[yt-dlp.git] / youtube_dl / extractor / kuwo.py

# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    get_element_by_id,
    clean_html,
    ExtractorError,
    InAdvancePagedList,
    remove_start,
)


class KuwoBaseIE(InfoExtractor):
    _FORMATS = [
        {'format': 'ape', 'ext': 'ape', 'preference': 100},
        {'format': 'mp3-320', 'ext': 'mp3', 'br': '320kmp3', 'abr': 320, 'preference': 80},
        {'format': 'mp3-192', 'ext': 'mp3', 'br': '192kmp3', 'abr': 192, 'preference': 70},
        {'format': 'mp3-128', 'ext': 'mp3', 'br': '128kmp3', 'abr': 128, 'preference': 60},
        {'format': 'wma', 'ext': 'wma', 'preference': 20},
        {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10}
    ]

    def _get_formats(self, song_id, tolerate_ip_deny=False):
        formats = []
        for file_format in self._FORMATS:
            headers = {}
            cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
            if cn_verification_proxy:
                headers['Ytdl-request-proxy'] = cn_verification_proxy

            query = {
                'format': file_format['ext'],
                'br': file_format.get('br', ''),
                'rid': 'MUSIC_%s' % song_id,
                'type': 'convert_url',
                'response': 'url'
            }

            song_url = self._download_webpage(
                'http://antiserver.kuwo.cn/anti.s',
                song_id, note='Download %s url info' % file_format['format'],
                query=query, headers=headers,
            )

            if song_url == 'IPDeny' and not tolerate_ip_deny:
                raise ExtractorError('This song is blocked in this region', expected=True)

            if song_url.startswith('http://') or song_url.startswith('https://'):
                formats.append({
                    'url': song_url,
                    'format_id': file_format['format'],
                    'format': file_format['format'],
                    'preference': file_format['preference'],
                    'abr': file_format.get('abr'),
                })

        return formats


class KuwoIE(KuwoBaseIE):
    IE_NAME = 'kuwo:song'
    IE_DESC = '酷我音乐'
    _VALID_URL = r'https?://www\.kuwo\.cn/yinyue/(?P<id>\d+)'
    _TESTS = [{
        'url': 'http://www.kuwo.cn/yinyue/635632/',
        'info_dict': {
            'id': '635632',
            'ext': 'ape',
            'title': '爱我别走',
            'creator': '张震岳',
            'upload_date': '20080122',
            'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c'
        },
        'skip': 'this song has been offline because of copyright issues',
    }, {
        'url': 'http://www.kuwo.cn/yinyue/6446136/',
        'info_dict': {
            'id': '6446136',
            'ext': 'mp3',
            'title': '心',
            'description': 'md5:5d0e947b242c35dc0eb1d2fce9fbf02c',
            'creator': 'IU',
            'upload_date': '20150518',
        },
        'params': {
            'format': 'mp3-320'
        },
    }, {
        'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        song_id = self._match_id(url)
        webpage = self._download_webpage(
            url, song_id, note='Download song detail info',
            errnote='Unable to get song detail info')
        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:
            raise ExtractorError('this song has been offline because of copyright issues', expected=True)

        song_name = self._html_search_regex(
            r'<p[^>]+id="lrcName">([^<]+)</p>', webpage, 'song name')
        singer_name = remove_start(self._html_search_regex(
            r'<a[^>]+href="http://www\.kuwo\.cn/artist/content\?name=([^"]+)">',
            webpage, 'singer name', fatal=False), '歌手')
        lrc_content = clean_html(get_element_by_id('lrcContent', webpage))
        if lrc_content == '暂无':     # indicates no lyrics
            lrc_content = None

        formats = self._get_formats(song_id)
        self._sort_formats(formats)

        album_id = self._html_search_regex(
            r'<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
            webpage, 'album id', fatal=False)

        publish_time = None
        if album_id is not None:
            album_info_page = self._download_webpage(
                'http://www.kuwo.cn/album/%s/' % album_id, song_id,
                note='Download album detail info',
                errnote='Unable to get album detail info')

            publish_time = self._html_search_regex(
                r'发行时间：(\d{4}-\d{2}-\d{2})', album_info_page,
                'publish time', fatal=False)
            if publish_time:
                publish_time = publish_time.replace('-', '')

        return {
            'id': song_id,
            'title': song_name,
            'creator': singer_name,
            'upload_date': publish_time,
            'description': lrc_content,
            'formats': formats,
        }


class KuwoAlbumIE(InfoExtractor):
    IE_NAME = 'kuwo:album'
    IE_DESC = '酷我音乐 - 专辑'
    _VALID_URL = r'https?://www\.kuwo\.cn/album/(?P<id>\d+?)/'
    _TEST = {
        'url': 'http://www.kuwo.cn/album/502294/',
        'info_dict': {
            'id': '502294',
            'title': 'M',
            'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c',
        },
        'playlist_count': 2,
    }

