]>
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 | ||
a9684c0d | 16 | class KuwoBaseIE(InfoExtractor): |
8f73e89c | 17 | _FORMATS = [ |
18 | {'format': 'ape', 'ext': 'ape', 'preference': 100}, | |
19 | {'format': 'mp3-320', 'ext': 'mp3', 'br': '320kmp3', 'abr': 320, 'preference': 80}, | |
20 | {'format': 'mp3-192', 'ext': 'mp3', 'br': '192kmp3', 'abr': 192, 'preference': 70}, | |
21 | {'format': 'mp3-128', 'ext': 'mp3', 'br': '128kmp3', 'abr': 128, 'preference': 60}, | |
22 | {'format': 'wma', 'ext': 'wma', 'preference': 20}, | |
23 | {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10} | |
24 | ] | |
25 | ||
26 | def _get_formats(self, song_id): | |
27 | formats = [] | |
28 | for file_format in self._FORMATS: | |
29 | song_url = self._download_webpage( | |
cf2c5fda | 30 | 'http://antiserver.kuwo.cn/anti.s?format=%s&br=%s&rid=MUSIC_%s&type=convert_url&response=url' % |
8f73e89c | 31 | (file_format['ext'], file_format.get('br', ''), song_id), |
cf2c5fda | 32 | song_id, note='Download %s url info' % file_format['format'], |
8f73e89c | 33 | ) |
58be9220 YCH |
34 | |
35 | if song_url == 'IPDeny': | |
36 | raise ExtractorError('This song is blocked in this region', expected=True) | |
37 | ||
8f73e89c | 38 | if song_url.startswith('http://') or song_url.startswith('https://'): |
39 | formats.append({ | |
40 | 'url': song_url, | |
41 | 'format_id': file_format['format'], | |
42 | 'format': file_format['format'], | |
43 | 'preference': file_format['preference'], | |
44 | 'abr': file_format.get('abr'), | |
45 | }) | |
46 | self._sort_formats(formats) | |
47 | return formats | |
48 | ||
a9684c0d YCH |
49 | |
50 | class KuwoIE(KuwoBaseIE): | |
51 | IE_NAME = 'kuwo:song' | |
0f08d7f8 | 52 | IE_DESC = '酷我音乐' |
9f01c1a8 | 53 | _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P<id>\d+?)/' |
a9684c0d YCH |
54 | _TESTS = [{ |
55 | 'url': 'http://www.kuwo.cn/yinyue/635632/', | |
56 | 'info_dict': { | |
57 | 'id': '635632', | |
58 | 'ext': 'ape', | |
59 | 'title': '爱我别走', | |
60 | 'creator': '张震岳', | |
61 | 'upload_date': '20080122', | |
62 | 'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c' | |
63 | }, | |
c44c7895 | 64 | 'skip': 'this song has been offline because of copyright issues', |
a9684c0d YCH |
65 | }, { |
66 | 'url': 'http://www.kuwo.cn/yinyue/6446136/', | |
67 | 'info_dict': { | |
68 | 'id': '6446136', | |
69 | 'ext': 'mp3', | |
70 | 'title': '心', | |
e048d87f | 71 | 'description': 'md5:b2ab6295d014005bfc607525bfc1e38a', |
a9684c0d YCH |
72 | 'creator': 'IU', |
73 | 'upload_date': '20150518', | |
74 | }, | |
75 | 'params': { | |
76 | 'format': 'mp3-320' | |
77 | }, | |
78 | }] | |
79 | ||
8f73e89c | 80 | def _real_extract(self, url): |
81 | song_id = self._match_id(url) | |
82 | webpage = self._download_webpage( | |
83 | url, song_id, note='Download song detail info', | |
84 | errnote='Unable to get song detail info') | |
5db34f68 | 85 | if '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: |
71936506 | 86 | raise ExtractorError('this song has been offline because of copyright issues', expected=True) |
8f73e89c | 87 | |
88 | song_name = self._html_search_regex( | |
