | |
120 | 'id': '502294', | |
121 | 'title': 'M', | |
122 | 'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c', | |
123 | }, | |
124 | 'playlist_count': 2, | |
125 | } | |
126 | ||
127 | def _real_extract(self, url): | |
128 | album_id = self._match_id(url) | |
129 | ||
130 | webpage = self._download_webpage( | |
131 | url, album_id, note='Download album info', | |
132 | errnote='Unable to get album info') | |
133 | ||
134 | album_name = self._html_search_regex( | |
a31e3e7d YCH |
135 | r'<div[^>]+class="comm"[^<]+<h1[^>]+title="([^"]+)"', webpage, |
136 | 'album name') | |
137 | album_intro = remove_start( | |
138 | clean_html(get_element_by_id("intro", webpage)), | |
139 | '%s简介:' % album_name) | |
8f73e89c | 140 | |
141 | entries = [ | |
142 | self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id) | |
143 | for song_id in re.findall( | |
a31e3e7d | 144 | r'<p[^>]+class="listen"><a[^>]+href="http://www\.kuwo\.cn/yinyue/(\d+)/"', |
8f73e89c | 145 | webpage) |
146 | ] | |
147 | return self.playlist_result(entries, album_id, album_name, album_intro) | |
148 | ||
149 | ||
150 | class KuwoChartIE(InfoExtractor): | |
151 | IE_NAME = 'kuwo:chart' | |
a31e3e7d | 152 | _VALID_URL = r'http://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm' |
8f73e89c | 153 | _TEST = { |
154 | 'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm', | |
155 | 'info_dict': { | |
156 | 'id': '香港中文龙虎榜', | |
157 | 'title': '香港中文龙虎榜', | |
158 | 'description': 're:[0-9]{4}第[0-9]{2}期', | |
159 | }, | |
160 | 'playlist_mincount': 10, | |
161 | } | |
162 | ||
163 | def _real_extract(self, url): | |
164 | chart_id = self._match_id(url) | |
165 | webpage = self._download_webpage( | |
166 | url, chart_id, note='Download chart info', | |
167 | errnote='Unable to get chart info') | |
168 | ||
169 | chart_name = self._html_search_regex( | |
a31e3e7d | 170 | r'<h1[^>]+class="unDis">([^<]+)</h1>', webpage, 'chart name') |
8f73e89c | 171 | |
172 | chart_desc = self._html_search_regex( | |
a31e3e7d | 173 | r'<p[^>]+class="tabDef">(\d{4}第\d{2}期)</p>', webpage, 'chart desc') |
8f73e89c | 174 | |
175 | entries = [ | |
176 | self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id) | |
177 | for song_id in re.findall( | |
a31e3e7d | 178 | r'<a[^>]+href="http://www\.kuwo\.cn/yinyue/(\d+)/"', webpage) |
8f73e89c | 179 | ] |
180 | return self.playlist_result(entries, chart_id, chart_name, chart_desc) | |
181 | ||
182 | ||
183 | class KuwoSingerIE(InfoExtractor): | |
184 | IE_NAME = 'kuwo:singer' | |
1633491b | 185 | _VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)' |
186 | _TESTS = [{ | |
8f73e89c | 187 | 'url': 'http://www.kuwo.cn/mingxing/bruno+mars/', |
188 | 'info_dict': { | |
189 | 'id': 'bruno+mars', | |
190 | 'title': 'Bruno Mars', | |
191 | }, | |
192 | 'playlist_count': 10, | |
1633491b | 193 | }, { |
8f73e89c | 194 | 'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm', |
195 | 'info_dict': { | |
196 | 'id': 'Ali', | |
1633491b | 197 | 'title': 'Ali', |
8f73e89c | 198 | }, |
199 | 'playlist_mincount': 95, | |
1633491b | 200 | }] |
8f73e89c | 201 | |
202 | def _real_extract(self, url): | |
203 | singer_id = self._match_id(url) | |
1633491b | 204 | webpage = self._download_webpage( |
205 | url, singer_id, note='Download singer info', | |
206 | errnote='Unable to get singer info') | |
207 | ||
208 | singer_name = self._html_search_regex( | |
a31e3e7d | 209 | r'<div class="title clearfix">\s*<h1>([^<]+)<span', webpage, 'singer name' |
1633491b | 210 | ) |
8f73e89c | 211 | |
8f73e89c | 212 | entries = [] |
a31e3e7d | 213 | first_page_only = False if re.search(r'/music(?:_[0-9]+)?\.htm', url) else True |
8f73e89c | 214 | for page_num in itertools.count(1): |
