[yt-dlp.git] / yt_dlp / extractor / neteasemusic.py

from hashlib import md5
from base64 import b64encode
from datetime import datetime
import re

from .common import InfoExtractor
from ..compat import (
    compat_urllib_parse_urlencode,
    compat_str,
    compat_itertools_count,
)
from ..utils import (
    sanitized_Request,
    float_or_none,
)


class NetEaseMusicBaseIE(InfoExtractor):
    _FORMATS = ['bMusic', 'mMusic', 'hMusic']
    _NETEASE_SALT = '3go8&$8*3*3h0k(2)2'
    _API_BASE = 'http://music.163.com/api/'

    @classmethod
    def _encrypt(cls, dfsid):
        salt_bytes = bytearray(cls._NETEASE_SALT.encode('utf-8'))
        string_bytes = bytearray(compat_str(dfsid).encode('ascii'))
        salt_len = len(salt_bytes)
        for i in range(len(string_bytes)):
            string_bytes[i] = string_bytes[i] ^ salt_bytes[i % salt_len]
        m = md5()
        m.update(bytes(string_bytes))
        result = b64encode(m.digest()).decode('ascii')
        return result.replace('/', '_').replace('+', '-')

    def extract_formats(self, info):
        formats = []
        for song_format in self._FORMATS:
            details = info.get(song_format)
            if not details:
                continue
            song_file_path = '/%s/%s.%s' % (
                self._encrypt(details['dfsId']), details['dfsId'], details['extension'])

            # 203.130.59.9, 124.40.233.182, 115.231.74.139, etc is a reverse proxy-like feature
            # from NetEase's CDN provider that can be used if m5.music.126.net does not
            # work, especially for users outside of Mainland China
            # via: https://github.com/JixunMoe/unblock-163/issues/3#issuecomment-163115880
            for host in ('http://m5.music.126.net', 'http://115.231.74.139/m1.music.126.net',
                         'http://124.40.233.182/m1.music.126.net', 'http://203.130.59.9/m1.music.126.net'):
                song_url = host + song_file_path
                if self._is_valid_url(song_url, info['id'], 'song'):
                    formats.append({
                        'url': song_url,
                        'ext': details.get('extension'),
                        'abr': float_or_none(details.get('bitrate'), scale=1000),
                        'format_id': song_format,
                        'filesize': details.get('size'),
                        'asr': details.get('sr')
                    })
                    break
        return formats

    @classmethod
    def convert_milliseconds(cls, ms):
        return int(round(ms / 1000.0))

    def query_api(self, endpoint, video_id, note):
        req = sanitized_Request('%s%s' % (self._API_BASE, endpoint))
        req.add_header('Referer', self._API_BASE)
        return self._download_json(req, video_id, note)


class NetEaseMusicIE(NetEaseMusicBaseIE):
    IE_NAME = 'netease:song'
    IE_DESC = '网易云音乐'
    _VALID_URL = r'https?://music\.163\.com/(#/)?song\?id=(?P<id>[0-9]+)'
    _TESTS = [{
        'url': 'http://music.163.com/#/song?id=32102397',
        'md5': 'f2e97280e6345c74ba9d5677dd5dcb45',
        'info_dict': {
            'id': '32102397',
            'ext': 'mp3',
            'title': 'Bad Blood (feat. Kendrick Lamar)',
            'creator': 'Taylor Swift / Kendrick Lamar',
            'upload_date': '20150517',
            'timestamp': 1431878400,
            'description': 'md5:a10a54589c2860300d02e1de821eb2ef',
        },
        'skip': 'Blocked outside Mainland China',
    }, {
        'note': 'No lyrics translation.',
        'url': 'http://music.163.com/#/song?id=29822014',
        'info_dict': {
            'id': '29822014',
            'ext': 'mp3',
            'title': '听见下雨的声音',
            'creator': '周杰伦',
            'upload_date': '20141225',
            'timestamp': 1419523200,
            'description': 'md5:a4d8d89f44656af206b7b2555c0bce6c',
        },
        'skip': 'Blocked outside Mainland China',
    }, {
        'note': 'No lyrics.',
        'url': 'http://music.163.com/song?id=17241424',
        'info_dict': {
            'id': '17241424',
            'ext': 'mp3',
            'title': 'Opus 28',
            'creator': 'Dustin O\'Halloran',
            'upload_date': '20080211',
            'timestamp': 1202745600,
        },
        'skip': 'Blocked outside Mainland China',
    }, {
        'note': 'Has translated name.',
        'url': 'http://music.163.com/#/song?id=22735043',
        'info_dict': {
            'id': '22735043',
            'ext': 'mp3',
            'title': '소원을 말해봐 (Genie)',
            'creator': '少女时代',
            'description': 'md5:79d99cc560e4ca97e0c4d86800ee4184',
            'upload_date': '20100127',
            'timestamp': 1264608000,
            'alt_title': '说出愿望吧(Genie)',
        },
        'skip': 'Blocked outside Mainland China',
    }]