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

        webpage = self._download_webpage(
            url, album_id, note='Download album info',
            errnote='Unable to get album info')

        album_name = self._html_search_regex(
            r'<div[^>]+class="comm"[^<]+<h1[^>]+title="([^"]+)"', webpage,
            'album name')
        album_intro = remove_start(
            clean_html(get_element_by_id('intro', webpage)),
            '%s简介：' % album_name)

        entries = [
            self.url_result(song_url, 'Kuwo') for song_url in re.findall(
                r'<p[^>]+class="listen"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"',
                webpage)
        ]
        return self.playlist_result(entries, album_id, album_name, album_intro)


class KuwoChartIE(InfoExtractor):
    IE_NAME = 'kuwo:chart'
    IE_DESC = '酷我音乐 - 排行榜'
    _VALID_URL = r'https?://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
    _TEST = {
        'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
        'info_dict': {
            'id': '香港中文龙虎榜',
        },
        'playlist_mincount': 10,
    }

    def _real_extract(self, url):
        chart_id = self._match_id(url)
        webpage = self._download_webpage(
            url, chart_id, note='Download chart info',
            errnote='Unable to get chart info')

        entries = [
            self.url_result(song_url, 'Kuwo') for song_url in re.findall(
                r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)', webpage)
        ]
        return self.playlist_result(entries, chart_id)


class KuwoSingerIE(InfoExtractor):
    IE_NAME = 'kuwo:singer'
    IE_DESC = '酷我音乐 - 歌手'
    _VALID_URL = r'https?://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
    _TESTS = [{
        'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
        'info_dict': {
            'id': 'bruno+mars',
            'title': 'Bruno Mars',
        },
        'playlist_mincount': 329,
    }, {
        'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
        'info_dict': {
            'id': 'Ali',
            'title': 'Ali',
        },
        'playlist_mincount': 95,
        'skip': 'Regularly stalls travis build',  # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540
    }]

    PAGE_SIZE = 15

    def _real_extract(self, url):
        singer_id = self._match_id(url)
        webpage = self._download_webpage(
            url, singer_id, note='Download singer info',
            errnote='Unable to get singer info')

        singer_name = self._html_search_regex(
            r'<h1>([^<]+)</h1>', webpage, 'singer name')

        artist_id = self._html_search_regex(
            r'data-artistid="(\d+)"', webpage, 'artist id')

        page_count = int(self._html_search_regex(
            r'data-page="(\d+)"', webpage, 'page count'))

        def page_func(page_num):
            webpage = self._download_webpage(
                'http://www.kuwo.cn/artist/contentMusicsAjax',
                singer_id, note='Download song list page #%d' % (page_num + 1),
                errnote='Unable to get song list page #%d' % (page_num + 1),
                query={'artistId': artist_id, 'pn': page_num, 'rn': self.PAGE_SIZE})

            return [
                self.url_result(song_url, 'Kuwo') for song_url in re.findall(
                    r'<div[^>]+class="name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)',
                    webpage)
            ]

        entries = InAdvancePagedList(page_func, page_count, self.PAGE_SIZE)

        return self.playlist_result(entries, singer_id, singer_name)


class KuwoCategoryIE(InfoExtractor):
    IE_NAME = 'kuwo:category'
    IE_DESC = '酷我音乐 - 分类'
    _VALID_URL = r'https?://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
    _TEST = {
        'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
        'info_dict': {
            'id': '86375',
            'title': '八十年代精选',
        },
        'playlist_mincount': 24,
    }

    def _real_extract(self, url):
        category_id = self._match_id(url)
        webpage = self._download_webpage(
            url, category_id, note='Download category info',
            errnote='Unable to get category info')