5db34f68 | 89 | r'(?s)class="(?:[^"\s]+\s+)*title(?:\s+[^"\s]+)*".*?<h1[^>]+title="([^"]+)"', webpage, 'song name') |
8f73e89c | 90 | singer_name = self._html_search_regex( |
a31e3e7d | 91 | r'<div[^>]+class="s_img">\s*<a[^>]+title="([^>]+)"', |
094790d2 | 92 | webpage, 'singer name', fatal=False) |
cf2c5fda | 93 | lrc_content = clean_html(get_element_by_id('lrcContent', webpage)) |
8f73e89c | 94 | if lrc_content == '暂无': # indicates no lyrics |
95 | lrc_content = None | |
96 | ||
97 | formats = self._get_formats(song_id) | |
98 | ||
99 | album_id = self._html_search_regex( | |
a31e3e7d | 100 | r'<p[^>]+class="album"[^<]+<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"', |
094790d2 | 101 | webpage, 'album id', fatal=False) |
8f73e89c | 102 | |
103 | publish_time = None | |
104 | if album_id is not None: | |
105 | album_info_page = self._download_webpage( | |
cf2c5fda | 106 | 'http://www.kuwo.cn/album/%s/' % album_id, song_id, |
8f73e89c | 107 | note='Download album detail info', |
108 | errnote='Unable to get album detail info') | |
109 | ||
110 | publish_time = self._html_search_regex( | |
111 | r'发行时间:(\d{4}-\d{2}-\d{2})', album_info_page, | |
094790d2 | 112 | 'publish time', fatal=False) |
8f73e89c | 113 | if publish_time: |
114 | publish_time = publish_time.replace('-', '') | |
115 | ||
116 | return { | |
117 | 'id': song_id, | |
118 | 'title': song_name, | |
119 | 'creator': singer_name, | |
120 | 'upload_date': publish_time, | |
121 | 'description': lrc_content, | |
122 | 'formats': formats, | |
123 | } | |
124 | ||
125 | ||
126 | class KuwoAlbumIE(InfoExtractor): | |
127 | IE_NAME = 'kuwo:album' | |
edd66be5 | 128 | IE_DESC = '酷我音乐 - 专辑' |
9f01c1a8 | 129 | _VALID_URL = r'http://www\.kuwo\.cn/album/(?P<id>\d+?)/' |
8f73e89c | 130 | _TEST = { |
131 | 'url': 'http://www.kuwo.cn/album/502294/', | |
132 | 'info_dict': { | |
133 | 'id': '502294', | |
134 | 'title': 'M', | |
135 | 'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c', | |
136 | }, | |
137 | 'playlist_count': 2, | |
138 | } | |
139 | ||
140 | def _real_extract(self, url): | |
141 | album_id = self._match_id(url) | |
142 | ||
143 | webpage = self._download_webpage( | |
144 | url, album_id, note='Download album info', | |
145 | errnote='Unable to get album info') | |
146 | ||
147 | album_name = self._html_search_regex( | |
a31e3e7d YCH |
148 | r'<div[^>]+class="comm"[^<]+<h1[^>]+title="([^"]+)"', webpage, |
149 | 'album name') | |
150 | album_intro = remove_start( | |
cf2c5fda | 151 | clean_html(get_element_by_id('intro', webpage)), |
a31e3e7d | 152 | '%s简介:' % album_name) |
8f73e89c | 153 | |
154 | entries = [ | |
d3b89088 YCH |
155 | self.url_result(song_url, 'Kuwo') for song_url in re.findall( |
156 | r'<p[^>]+class="listen"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"', | |
8f73e89c | 157 | webpage) |
158 | ] | |
159 | return self.playlist_result(entries, album_id, album_name, album_intro) | |
160 | ||
161 | ||
162 | class KuwoChartIE(InfoExtractor): | |
163 | IE_NAME = 'kuwo:chart' | |
edd66be5 | 164 | IE_DESC = '酷我音乐 - 排行榜' |