    def _process_lyrics(self, lyrics_info):
        original = lyrics_info.get('lrc', {}).get('lyric')
        translated = lyrics_info.get('tlyric', {}).get('lyric')

        if not translated:
            return original

        lyrics_expr = r'(\[[0-9]{2}:[0-9]{2}\.[0-9]{2,}\])([^\n]+)'
        original_ts_texts = re.findall(lyrics_expr, original)
        translation_ts_dict = dict(
            (time_stamp, text) for time_stamp, text in re.findall(lyrics_expr, translated)
        )
        lyrics = '\n'.join([
            '%s%s / %s' % (time_stamp, text, translation_ts_dict.get(time_stamp, ''))
            for time_stamp, text in original_ts_texts
        ])
        return lyrics

    def _real_extract(self, url):
        song_id = self._match_id(url)

        params = {
            'id': song_id,
            'ids': '[%s]' % song_id
        }
        info = self.query_api(
            'song/detail?' + compat_urllib_parse_urlencode(params),
            song_id, 'Downloading song info')['songs'][0]

        formats = self.extract_formats(info)
        self._sort_formats(formats)

        lyrics_info = self.query_api(
            'song/lyric?id=%s&lv=-1&tv=-1' % song_id,
            song_id, 'Downloading lyrics data')
        lyrics = self._process_lyrics(lyrics_info)

        alt_title = None
        if info.get('transNames'):
            alt_title = '/'.join(info.get('transNames'))

        return {
            'id': song_id,
            'title': info['name'],
            'alt_title': alt_title,
            'creator': ' / '.join([artist['name'] for artist in info.get('artists', [])]),
            'timestamp': self.convert_milliseconds(info.get('album', {}).get('publishTime')),
            'thumbnail': info.get('album', {}).get('picUrl'),
            'duration': self.convert_milliseconds(info.get('duration', 0)),
            'description': lyrics,
            'formats': formats,
        }


class NetEaseMusicAlbumIE(NetEaseMusicBaseIE):
    IE_NAME = 'netease:album'
    IE_DESC = '网易云音乐 - 专辑'
    _VALID_URL = r'https?://music\.163\.com/(#/)?album\?id=(?P<id>[0-9]+)'
    _TEST = {
        'url': 'http://music.163.com/#/album?id=220780',
        'info_dict': {
            'id': '220780',
            'title': 'B\'day',
        },
        'playlist_count': 23,
        'skip': 'Blocked outside Mainland China',
    }

    def _real_extract(self, url):
        album_id = self._match_id(url)

        info = self.query_api(
            'album/%s?id=%s' % (album_id, album_id),
            album_id, 'Downloading album data')['album']

        name = info['name']
        desc = info.get('description')
        entries = [
            self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
                            'NetEaseMusic', song['id'])
            for song in info['songs']
        ]
        return self.playlist_result(entries, album_id, name, desc)


class NetEaseMusicSingerIE(NetEaseMusicBaseIE):
    IE_NAME = 'netease:singer'
    IE_DESC = '网易云音乐 - 歌手'
    _VALID_URL = r'https?://music\.163\.com/(#/)?artist\?id=(?P<id>[0-9]+)'
    _TESTS = [{
        'note': 'Singer has aliases.',
        'url': 'http://music.163.com/#/artist?id=10559',
        'info_dict': {
            'id': '10559',
            'title': '张惠妹 - aMEI;阿密特',
        },
        'playlist_count': 50,
        'skip': 'Blocked outside Mainland China',
    }, {
        'note': 'Singer has translated name.',
        'url': 'http://music.163.com/#/artist?id=124098',
        'info_dict': {
            'id': '124098',
            'title': '李昇基 - 이승기',
        },
        'playlist_count': 50,
        'skip': 'Blocked outside Mainland China',
    }]

    def _real_extract(self, url):
        singer_id = self._match_id(url)

        info = self.query_api(
            'artist/%s?id=%s' % (singer_id, singer_id),
            singer_id, 'Downloading singer data')

        name = info['artist']['name']
        if info['artist']['trans']:
            name = '%s - %s' % (name, info['artist']['trans'])
        if info['artist']['alias']:
            name = '%s - %s' % (name, ';'.join(info['artist']['alias']))

        entries = [
            self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
                            'NetEaseMusic', song['id'])
            for song in info['hotSongs']
        ]
        return self.playlist_result(entries, singer_id, name)