        category_name = self._html_search_regex(
            r'<h1[^>]+title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name')

        category_desc = remove_start(
            get_element_by_id('intro', webpage).strip(),
            '%s简介：' % category_name)
        if category_desc == '暂无':
            category_desc = None

        jsonm = self._parse_json(self._html_search_regex(
            r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)

        entries = [
            self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo')
            for song in jsonm['musiclist']
        ]
        return self.playlist_result(entries, category_id, category_name, category_desc)


class KuwoMvIE(KuwoBaseIE):
    IE_NAME = 'kuwo:mv'
    IE_DESC = '酷我音乐 - MV'
    _VALID_URL = r'https?://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
    _TEST = {
        'url': 'http://www.kuwo.cn/mv/6480076/',
        'info_dict': {
            'id': '6480076',
            'ext': 'mp4',
            'title': 'My HouseMV',
            'creator': '2PM',
        },
        # In this video, music URLs (anti.s) are blocked outside China and
        # USA, while the MV URL (mvurl) is available globally, so force the MV
        # URL for consistent results in different countries
        'params': {
            'format': 'mv',
        },
    }
    _FORMATS = KuwoBaseIE._FORMATS + [
        {'format': 'mkv', 'ext': 'mkv', 'preference': 250},
        {'format': 'mp4', 'ext': 'mp4', 'preference': 200},
    ]

    def _real_extract(self, url):
        song_id = self._match_id(url)
        webpage = self._download_webpage(
            url, song_id, note='Download mv detail info: %s' % song_id,
            errnote='Unable to get mv detail info: %s' % song_id)

        mobj = re.search(
            r'<h1[^>]+title="(?P<song>[^"]+)">[^<]+<span[^>]+title="(?P<singer>[^"]+)"',
            webpage)
        if mobj:
            song_name = mobj.group('song')
            singer_name = mobj.group('singer')
        else:
            raise ExtractorError('Unable to find song or singer names')

        formats = self._get_formats(song_id, tolerate_ip_deny=True)

        mv_url = self._download_webpage(
            'http://www.kuwo.cn/yy/st/mvurl?rid=MUSIC_%s' % song_id,
            song_id, note='Download %s MV URL' % song_id)
        formats.append({
            'url': mv_url,
            'format_id': 'mv',
        })

        self._sort_formats(formats)