215 | webpage = self._download_webpage( | |
216 | 'http://www.kuwo.cn/mingxing/%s/music_%d.htm' % (singer_id, page_num), | |
217 | singer_id, note='Download song list page #%d' % page_num, | |
218 | errnote='Unable to get song list page #%d' % page_num) | |
219 | ||
8f73e89c | 220 | entries.extend([ |
221 | self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id) | |
222 | for song_id in re.findall( | |
a31e3e7d | 223 | r'<p[^>]+class="m_name"><a[^>]+href="http://www\.kuwo\.cn/yinyue/([0-9]+)/', |
8f73e89c | 224 | webpage) |
1633491b | 225 | ][:10 if first_page_only else None]) |
226 | ||
a31e3e7d | 227 | if first_page_only or not re.search(r'<a[^>]+href="[^"]+">下一页</a>', webpage): |
8f73e89c | 228 | break |
229 | ||
1633491b | 230 | return self.playlist_result(entries, singer_id, singer_name) |
8f73e89c | 231 | |
232 | ||
233 | class KuwoCategoryIE(InfoExtractor): | |
234 | IE_NAME = 'kuwo:category' | |
235 | _VALID_URL = r'http://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>[0-9]+?).htm' | |
236 | _TEST = { | |
237 | 'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm', | |
238 | 'info_dict': { | |
239 | 'id': '86375', | |
240 | 'title': '八十年代精选', | |
241 | 'description': '这些都是属于八十年代的回忆!', | |
242 | }, | |
243 | 'playlist_count': 30, | |
244 | } | |
245 | ||
246 | def _real_extract(self, url): | |
247 | category_id = self._match_id(url) | |
248 | webpage = self._download_webpage( | |
249 | url, category_id, note='Download category info', | |
250 | errnote='Unable to get category info') | |
251 | ||
252 | category_name = self._html_search_regex( | |
a31e3e7d | 253 | r'<h1[^>]+title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name') |
a34af8d0 | 254 | |
a31e3e7d YCH |
255 | category_desc = remove_start( |
256 | get_element_by_id("intro", webpage).strip(), | |
257 | '%s简介:' % category_name) | |
a34af8d0 | 258 | |
8f73e89c | 259 | jsonm = self._parse_json(self._html_search_regex( |
a31e3e7d | 260 | r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id) |
8f73e89c | 261 | |
262 | entries = [ | |
263 | self.url_result( | |
264 | "http://www.kuwo.cn/yinyue/%s/" % song['musicrid'], | |
265 | 'Kuwo', song['musicrid']) | |
266 | for song in jsonm['musiclist'] | |
267 | ] | |
268 | return self.playlist_result(entries, category_id, category_name, category_desc) | |
269 | ||
270 | ||
271 | class KuwoMvIE(KuwoIE): | |
272 | IE_NAME = 'kuwo:mv' | |
273 | _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P<id>[0-9]+?)/' | |
274 | _TESTS = [{ | |
275 | 'url': 'http://www.kuwo.cn/mv/6480076/', | |
276 | 'info_dict': { | |
277 | 'id': '6480076', | |
278 | 'ext': 'mkv', | |
279 | 'title': '我们家MV', | |
280 | 'creator': '2PM', | |
281 | }, | |
282 | }] | |
283 | _FORMATS = KuwoIE._FORMATS + [ | |
284 | {'format': 'mkv', 'ext': 'mkv', 'preference': 250}, | |
285 | {'format': 'mp4', 'ext': 'mp4', 'preference': 200}, | |
286 | ] | |
287 | ||
288 | def _real_extract(self, url): | |
289 | song_id = self._match_id(url) | |
290 | webpage = self._download_webpage( | |
291 | url, song_id, note='Download mv detail info: %s' % song_id, | |
292 | errnote='Unable to get mv detail info: %s' % song_id) | |
293 | ||
294 | mobj = re.search( | |
a31e3e7d | 295 | r'<h1[^>]+title="(?P<song>[^"]+)">[^<]+<span[^>]+title="(?P<singer>[^"]+)"', |
8f73e89c | 296 | webpage) |
297 | if mobj: | |
298 | song_name = mobj.group('song') | |
299 | singer_name = mobj.group('singer') | |
300 | else: | |
301 | raise ExtractorError("Unable to find song or singer names") | |
302 | ||
303 | formats = self._get_formats(song_id) | |
304 | ||
305 | return { | |
306 | 'id': song_id, | |
307 | 'title': song_name, | |
308 | 'creator': singer_name, | |
309 | 'formats': formats, | |
310 | } |