class NetEaseMusicListIE(NetEaseMusicBaseIE):
    IE_NAME = 'netease:playlist'
    IE_DESC = '网易云音乐 - 歌单'
    _VALID_URL = r'https?://music\.163\.com/(#/)?(playlist|discover/toplist)\?id=(?P<id>[0-9]+)'
    _TESTS = [{
        'url': 'http://music.163.com/#/playlist?id=79177352',
        'info_dict': {
            'id': '79177352',
            'title': 'Billboard 2007 Top 100',
            'description': 'md5:12fd0819cab2965b9583ace0f8b7b022'
        },
        'playlist_count': 99,
        'skip': 'Blocked outside Mainland China',
    }, {
        'note': 'Toplist/Charts sample',
        'url': 'http://music.163.com/#/discover/toplist?id=3733003',
        'info_dict': {
            'id': '3733003',
            'title': 're:韩国Melon排行榜周榜 [0-9]{4}-[0-9]{2}-[0-9]{2}',
            'description': 'md5:73ec782a612711cadc7872d9c1e134fc',
        },
        'playlist_count': 50,
        'skip': 'Blocked outside Mainland China',
    }]

    def _real_extract(self, url):
        list_id = self._match_id(url)

        info = self.query_api(
            'playlist/detail?id=%s&lv=-1&tv=-1' % list_id,
            list_id, 'Downloading playlist data')['result']

        name = info['name']
        desc = info.get('description')

        if info.get('specialType') == 10:  # is a chart/toplist
            datestamp = datetime.fromtimestamp(
                self.convert_milliseconds(info['updateTime'])).strftime('%Y-%m-%d')
            name = '%s %s' % (name, datestamp)

        entries = [
            self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
                            'NetEaseMusic', song['id'])
            for song in info['tracks']
        ]
        return self.playlist_result(entries, list_id, name, desc)


class NetEaseMusicMvIE(NetEaseMusicBaseIE):
    IE_NAME = 'netease:mv'
    IE_DESC = '网易云音乐 - MV'
    _VALID_URL = r'https?://music\.163\.com/(#/)?mv\?id=(?P<id>[0-9]+)'
    _TEST = {
        'url': 'http://music.163.com/#/mv?id=415350',
        'info_dict': {
            'id': '415350',
            'ext': 'mp4',
            'title': '이럴거면 그러지말지',
            'description': '白雅言自作曲唱甜蜜爱情',
            'creator': '白雅言',
            'upload_date': '20150520',
        },
        'skip': 'Blocked outside Mainland China',
    }

    def _real_extract(self, url):
        mv_id = self._match_id(url)

        info = self.query_api(
            'mv/detail?id=%s&type=mp4' % mv_id,
            mv_id, 'Downloading mv info')['data']

        formats = [
            {'url': mv_url, 'ext': 'mp4', 'format_id': '%sp' % brs, 'height': int(brs)}
            for brs, mv_url in info['brs'].items()
        ]
        self._sort_formats(formats)

        return {
            'id': mv_id,
            'title': info['name'],
            'description': info.get('desc') or info.get('briefDesc'),
            'creator': info['artistName'],
            'upload_date': info['publishTime'].replace('-', ''),
            'formats': formats,
            'thumbnail': info.get('cover'),
            'duration': self.convert_milliseconds(info.get('duration', 0)),
        }


class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
    IE_NAME = 'netease:program'
    IE_DESC = '网易云音乐 - 电台节目'
    _VALID_URL = r'https?://music\.163\.com/(#/?)program\?id=(?P<id>[0-9]+)'
    _TESTS = [{
        'url': 'http://music.163.com/#/program?id=10109055',
        'info_dict': {
            'id': '10109055',
            'ext': 'mp3',
            'title': '不丹足球背后的故事',
            'description': '喜马拉雅人的足球梦 ...',
            'creator': '大话西藏',
            'timestamp': 1434179342,
            'upload_date': '20150613',
            'duration': 900,
        },
        'skip': 'Blocked outside Mainland China',
    }, {
        'note': 'This program has accompanying songs.',
        'url': 'http://music.163.com/#/program?id=10141022',
        'info_dict': {
            'id': '10141022',
            'title': '25岁，你是自在如风的少年<27°C>',
            'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b',
        },
        'playlist_count': 4,
        'skip': 'Blocked outside Mainland China',
    }, {
        'note': 'This program has accompanying songs.',
        'url': 'http://music.163.com/#/program?id=10141022',
        'info_dict': {
            'id': '10141022',
            'ext': 'mp3',
            'title': '25岁，你是自在如风的少年<27°C>',
            'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b',
            'timestamp': 1434450841,
            'upload_date': '20150616',
        },
        'params': {
            'noplaylist': True
        },
        'skip': 'Blocked outside Mainland China',
    }]