a31e3e7d | 165 | _VALID_URL = r'http://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm' |
8f73e89c | 166 | _TEST = { |
167 | 'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm', | |
168 | 'info_dict': { | |
169 | 'id': '香港中文龙虎榜', | |
170 | 'title': '香港中文龙虎榜', | |
9f01c1a8 | 171 | 'description': 're:\d{4}第\d{2}期', |
8f73e89c | 172 | }, |
173 | 'playlist_mincount': 10, | |
174 | } | |
175 | ||
176 | def _real_extract(self, url): | |
177 | chart_id = self._match_id(url) | |
178 | webpage = self._download_webpage( | |
179 | url, chart_id, note='Download chart info', | |
180 | errnote='Unable to get chart info') | |
181 | ||
182 | chart_name = self._html_search_regex( | |
a31e3e7d | 183 | r'<h1[^>]+class="unDis">([^<]+)</h1>', webpage, 'chart name') |
8f73e89c | 184 | |
185 | chart_desc = self._html_search_regex( | |
a31e3e7d | 186 | r'<p[^>]+class="tabDef">(\d{4}第\d{2}期)</p>', webpage, 'chart desc') |
8f73e89c | 187 | |
188 | entries = [ | |
d3b89088 YCH |
189 | self.url_result(song_url, 'Kuwo') for song_url in re.findall( |
190 | r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/"', webpage) | |
8f73e89c | 191 | ] |
192 | return self.playlist_result(entries, chart_id, chart_name, chart_desc) | |
193 | ||
194 | ||
195 | class KuwoSingerIE(InfoExtractor): | |
196 | IE_NAME = 'kuwo:singer' | |
edd66be5 | 197 | IE_DESC = '酷我音乐 - 歌手' |
1633491b | 198 | _VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)' |
199 | _TESTS = [{ | |
8f73e89c | 200 | 'url': 'http://www.kuwo.cn/mingxing/bruno+mars/', |
201 | 'info_dict': { | |
202 | 'id': 'bruno+mars', | |
203 | 'title': 'Bruno Mars', | |
204 | }, | |
205 | 'playlist_count': 10, | |
1633491b | 206 | }, { |
8f73e89c | 207 | 'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm', |
208 | 'info_dict': { | |
209 | 'id': 'Ali', | |
1633491b | 210 | 'title': 'Ali', |
8f73e89c | 211 | }, |
212 | 'playlist_mincount': 95, | |
12bbd32a | 213 | 'skip': 'Regularly stalls travis build', # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540 |
1633491b | 214 | }] |
8f73e89c | 215 | |
216 | def _real_extract(self, url): | |
217 | singer_id = self._match_id(url) | |
1633491b | 218 | webpage = self._download_webpage( |
219 | url, singer_id, note='Download singer info', | |
220 | errnote='Unable to get singer info') | |
221 | ||
222 | singer_name = self._html_search_regex( | |
a31e3e7d | 223 | r'<div class="title clearfix">\s*<h1>([^<]+)<span', webpage, 'singer name' |
1633491b | 224 | ) |
8f73e89c | 225 | |
8f73e89c | 226 | entries = [] |
9f01c1a8 | 227 | first_page_only = False if re.search(r'/music(?:_\d+)?\.htm', url) else True |
8f73e89c | 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 | ||
8f73e89c | 234 | entries.extend([ |
d3b89088 YCH |
235 | self.url_result(song_url, 'Kuwo') for song_url in re.findall( |
236 | r'<p[^>]+class="m_name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/', | |
8f73e89c | 237 | webpage) |
1633491b | 238 | ][:10 if first_page_only else None]) |
239 | ||
a31e3e7d | 240 | if first_page_only or not re.search(r'<a[^>]+href="[^"]+">下一页</a>', webpage): |
8f73e89c | 241 | break |
242 | ||
