2 from __future__ import unicode_literals
4 from hashlib import md5
5 from base64 import b64encode
6 from datetime import datetime
9 from .common import InfoExtractor
10 from ..compat import (
11 compat_urllib_request,
14 compat_itertools_count,
18 class NetEaseMusicBaseIE(InfoExtractor):
19 _FORMATS = ['bMusic', 'mMusic', 'hMusic']
20 _NETEASE_SALT = '3go8&$8*3*3h0k(2)2'
21 _API_BASE = 'http://music.163.com/api/'
24 def _encrypt(cls, dfsid):
25 salt_bytes = bytearray(cls._NETEASE_SALT.encode('utf-8'))
26 string_bytes = bytearray(compat_str(dfsid).encode('ascii'))
27 salt_len = len(salt_bytes)
28 for i in range(len(string_bytes)):
29 string_bytes[i] = string_bytes[i] ^ salt_bytes[i % salt_len]
31 m.update(bytes(string_bytes))
32 result = b64encode(m.digest()).decode('ascii')
33 return result.replace('/', '_').replace('+', '-')
36 def extract_formats(cls, info):
38 for song_format in cls._FORMATS:
39 details = info.get(song_format)
43 'url': 'http://m1.music.126.net/%s/%s.%s' %
44 (cls._encrypt(details['dfsId']), details['dfsId'],
45 details['extension']),
46 'ext': details.get('extension'),
47 'abr': details.get('bitrate', 0) / 1000,
48 'format_id': song_format,
49 'filesize': details.get('size'),
50 'asr': details.get('sr')
55 def convert_milliseconds(cls, ms):
56 return int(round(ms / 1000.0))
58 def query_api(self, endpoint, video_id, note):
59 req = compat_urllib_request.Request('%s%s' % (self._API_BASE, endpoint))
60 req.add_header('Referer', self._API_BASE)
61 return self._download_json(req, video_id, note)
64 class NetEaseMusicIE(NetEaseMusicBaseIE):
65 IE_NAME = 'netease:song'
67 _VALID_URL = r'https?://music\.163\.com/(#/)?song\?id=(?P<id>[0-9]+)'
69 'url': 'http://music.163.com/#/song?id=32102397',
70 'md5': 'f2e97280e6345c74ba9d5677dd5dcb45',
74 'title': 'Bad Blood (feat. Kendrick Lamar)',
75 'creator': 'Taylor Swift / Kendrick Lamar',
76 'upload_date': '20150517',
77 'timestamp': 1431878400,
78 'description': 'md5:a10a54589c2860300d02e1de821eb2ef',
81 'note': 'No lyrics translation.',
82 'url': 'http://music.163.com/#/song?id=29822014',
88 'upload_date': '20141225',
89 'timestamp': 1419523200,
90 'description': 'md5:a4d8d89f44656af206b7b2555c0bce6c',
94 'url': 'http://music.163.com/song?id=17241424',
99 'creator': 'Dustin O\'Halloran',
100 'upload_date': '20080211',
101 'timestamp': 1202745600,
104 'note': 'Has translated name.',
105 'url': 'http://music.163.com/#/song?id=22735043',
109 'title': '소원을 말해봐 (Genie)',
111 'description': 'md5:79d99cc560e4ca97e0c4d86800ee4184',
112 'upload_date': '20100127',
113 'timestamp': 1264608000,
114 'alt_title': '说出愿望吧(Genie)',
118 def _process_lyrics(self, lyrics_info):
119 original = lyrics_info.get('lrc', {}).get('lyric')
120 translated = lyrics_info.get('tlyric', {}).get('lyric')
125 lyrics_expr = r'(\[[0-9]{2}:[0-9]{2}\.[0-9]{2,}\])([^\n]+)'
126 original_ts_texts = re.findall(lyrics_expr, original)
127 translation_ts_dict = dict(
128 (time_stamp, text) for time_stamp, text in re.findall(lyrics_expr, translated)
131 '%s%s / %s' % (time_stamp, text, translation_ts_dict.get(time_stamp, ''))
132 for time_stamp, text in original_ts_texts
136 def _real_extract(self, url):
137 song_id = self._match_id(url)
141 'ids': '[%s]' % song_id
143 info = self.query_api(
144 'song/detail?' + compat_urllib_parse.urlencode(params),
145 song_id, 'Downloading song info')['songs'][0]
147 formats = self.extract_formats(info)
148 self._sort_formats(formats)
150 lyrics_info = self.query_api(
151 'song/lyric?id=%s&lv=-1&tv=-1' % song_id,
152 song_id, 'Downloading lyrics data')
153 lyrics = self._process_lyrics(lyrics_info)
156 if info.get('transNames'):