    def _real_extract(self, url):
        program_id = self._match_id(url)

        info = self.query_api(
            'dj/program/detail?id=%s' % program_id,
            program_id, 'Downloading program info')['program']

        name = info['name']
        description = info['description']

        if not self._yes_playlist(info['songs'] and program_id, info['mainSong']['id']):
            formats = self.extract_formats(info['mainSong'])
            self._sort_formats(formats)

            return {
                'id': info['mainSong']['id'],
                'title': name,
                'description': description,
                'creator': info['dj']['brand'],
                'timestamp': self.convert_milliseconds(info['createTime']),
                'thumbnail': info['coverUrl'],
                'duration': self.convert_milliseconds(info.get('duration', 0)),
                'formats': formats,
            }

        song_ids = [info['mainSong']['id']]
        song_ids.extend([song['id'] for song in info['songs']])
        entries = [
            self.url_result('http://music.163.com/#/song?id=%s' % song_id,
                            'NetEaseMusic', song_id)
            for song_id in song_ids
        ]
        return self.playlist_result(entries, program_id, name, description)


class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE):
    IE_NAME = 'netease:djradio'
    IE_DESC = '网易云音乐 - 电台'
    _VALID_URL = r'https?://music\.163\.com/(#/)?djradio\?id=(?P<id>[0-9]+)'
    _TEST = {
        'url': 'http://music.163.com/#/djradio?id=42',
        'info_dict': {
            'id': '42',
            'title': '声音蔓延',
            'description': 'md5:766220985cbd16fdd552f64c578a6b15'
        },
        'playlist_mincount': 40,
        'skip': 'Blocked outside Mainland China',
    }
    _PAGE_SIZE = 1000

    def _real_extract(self, url):
        dj_id = self._match_id(url)

        name = None
        desc = None
        entries = []
        for offset in compat_itertools_count(start=0, step=self._PAGE_SIZE):
            info = self.query_api(
                'dj/program/byradio?asc=false&limit=%d&radioId=%s&offset=%d'
                % (self._PAGE_SIZE, dj_id, offset),
                dj_id, 'Downloading dj programs - %d' % offset)

            entries.extend([
                self.url_result(
                    'http://music.163.com/#/program?id=%s' % program['id'],
                    'NetEaseMusicProgram', program['id'])
                for program in info['programs']
            ])

            if name is None:
                radio = info['programs'][0]['radio']
                name = radio['name']
                desc = radio['desc']