1633491b | 243 | return self.playlist_result(entries, singer_id, singer_name) |
8f73e89c | 244 | |
245 | ||
246 | class KuwoCategoryIE(InfoExtractor): | |
247 | IE_NAME = 'kuwo:category' | |
edd66be5 | 248 | IE_DESC = '酷我音乐 - 分类' |
9f01c1a8 | 249 | _VALID_URL = r'http://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm' |
8f73e89c | 250 | _TEST = { |
251 | 'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm', | |
252 | 'info_dict': { | |
253 | 'id': '86375', | |
254 | 'title': '八十年代精选', | |
255 | 'description': '这些都是属于八十年代的回忆!', | |
256 | }, | |
257 | 'playlist_count': 30, | |
258 | } | |
259 | ||
260 | def _real_extract(self, url): | |
261 | category_id = self._match_id(url) | |
262 | webpage = self._download_webpage( | |
263 | url, category_id, note='Download category info', | |
264 | errnote='Unable to get category info') | |
265 | ||
266 | category_name = self._html_search_regex( | |
a31e3e7d | 267 | r'<h1[^>]+title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name') |
a34af8d0 | 268 | |
a31e3e7d | 269 | category_desc = remove_start( |
cf2c5fda | 270 | get_element_by_id('intro', webpage).strip(), |
a31e3e7d | 271 | '%s简介:' % category_name) |
a34af8d0 | 272 | |
8f73e89c | 273 | jsonm = self._parse_json(self._html_search_regex( |
a31e3e7d | 274 | r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id) |
8f73e89c | 275 | |
276 | entries = [ | |
d3b89088 | 277 | self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo') |
8f73e89c | 278 | for song in jsonm['musiclist'] |
279 | ] | |
280 | return self.playlist_result(entries, category_id, category_name, category_desc) | |
281 | ||
282 | ||
a9684c0d | 283 | class KuwoMvIE(KuwoBaseIE): |
8f73e89c | 284 | IE_NAME = 'kuwo:mv' |
edd66be5 | 285 | IE_DESC = '酷我音乐 - MV' |
9f01c1a8 | 286 | _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P<id>\d+?)/' |
a9684c0d | 287 | _TEST = { |
8f73e89c | 288 | 'url': 'http://www.kuwo.cn/mv/6480076/', |
289 | 'info_dict': { | |
290 | 'id': '6480076', | |
291 | 'ext': 'mkv', | |
292 | 'title': '我们家MV', | |
293 | 'creator': '2PM', | |
294 | }, | |
a9684c0d YCH |
295 | } |
296 | _FORMATS = KuwoBaseIE._FORMATS + [ | |
8f73e89c | 297 | {'format': 'mkv', 'ext': 'mkv', 'preference': 250}, |
298 | {'format': 'mp4', 'ext': 'mp4', 'preference': 200}, | |
299 | ] | |
300 | ||
301 | def _real_extract(self, url): | |
302 | song_id = self._match_id(url) | |
303 | webpage = self._download_webpage( | |
304 | url, song_id, note='Download mv detail info: %s' % song_id, | |
305 | errnote='Unable to get mv detail info: %s' % song_id) | |
306 | ||
307 | mobj = re.search( | |
a31e3e7d | 308 | r'<h1[^>]+title="(?P<song>[^"]+)">[^<]+<span[^>]+title="(?P<singer>[^"]+)"', |
8f73e89c | 309 | webpage) |
310 | if mobj: | |
311 | song_name = mobj.group('song') | |
312 | singer_name = mobj.group('singer') | |
313 | else: | |
cf2c5fda | 314 | raise ExtractorError('Unable to find song or singer names') |
8f73e89c | 315 | |
316 | formats = self._get_formats(song_id) | |
317 | ||
318 | return { | |
319 | 'id': song_id, | |
320 | 'title': song_name, | |
321 | 'creator': singer_name, | |
322 | 'formats': formats, | |
323 | } |