157 alt_title = '/'.join(info.get('transNames'))
161 'title': info['name'],
162 'alt_title': alt_title,
163 'creator': ' / '.join([artist['name'] for artist in info.get('artists', [])]),
164 'timestamp': self.convert_milliseconds(info.get('album', {}).get('publishTime')),
165 'thumbnail': info.get('album', {}).get('picUrl'),
166 'duration': self.convert_milliseconds(info.get('duration', 0)),
167 'description': lyrics,
172 class NetEaseMusicAlbumIE(NetEaseMusicBaseIE):
173 IE_NAME = 'netease:album'
174 IE_DESC = '网易云音乐 - 专辑'
175 _VALID_URL = r'https?://music\.163\.com/(#/)?album\?id=(?P<id>[0-9]+)'
177 'url': 'http://music.163.com/#/album?id=220780',
182 'playlist_count': 23,
185 def _real_extract(self, url):
186 album_id = self._match_id(url)
188 info = self.query_api(
189 'album/%s?id=%s' % (album_id, album_id),
190 album_id, 'Downloading album data')['album']
193 desc = info.get('description')
195 self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
196 'NetEaseMusic', song['id'])
197 for song in info['songs']
199 return self.playlist_result(entries, album_id, name, desc)
202 class NetEaseMusicSingerIE(NetEaseMusicBaseIE):
203 IE_NAME = 'netease:singer'
204 IE_DESC = '网易云音乐 - 歌手'
205 _VALID_URL = r'https?://music\.163\.com/(#/)?artist\?id=(?P<id>[0-9]+)'
207 'note': 'Singer has aliases.',
208 'url': 'http://music.163.com/#/artist?id=10559',
211 'title': '张惠妹 - aMEI;阿密特',
213 'playlist_count': 50,
215 'note': 'Singer has translated name.',
216 'url': 'http://music.163.com/#/artist?id=124098',
219 'title': '李昇基 - 이승기',
221 'playlist_count': 50,
224 def _real_extract(self, url):
225 singer_id = self._match_id(url)
227 info = self.query_api(
228 'artist/%s?id=%s' % (singer_id, singer_id),
229 singer_id, 'Downloading singer data')
231 name = info['artist']['name']
232 if info['artist']['trans']:
233 name = '%s - %s' % (name, info['artist']['trans'])
234 if info['artist']['alias']:
235 name = '%s - %s' % (name, ';'.join(info['artist']['alias']))
238 self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
239 'NetEaseMusic', song['id'])
240 for song in info['hotSongs']
242 return self.playlist_result(entries, singer_id, name)
245 class NetEaseMusicListIE(NetEaseMusicBaseIE):
246 IE_NAME = 'netease:playlist'
247 IE_DESC = '网易云音乐 - 歌单'
248 _VALID_URL = r'https?://music\.163\.com/(#/)?(playlist|discover/toplist)\?id=(?P<id>[0-9]+)'
250 'url': 'http://music.163.com/#/playlist?id=79177352',
253 'title': 'Billboard 2007 Top 100',
254 'description': 'md5:12fd0819cab2965b9583ace0f8b7b022'
256 'playlist_count': 99,
258 'note': 'Toplist/Charts sample',
259 'url': 'http://music.163.com/#/discover/toplist?id=3733003',
262 'title': 're:韩国Melon排行榜周榜 [0-9]{4}-[0-9]{2}-[0-9]{2}',
263 'description': 'md5:73ec782a612711cadc7872d9c1e134fc',
265 'playlist_count': 50,
268 def _real_extract(self, url):
269 list_id = self._match_id(url)
271 info = self.query_api(
272 'playlist/detail?id=%s&lv=-1&tv=-1' % list_id,
273 list_id, 'Downloading playlist data')['result']
276 desc = info.get('description')
278 if info.get('specialType') == 10: # is a chart/toplist
279 datestamp = datetime.fromtimestamp(
280 self.convert_milliseconds(info['updateTime'])).strftime('%Y-%m-%d')
281 name = '%s %s' % (name, datestamp)
284 self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
285 'NetEaseMusic', song['id'])
286 for song in info['tracks']
288 return self.playlist_result(entries, list_id, name, desc)
291 class NetEaseMusicMvIE(NetEaseMusicBaseIE):
292 IE_NAME = 'netease:mv'
293 IE_DESC = '网易云音乐 - MV'
294 _VALID_URL = r'https?://music\.163\.com/(#/)?mv\?id=(?P<id>[0-9]+)'