            if not info['more']:
                break

        return self.playlist_result(entries, dj_id, name, desc)
Commit	Line	Data
af1fa623	1	from hashlib import md5
02b386f8	2	from base64 import b64encode
af1fa623	3	from datetime import datetime
af1fa623	4	import re
	5
	6	from .common import InfoExtractor
	7	from ..compat import (
15707c7e	8	compat_urllib_parse_urlencode,
397a8ea9	9	compat_str,
4eab60cb	10	compat_itertools_count,
af1fa623	11	)
fe6856b0 YCH	12	from ..utils import (
	13	sanitized_Request,
	14	float_or_none,
	15	)
af1fa623	16
	17
	18	class NetEaseMusicBaseIE(InfoExtractor):
	19	_FORMATS = ['bMusic', 'mMusic', 'hMusic']
	20	_NETEASE_SALT = '3go8&$833h0k(2)2'
	21	_API_BASE = 'http://music.163.com/api/'
	22
	23	@classmethod
	24	def _encrypt(cls, dfsid):
397a8ea9 YCH	25	salt_bytes = bytearray(cls._NETEASE_SALT.encode('utf-8'))
397a8ea9 YCH	26	string_bytes = bytearray(compat_str(dfsid).encode('ascii'))
af1fa623	27	salt_len = len(salt_bytes)
02b386f8	28	for i in range(len(string_bytes)):
af1fa623	29	string_bytes[i] = string_bytes[i] ^ salt_bytes[i % salt_len]
af1fa623	30	m = md5()
397a8ea9 YCH	31	m.update(bytes(string_bytes))
397a8ea9 YCH	32	result = b64encode(m.digest()).decode('ascii')
af1fa623	33	return result.replace('/', '_').replace('+', '-')
af1fa623	34
e0ef13dd	35	def extract_formats(self, info):
af1fa623	36	formats = []
e0ef13dd	37	for song_format in self._FORMATS:
af1fa623	38	details = info.get(song_format)
	39	if not details:
	40	continue
e0ef13dd	41	song_file_path = '/%s/%s.%s' % (
	42	self._encrypt(details['dfsId']), details['dfsId'], details['extension'])
	43
	44	# 203.130.59.9, 124.40.233.182, 115.231.74.139, etc is a reverse proxy-like feature
	45	# from NetEase's CDN provider that can be used if m5.music.126.net does not
	46	# work, especially for users outside of Mainland China
	47	# via: https://github.com/JixunMoe/unblock-163/issues/3#issuecomment-163115880
	48	for host in ('http://m5.music.126.net', 'http://115.231.74.139/m1.music.126.net',
	49	'http://124.40.233.182/m1.music.126.net', 'http://203.130.59.9/m1.music.126.net'):
	50	song_url = host + song_file_path
	51	if self._is_valid_url(song_url, info['id'], 'song'):
	52	formats.append({
	53	'url': song_url,
	54	'ext': details.get('extension'),
fe6856b0	55	'abr': float_or_none(details.get('bitrate'), scale=1000),
e0ef13dd	56	'format_id': song_format,
	57	'filesize': details.get('size'),
	58	'asr': details.get('sr')
	59	})
	60	break
af1fa623	61	return formats
af1fa623	62
2da0cad6	63	@classmethod
2da0cad6	64	def convert_milliseconds(cls, ms):
15830339	65	return int(round(ms / 1000.0))
2da0cad6	66
af1fa623	67	def query_api(self, endpoint, video_id, note):
5c2266df	68	req = sanitized_Request('%s%s' % (self._API_BASE, endpoint))
af1fa623	69	req.add_header('Referer', self._API_BASE)
	70	return self._download_json(req, video_id, note)
	71
	72
	73	class NetEaseMusicIE(NetEaseMusicBaseIE):
	74	IE_NAME = 'netease:song'
6ce89aec	75	IE_DESC = '网易云音乐'
af1fa623	76	_VALID_URL = r'https?://music\.163\.com/(#/)?song\?id=(?P<id>[0-9]+)'
	77	_TESTS = [{
	78	'url': 'http://music.163.com/#/song?id=32102397',
	79	'md5': 'f2e97280e6345c74ba9d5677dd5dcb45',
	80	'info_dict': {
	81	'id': '32102397',
	82	'ext': 'mp3',
	83	'title': 'Bad Blood (feat. Kendrick Lamar)',
	84	'creator': 'Taylor Swift / Kendrick Lamar',
	85	'upload_date': '20150517',
	86	'timestamp': 1431878400,
	87	'description': 'md5:a10a54589c2860300d02e1de821eb2ef',
	88	},
75af5d59	89	'skip': 'Blocked outside Mainland China',
af1fa623	90	}, {
	91	'note': 'No lyrics translation.',
	92	'url': 'http://music.163.com/#/song?id=29822014',
	93	'info_dict': {
	94	'id': '29822014',
	95	'ext': 'mp3',
	96	'title': '听见下雨的声音',
	97	'creator': '周杰伦',
	98	'upload_date': '20141225',
	99	'timestamp': 1419523200,
	100	'description': 'md5:a4d8d89f44656af206b7b2555c0bce6c',
	101	},
75af5d59	102	'skip': 'Blocked outside Mainland China',
af1fa623	103	}, {
	104	'note': 'No lyrics.',
	105	'url': 'http://music.163.com/song?id=17241424',
	106	'info_dict': {