        return {
            'id': song_id,
            'title': song_name,
            'creator': singer_name,
            'formats': formats,
        }
Commit	Line	Data
8f73e89c	1	# coding: utf-8
	2	from __future__ import unicode_literals
	3
	4	import re
8f73e89c	5
	6	from .common import InfoExtractor
	7	from ..utils import (
	8	get_element_by_id,
	9	clean_html,
	10	ExtractorError,
daef04a4	11	InAdvancePagedList,
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
3ff8279e	26	def _get_formats(self, song_id, tolerate_ip_deny=False):
8f73e89c	27	formats = []
8f73e89c	28	for file_format in self._FORMATS:
e621a344 YCH	29	headers = {}
	30	cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
	31	if cn_verification_proxy:
	32	headers['Ytdl-request-proxy'] = cn_verification_proxy
	33
	34	query = {
	35	'format': file_format['ext'],
	36	'br': file_format.get('br', ''),
	37	'rid': 'MUSIC_%s' % song_id,
	38	'type': 'convert_url',
	39	'response': 'url'
	40	}
	41
8f73e89c	42	song_url = self._download_webpage(
e621a344	43	'http://antiserver.kuwo.cn/anti.s',
cf2c5fda	44	song_id, note='Download %s url info' % file_format['format'],
e621a344	45	query=query, headers=headers,
8f73e89c	46	)
58be9220	47
3ff8279e	48	if song_url == 'IPDeny' and not tolerate_ip_deny:
58be9220 YCH	49	raise ExtractorError('This song is blocked in this region', expected=True)
58be9220 YCH	50
8f73e89c	51	if song_url.startswith('http://') or song_url.startswith('https://'):
	52	formats.append({
	53	'url': song_url,
	54	'format_id': file_format['format'],
	55	'format': file_format['format'],
	56	'preference': file_format['preference'],
	57	'abr': file_format.get('abr'),
	58	})
3ff8279e	59
8f73e89c	60	return formats
8f73e89c	61
a9684c0d YCH	62
	63	class KuwoIE(KuwoBaseIE):
	64	IE_NAME = 'kuwo:song'
0f08d7f8	65	IE_DESC = '酷我音乐'
597d52fa	66	_VALID_URL = r'https?://www\.kuwo\.cn/yinyue/(?P<id>\d+)'
a9684c0d YCH	67	_TESTS = [{
	68	'url': 'http://www.kuwo.cn/yinyue/635632/',
	69	'info_dict': {
	70	'id': '635632',
	71	'ext': 'ape',
	72	'title': '爱我别走',
	73	'creator': '张震岳',
	74	'upload_date': '20080122',
	75	'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c'
	76	},
c44c7895	77	'skip': 'this song has been offline because of copyright issues',
a9684c0d YCH	78	}, {
	79	'url': 'http://www.kuwo.cn/yinyue/6446136/',
	80	'info_dict': {
	81	'id': '6446136',
	82	'ext': 'mp3',
	83	'title': '心',
a82398bd	84	'description': 'md5:5d0e947b242c35dc0eb1d2fce9fbf02c',
a9684c0d YCH	85	'creator': 'IU',
	86	'upload_date': '20150518',
	87	},
	88	'params': {
	89	'format': 'mp3-320'
	90	},
daef04a4 YCH	91	}, {
	92	'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016',
	93	'only_matching': True,
a9684c0d YCH	94	}]
a9684c0d YCH	95
8f73e89c	96	def _real_extract(self, url):
	97	song_id = self._match_id(url)
	98	webpage = self._download_webpage(
	99	url, song_id, note='Download song detail info',
	100	errnote='Unable to get song detail info')
5db34f68	101	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	102	raise ExtractorError('this song has been offline because of copyright issues', expected=True)
8f73e89c	103
8f73e89c	104	song_name = self._html_search_regex(
a82398bd YCH	105	r'<p[^>]+id="lrcName">([^<]+)</p>', webpage, 'song name')
	106	singer_name = remove_start(self._html_search_regex(
	107	r'<a[^>]+href="http://www\.kuwo\.cn/artist/content\?name=([^"]+)">',
	108	webpage, 'singer name', fatal=False), '歌手')
cf2c5fda	109	lrc_content = clean_html(get_element_by_id('lrcContent', webpage))
8f73e89c	110	if lrc_content == '暂无': # indicates no lyrics
	111	lrc_content = None
	112
	113	formats = self._get_formats(song_id)
3ae6f8fe	114	self._sort_formats(formats)
8f73e89c	115
8f73e89c	116	album_id = self._html_search_regex(
a82398bd	117	r'<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
094790d2	118	webpage, 'album id', fatal=False)
8f73e89c	119
	120	publish_time = None
	121	if album_id is not None:
	122	album_info_page = self._download_webpage(
cf2c5fda	123	'http://www.kuwo.cn/album/%s/' % album_id, song_id,