296 'url': 'http://music.163.com/#/mv?id=415350',
300 'title': '이럴거면 그러지말지',
301 'description': '白雅言自作曲唱甜蜜爱情',
303 'upload_date': '20150520',
307 def _real_extract(self, url):
308 mv_id = self._match_id(url)
310 info = self.query_api(
311 'mv/detail?id=%s&type=mp4' % mv_id,
312 mv_id, 'Downloading mv info')['data']
315 {'url': mv_url, 'ext': 'mp4', 'format_id': '%sp' % brs, 'height': int(brs)}
316 for brs, mv_url in info['brs'].items()
318 self._sort_formats(formats)
322 'title': info['name'],
323 'description': info.get('desc') or info.get('briefDesc'),
324 'creator': info['artistName'],
325 'upload_date': info['publishTime'].replace('-', ''),
327 'thumbnail': info.get('cover'),
328 'duration': self.convert_milliseconds(info.get('duration', 0)),
332 class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
333 IE_NAME = 'netease:program'
334 IE_DESC = '网易云音乐 - 电台节目'
335 _VALID_URL = r'https?://music\.163\.com/(#/?)program\?id=(?P<id>[0-9]+)'
337 'url': 'http://music.163.com/#/program?id=10109055',
341 'title': '不丹足球背后的故事',
342 'description': '喜马拉雅人的足球梦 ...',
344 'timestamp': 1434179342,
345 'upload_date': '20150613',
349 'note': 'This program has accompanying songs.',
350 'url': 'http://music.163.com/#/program?id=10141022',
353 'title': '25岁,你是自在如风的少年<27°C>',
354 'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b',
358 'note': 'This program has accompanying songs.',
359 'url': 'http://music.163.com/#/program?id=10141022',
363 'title': '25岁,你是自在如风的少年<27°C>',
364 'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b',
365 'timestamp': 1434450841,
366 'upload_date': '20150616',
373 def _real_extract(self, url):
374 program_id = self._match_id(url)
376 info = self.query_api(
377 'dj/program/detail?id=%s' % program_id,
378 program_id, 'Downloading program info')['program']
381 description = info['description']
383 if not info['songs'] or self._downloader.params.get('noplaylist'):
386 'Downloading just the main audio %s because of --no-playlist'
387 % info['mainSong']['id'])
389 formats = self.extract_formats(info['mainSong'])
390 self._sort_formats(formats)
395 'description': description,
396 'creator': info['dj']['brand'],
397 'timestamp': self.convert_milliseconds(info['createTime']),
398 'thumbnail': info['coverUrl'],
399 'duration': self.convert_milliseconds(info.get('duration', 0)),
404 'Downloading playlist %s - add --no-playlist to just download the main audio %s'
405 % (program_id, info['mainSong']['id']))
407 song_ids = [info['mainSong']['id']]
408 song_ids.extend([song['id'] for song in info['songs']])
410 self.url_result('http://music.163.com/#/song?id=%s' % song_id,
411 'NetEaseMusic', song_id)
412 for song_id in song_ids
414 return self.playlist_result(entries, program_id, name, description)
417 class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE):
418 IE_NAME = 'netease:djradio'
419 IE_DESC = '网易云音乐 - 电台'
420 _VALID_URL = r'https?://music\.163\.com/(#/)?djradio\?id=(?P<id>[0-9]+)'
422 'url': 'http://music.163.com/#/djradio?id=42',
426 'description': 'md5:766220985cbd16fdd552f64c578a6b15'
428 'playlist_mincount': 40,
432 def _real_extract(self, url):
433 dj_id = self._match_id(url)
438 for offset in compat_itertools_count(start=0, step=self._PAGE_SIZE):
439 info = self.query_api(
440 'dj/program/byradio?asc=false&limit=%d&radioId=%s&offset=%d'
441 % (self._PAGE_SIZE, dj_id, offset),
442 dj_id, 'Downloading dj programs - %d' % offset)
446 'http://music.163.com/#/program?id=%s' % program['id'],
447 'NetEaseMusicProgram', program['id'])
448 for program in info['programs']
452 radio = info['programs'][0]['radio']
459 return self.playlist_result(entries, dj_id, name, desc)