	107	'id': '17241424',
	108	'ext': 'mp3',
	109	'title': 'Opus 28',
	110	'creator': 'Dustin O\'Halloran',
	111	'upload_date': '20080211',
	112	'timestamp': 1202745600,
	113	},
75af5d59	114	'skip': 'Blocked outside Mainland China',
02b386f8	115	}, {
	116	'note': 'Has translated name.',
	117	'url': 'http://music.163.com/#/song?id=22735043',
	118	'info_dict': {
	119	'id': '22735043',
	120	'ext': 'mp3',
	121	'title': '소원을 말해봐 (Genie)',
	122	'creator': '少女时代',
	123	'description': 'md5:79d99cc560e4ca97e0c4d86800ee4184',
	124	'upload_date': '20100127',
	125	'timestamp': 1264608000,
	126	'alt_title': '说出愿望吧(Genie)',
75af5d59 YCH	127	},
75af5d59 YCH	128	'skip': 'Blocked outside Mainland China',
af1fa623	129	}]
	130
	131	def _process_lyrics(self, lyrics_info):
	132	original = lyrics_info.get('lrc', {}).get('lyric')
	133	translated = lyrics_info.get('tlyric', {}).get('lyric')
	134
	135	if not translated:
	136	return original
	137
	138	lyrics_expr = r'(\[[0-9]{2}:[0-9]{2}\.[0-9]{2,}\])([^\n]+)'
	139	original_ts_texts = re.findall(lyrics_expr, original)
02b386f8	140	translation_ts_dict = dict(
	141	(time_stamp, text) for time_stamp, text in re.findall(lyrics_expr, translated)
	142	)
af1fa623	143	lyrics = '\n'.join([
	144	'%s%s / %s' % (time_stamp, text, translation_ts_dict.get(time_stamp, ''))
	145	for time_stamp, text in original_ts_texts
	146	])
	147	return lyrics
	148
	149	def _real_extract(self, url):
	150	song_id = self._match_id(url)
	151
	152	params = {
	153	'id': song_id,
	154	'ids': '[%s]' % song_id
	155	}
	156	info = self.query_api(
15707c7e	157	'song/detail?' + compat_urllib_parse_urlencode(params),
af1fa623	158	song_id, 'Downloading song info')['songs'][0]
	159
	160	formats = self.extract_formats(info)
	161	self._sort_formats(formats)
	162
	163	lyrics_info = self.query_api(
15830339	164	'song/lyric?id=%s&lv=-1&tv=-1' % song_id,
af1fa623	165	song_id, 'Downloading lyrics data')
	166	lyrics = self._process_lyrics(lyrics_info)
	167
	168	alt_title = None
02b386f8	169	if info.get('transNames'):
02b386f8	170	alt_title = '/'.join(info.get('transNames'))
af1fa623	171
	172	return {
	173	'id': song_id,
	174	'title': info['name'],
	175	'alt_title': alt_title,
	176	'creator': ' / '.join([artist['name'] for artist in info.get('artists', [])]),
2da0cad6	177	'timestamp': self.convert_milliseconds(info.get('album', {}).get('publishTime')),
af1fa623	178	'thumbnail': info.get('album', {}).get('picUrl'),
2da0cad6	179	'duration': self.convert_milliseconds(info.get('duration', 0)),
af1fa623	180	'description': lyrics,
	181	'formats': formats,
	182	}
	183
	184
	185	class NetEaseMusicAlbumIE(NetEaseMusicBaseIE):
	186	IE_NAME = 'netease:album'
ed848087	187	IE_DESC = '网易云音乐 - 专辑'
af1fa623	188	_VALID_URL = r'https?://music\.163\.com/(#/)?album\?id=(?P<id>[0-9]+)'
	189	_TEST = {
	190	'url': 'http://music.163.com/#/album?id=220780',
	191	'info_dict': {
	192	'id': '220780',
	193	'title': 'B\'day',
	194	},
	195	'playlist_count': 23,
75af5d59	196	'skip': 'Blocked outside Mainland China',
af1fa623	197	}
	198
	199	def _real_extract(self, url):
	200	album_id = self._match_id(url)
	201
	202	info = self.query_api(
15830339	203	'album/%s?id=%s' % (album_id, album_id),
af1fa623	204	album_id, 'Downloading album data')['album']
	205
	206	name = info['name']
	207	desc = info.get('description')
	208	entries = [
	209	self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
	210	'NetEaseMusic', song['id'])
	211	for song in info['songs']
	212	]
	213	return self.playlist_result(entries, album_id, name, desc)
	214
	215
	216	class NetEaseMusicSingerIE(NetEaseMusicBaseIE):
	217	IE_NAME = 'netease:singer'
ed848087	218	IE_DESC = '网易云音乐 - 歌手'
af1fa623	219	_VALID_URL = r'https?://music\.163\.com/(#/)?artist\?id=(?P<id>[0-9]+)'
	220	_TESTS = [{
	221	'note': 'Singer has aliases.',
	222	'url': 'http://music.163.com/#/artist?id=10559',
	223	'info_dict': {
	224	'id': '10559',
	225	'title': '张惠妹 - aMEI;阿密特',
	226	},
	227	'playlist_count': 50,
75af5d59	228	'skip': 'Blocked outside Mainland China',
af1fa623	229	}, {