8f73e89c	124	note='Download album detail info',
	125	errnote='Unable to get album detail info')
	126
	127	publish_time = self._html_search_regex(
	128	r'发行时间：(\d{4}-\d{2}-\d{2})', album_info_page,
094790d2	129	'publish time', fatal=False)
8f73e89c	130	if publish_time:
	131	publish_time = publish_time.replace('-', '')
	132
	133	return {
	134	'id': song_id,
	135	'title': song_name,
	136	'creator': singer_name,
	137	'upload_date': publish_time,
	138	'description': lrc_content,
	139	'formats': formats,
	140	}
	141
	142
	143	class KuwoAlbumIE(InfoExtractor):
	144	IE_NAME = 'kuwo:album'
edd66be5	145	IE_DESC = '酷我音乐 - 专辑'
5886b38d	146	_VALID_URL = r'https?://www\.kuwo\.cn/album/(?P<id>\d+?)/'
8f73e89c	147	_TEST = {
	148	'url': 'http://www.kuwo.cn/album/502294/',
	149	'info_dict': {
	150	'id': '502294',
	151	'title': 'M',
	152	'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c',
	153	},
	154	'playlist_count': 2,
	155	}
	156
	157	def _real_extract(self, url):
	158	album_id = self._match_id(url)
	159
	160	webpage = self._download_webpage(
	161	url, album_id, note='Download album info',
	162	errnote='Unable to get album info')
	163
	164	album_name = self._html_search_regex(
a31e3e7d YCH	165	r'<div[^>]+class="comm"[^<]+<h1[^>]+title="([^"]+)"', webpage,
	166	'album name')
	167	album_intro = remove_start(
cf2c5fda	168	clean_html(get_element_by_id('intro', webpage)),
a31e3e7d	169	'%s简介：' % album_name)
8f73e89c	170
8f73e89c	171	entries = [
d3b89088 YCH	172	self.url_result(song_url, 'Kuwo') for song_url in re.findall(
d3b89088 YCH	173	r'<p[^>]+class="listen"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"',
8f73e89c	174	webpage)
	175	]
	176	return self.playlist_result(entries, album_id, album_name, album_intro)
	177
	178
	179	class KuwoChartIE(InfoExtractor):
	180	IE_NAME = 'kuwo:chart'
edd66be5	181	IE_DESC = '酷我音乐 - 排行榜'
5886b38d	182	_VALID_URL = r'https?://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
8f73e89c	183	_TEST = {
	184	'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
	185	'info_dict': {
	186	'id': '香港中文龙虎榜',
8f73e89c	187	},
	188	'playlist_mincount': 10,
	189	}
	190
	191	def _real_extract(self, url):
	192	chart_id = self._match_id(url)
	193	webpage = self._download_webpage(
	194	url, chart_id, note='Download chart info',
	195	errnote='Unable to get chart info')
	196
8f73e89c	197	entries = [
d3b89088	198	self.url_result(song_url, 'Kuwo') for song_url in re.findall(
daef04a4	199	r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)', webpage)
8f73e89c	200	]
daef04a4	201	return self.playlist_result(entries, chart_id)
8f73e89c	202
	203
	204	class KuwoSingerIE(InfoExtractor):
	205	IE_NAME = 'kuwo:singer'
edd66be5	206	IE_DESC = '酷我音乐 - 歌手'
5886b38d	207	_VALID_URL = r'https?://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
1633491b	208	_TESTS = [{
8f73e89c	209	'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
	210	'info_dict': {
	211	'id': 'bruno+mars',
	212	'title': 'Bruno Mars',
	213	},
daef04a4	214	'playlist_mincount': 329,
1633491b	215	}, {
8f73e89c	216	'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
	217	'info_dict': {
	218	'id': 'Ali',
1633491b	219	'title': 'Ali',
8f73e89c	220	},
8f73e89c	221	'playlist_mincount': 95,
12bbd32a	222	'skip': 'Regularly stalls travis build', # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540
1633491b	223	}]
8f73e89c	224
daef04a4 YCH	225	PAGE_SIZE = 15
daef04a4 YCH	226
8f73e89c	227	def _real_extract(self, url):
8f73e89c	228	singer_id = self._match_id(url)
1633491b	229	webpage = self._download_webpage(
	230	url, singer_id, note='Download singer info',
	231	errnote='Unable to get singer info')
	232
	233	singer_name = self._html_search_regex(
daef04a4 YCH	234	r'<h1>([^<]+)</h1>', webpage, 'singer name')
	235
	236	artist_id = self._html_search_regex(
	237	r'data-artistid="(\d+)"', webpage, 'artist id')
	238
	239	page_count = int(self._html_search_regex(
	240	r'data-page="(\d+)"', webpage, 'page count'))
8f73e89c	241
daef04a4	242	def page_func(page_num):
8f73e89c	243	webpage = self._download_webpage(