	230	'note': 'Singer has translated name.',
	231	'url': 'http://music.163.com/#/artist?id=124098',
	232	'info_dict': {
	233	'id': '124098',
	234	'title': '李昇基 - 이승기',
	235	},
	236	'playlist_count': 50,
75af5d59	237	'skip': 'Blocked outside Mainland China',
af1fa623	238	}]
	239
	240	def _real_extract(self, url):
	241	singer_id = self._match_id(url)
	242
	243	info = self.query_api(
15830339	244	'artist/%s?id=%s' % (singer_id, singer_id),
af1fa623	245	singer_id, 'Downloading singer data')
	246
	247	name = info['artist']['name']
	248	if info['artist']['trans']:
	249	name = '%s - %s' % (name, info['artist']['trans'])
	250	if info['artist']['alias']:
a31e3e7d	251	name = '%s - %s' % (name, ';'.join(info['artist']['alias']))
af1fa623	252
	253	entries = [
	254	self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
	255	'NetEaseMusic', song['id'])
	256	for song in info['hotSongs']
	257	]
	258	return self.playlist_result(entries, singer_id, name)
	259
	260
	261	class NetEaseMusicListIE(NetEaseMusicBaseIE):
	262	IE_NAME = 'netease:playlist'
ed848087	263	IE_DESC = '网易云音乐 - 歌单'
af1fa623	264	_VALID_URL = r'https?://music\.163\.com/(#/)?(playlist\|discover/toplist)\?id=(?P<id>[0-9]+)'
	265	_TESTS = [{
	266	'url': 'http://music.163.com/#/playlist?id=79177352',
	267	'info_dict': {
	268	'id': '79177352',
	269	'title': 'Billboard 2007 Top 100',
	270	'description': 'md5:12fd0819cab2965b9583ace0f8b7b022'
	271	},
	272	'playlist_count': 99,
75af5d59	273	'skip': 'Blocked outside Mainland China',
af1fa623	274	}, {
	275	'note': 'Toplist/Charts sample',
	276	'url': 'http://music.163.com/#/discover/toplist?id=3733003',
	277	'info_dict': {
	278	'id': '3733003',
	279	'title': 're:韩国Melon排行榜周榜 [0-9]{4}-[0-9]{2}-[0-9]{2}',
	280	'description': 'md5:73ec782a612711cadc7872d9c1e134fc',
	281	},
	282	'playlist_count': 50,
75af5d59	283	'skip': 'Blocked outside Mainland China',
af1fa623	284	}]
	285
	286	def _real_extract(self, url):
	287	list_id = self._match_id(url)
	288
	289	info = self.query_api(
15830339	290	'playlist/detail?id=%s&lv=-1&tv=-1' % list_id,
af1fa623	291	list_id, 'Downloading playlist data')['result']
	292
	293	name = info['name']
	294	desc = info.get('description')
	295
	296	if info.get('specialType') == 10: # is a chart/toplist
2da0cad6	297	datestamp = datetime.fromtimestamp(
2da0cad6	298	self.convert_milliseconds(info['updateTime'])).strftime('%Y-%m-%d')
af1fa623	299	name = '%s %s' % (name, datestamp)
	300
	301	entries = [
	302	self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
	303	'NetEaseMusic', song['id'])
	304	for song in info['tracks']
	305	]
	306	return self.playlist_result(entries, list_id, name, desc)
	307
	308
	309	class NetEaseMusicMvIE(NetEaseMusicBaseIE):
	310	IE_NAME = 'netease:mv'
ed848087	311	IE_DESC = '网易云音乐 - MV'
af1fa623	312	_VALID_URL = r'https?://music\.163\.com/(#/)?mv\?id=(?P<id>[0-9]+)'
	313	_TEST = {
	314	'url': 'http://music.163.com/#/mv?id=415350',
	315	'info_dict': {
	316	'id': '415350',
	317	'ext': 'mp4',
	318	'title': '이럴거면 그러지말지',
	319	'description': '白雅言自作曲唱甜蜜爱情',
	320	'creator': '白雅言',
	321	'upload_date': '20150520',
	322	},
75af5d59	323	'skip': 'Blocked outside Mainland China',
af1fa623	324	}
	325
	326	def _real_extract(self, url):
	327	mv_id = self._match_id(url)
	328
	329	info = self.query_api(
	330	'mv/detail?id=%s&type=mp4' % mv_id,
	331	mv_id, 'Downloading mv info')['data']
	332
	333	formats = [
02b386f8	334	{'url': mv_url, 'ext': 'mp4', 'format_id': '%sp' % brs, 'height': int(brs)}
af1fa623	335	for brs, mv_url in info['brs'].items()
	336	]
	337	self._sort_formats(formats)
	338
	339	return {
	340	'id': mv_id,
	341	'title': info['name'],
	342	'description': info.get('desc') or info.get('briefDesc'),
	343	'creator': info['artistName'],
	344	'upload_date': info['publishTime'].replace('-', ''),
	345	'formats': formats,
	346	'thumbnail': info.get('cover'),
2da0cad6	347	'duration': self.convert_milliseconds(info.get('duration', 0)),
af1fa623	348	}
	349
	350
	351	class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
	352	IE_NAME = 'netease:program'
ed848087	353	IE_DESC = '网易云音乐 - 电台节目'
af1fa623	354	_VALID_URL = r'https?://music\.163\.com/(#/?)program\?id=(?P<id>[0-9]+)'
	355	_TESTS = [{
	356	'url': 'http://music.163.com/#/program?id=10109055',
	357	'info_dict': {
	358	'id': '10109055',
	359	'ext': 'mp3',
	360	'title': '不丹足球背后的故事',
	361	'description': '喜马拉雅人的足球梦 ...',
	362	'creator': '大话西藏',
2da0cad6	363	'timestamp': 1434179342,
af1fa623	364	'upload_date': '20150613',
	365	'duration': 900,
	366	},
75af5d59	367	'skip': 'Blocked outside Mainland China',
af1fa623	368	}, {
	369	'note': 'This program has accompanying songs.',
	370	'url': 'http://music.163.com/#/program?id=10141022',
	371	'info_dict': {
	372	'id': '10141022',
	373	'title': '25岁，你是自在如风的少年<27°C>',
	374	'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b',
	375	},
	376	'playlist_count': 4,
75af5d59	377	'skip': 'Blocked outside Mainland China',
af1fa623	378	}, {
	379	'note': 'This program has accompanying songs.',
	380	'url': 'http://music.163.com/#/program?id=10141022',
	381	'info_dict': {
	382	'id': '10141022',
	383	'ext': 'mp3',
	384	'title': '25岁，你是自在如风的少年<27°C>',
	385	'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b',
2da0cad6	386	'timestamp': 1434450841,
af1fa623	387	'upload_date': '20150616',
	388	},
	389	'params': {
	390	'noplaylist': True
75af5d59 YCH	391	},
75af5d59 YCH	392	'skip': 'Blocked outside Mainland China',
af1fa623	393	}]
	394
	395	def _real_extract(self, url):
	396	program_id = self._match_id(url)
	397
	398	info = self.query_api(
	399	'dj/program/detail?id=%s' % program_id,
	400	program_id, 'Downloading program info')['program']
	401
	402	name = info['name']
	403	description = info['description']
	404
f40ee5e9	405	if not self._yes_playlist(info['songs'] and program_id, info['mainSong']['id']):
af1fa623	406	formats = self.extract_formats(info['mainSong'])
	407	self._sort_formats(formats)
	408
	409	return {
f40ee5e9	410	'id': info['mainSong']['id'],
af1fa623	411	'title': name,
	412	'description': description,
	413	'creator': info['dj']['brand'],
2da0cad6	414	'timestamp': self.convert_milliseconds(info['createTime']),
af1fa623	415	'thumbnail': info['coverUrl'],
2da0cad6	416	'duration': self.convert_milliseconds(info.get('duration', 0)),
af1fa623	417	'formats': formats,
	418	}
	419
af1fa623	420	song_ids = [info['mainSong']['id']]
	421	song_ids.extend([song['id'] for song in info['songs']])
	422	entries = [
	423	self.url_result('http://music.163.com/#/song?id=%s' % song_id,
	424	'NetEaseMusic', song_id)
	425	for song_id in song_ids
	426	]
	427	return self.playlist_result(entries, program_id, name, description)
	428
	429
	430	class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE):
	431	IE_NAME = 'netease:djradio'
ed848087	432	IE_DESC = '网易云音乐 - 电台'
af1fa623	433	_VALID_URL = r'https?://music\.163\.com/(#/)?djradio\?id=(?P<id>[0-9]+)'
	434	_TEST = {
	435	'url': 'http://music.163.com/#/djradio?id=42',
	436	'info_dict': {
	437	'id': '42',
	438	'title': '声音蔓延',
	439	'description': 'md5:766220985cbd16fdd552f64c578a6b15'
	440	},
	441	'playlist_mincount': 40,
75af5d59	442	'skip': 'Blocked outside Mainland China',
af1fa623	443	}
	444	_PAGE_SIZE = 1000
	445
	446	def _real_extract(self, url):
	447	dj_id = self._match_id(url)
	448
	449	name = None
	450	desc = None
	451	entries = []
4eab60cb	452	for offset in compat_itertools_count(start=0, step=self._PAGE_SIZE):
af1fa623	453	info = self.query_api(
15830339	454	'dj/program/byradio?asc=false&limit=%d&radioId=%s&offset=%d'
af1fa623	455	% (self._PAGE_SIZE, dj_id, offset),
	456	dj_id, 'Downloading dj programs - %d' % offset)
	457
	458	entries.extend([
	459	self.url_result(
	460	'http://music.163.com/#/program?id=%s' % program['id'],
	461	'NetEaseMusicProgram', program['id'])
	462	for program in info['programs']
	463	])
	464
	465	if name is None:
	466	radio = info['programs'][0]['radio']
	467	name = radio['name']
	468	desc = radio['desc']
	469
	470	if not info['more']:
	471	break
	472
	473	return self.playlist_result(entries, dj_id, name, desc)