daef04a4 YCH	244	'http://www.kuwo.cn/artist/contentMusicsAjax',
	245	singer_id, note='Download song list page #%d' % (page_num + 1),
	246	errnote='Unable to get song list page #%d' % (page_num + 1),
	247	query={'artistId': artist_id, 'pn': page_num, 'rn': self.PAGE_SIZE})
8f73e89c	248
daef04a4	249	return [
d3b89088	250	self.url_result(song_url, 'Kuwo') for song_url in re.findall(
daef04a4	251	r'<div[^>]+class="name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)',
8f73e89c	252	webpage)
daef04a4	253	]
1633491b	254
daef04a4	255	entries = InAdvancePagedList(page_func, page_count, self.PAGE_SIZE)
8f73e89c	256
1633491b	257	return self.playlist_result(entries, singer_id, singer_name)
8f73e89c	258
	259
	260	class KuwoCategoryIE(InfoExtractor):
	261	IE_NAME = 'kuwo:category'
edd66be5	262	IE_DESC = '酷我音乐 - 分类'
5886b38d	263	_VALID_URL = r'https?://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
8f73e89c	264	_TEST = {
	265	'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
	266	'info_dict': {
	267	'id': '86375',
	268	'title': '八十年代精选',
8f73e89c	269	},
03dd60ca	270	'playlist_mincount': 24,
8f73e89c	271	}
	272
	273	def _real_extract(self, url):
	274	category_id = self._match_id(url)
	275	webpage = self._download_webpage(
	276	url, category_id, note='Download category info',
	277	errnote='Unable to get category info')
	278
	279	category_name = self._html_search_regex(
a31e3e7d	280	r'<h1[^>]+title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name')
a34af8d0	281
a31e3e7d	282	category_desc = remove_start(
cf2c5fda	283	get_element_by_id('intro', webpage).strip(),
a31e3e7d	284	'%s简介：' % category_name)
a0a309b9 YCH	285	if category_desc == '暂无':
a0a309b9 YCH	286	category_desc = None
a34af8d0	287
8f73e89c	288	jsonm = self._parse_json(self._html_search_regex(
a31e3e7d	289	r'var\s+jsonm\s=\s([^;]+);', webpage, 'category songs'), category_id)
8f73e89c	290
8f73e89c	291	entries = [
d3b89088	292	self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo')
8f73e89c	293	for song in jsonm['musiclist']
	294	]
	295	return self.playlist_result(entries, category_id, category_name, category_desc)
	296
	297
a9684c0d	298	class KuwoMvIE(KuwoBaseIE):
8f73e89c	299	IE_NAME = 'kuwo:mv'
edd66be5	300	IE_DESC = '酷我音乐 - MV'
5886b38d	301	_VALID_URL = r'https?://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
a9684c0d	302	_TEST = {
8f73e89c	303	'url': 'http://www.kuwo.cn/mv/6480076/',
	304	'info_dict': {
	305	'id': '6480076',
3ff8279e YCH	306	'ext': 'mp4',
3ff8279e YCH	307	'title': 'My HouseMV',
8f73e89c	308	'creator': '2PM',
8f73e89c	309	},
3ff8279e YCH	310	# In this video, music URLs (anti.s) are blocked outside China and
	311	# USA, while the MV URL (mvurl) is available globally, so force the MV
	312	# URL for consistent results in different countries
	313	'params': {
	314	'format': 'mv',
	315	},
a9684c0d YCH	316	}
a9684c0d YCH	317	_FORMATS = KuwoBaseIE._FORMATS + [
8f73e89c	318	{'format': 'mkv', 'ext': 'mkv', 'preference': 250},
	319	{'format': 'mp4', 'ext': 'mp4', 'preference': 200},
	320	]
	321
	322	def _real_extract(self, url):
	323	song_id = self._match_id(url)
	324	webpage = self._download_webpage(
	325	url, song_id, note='Download mv detail info: %s' % song_id,
	326	errnote='Unable to get mv detail info: %s' % song_id)
	327
	328	mobj = re.search(
a31e3e7d	329	r'<h1[^>]+title="(?P<song>[^"]+)">[^<]+<span[^>]+title="(?P<singer>[^"]+)"',
8f73e89c	330	webpage)
	331	if mobj:
	332	song_name = mobj.group('song')
	333	singer_name = mobj.group('singer')
	334	else:
cf2c5fda	335	raise ExtractorError('Unable to find song or singer names')
8f73e89c	336
3ff8279e YCH	337	formats = self._get_formats(song_id, tolerate_ip_deny=True)
	338
	339	mv_url = self._download_webpage(
	340	'http://www.kuwo.cn/yy/st/mvurl?rid=MUSIC_%s' % song_id,
	341	song_id, note='Download %s MV URL' % song_id)
	342	formats.append({
	343	'url': mv_url,
	344	'format_id': 'mv',
	345	})
	346
	347	self._sort_formats(formats)
8f73e89c	348
	349	return {
	350	'id': song_id,
	351	'title': song_name,
	352	'creator': singer_name,
	353	'formats': formats,
	354	}