[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:
            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=self.geo_verification_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': 'Made\xa0Series\xa0《M》',
            'description': 'md5:d463f0d8a0ff3c3ea3d6ed7452a9483f',
        },
        '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\xa0Mars',
        },
        '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',
            'description': '这些都是属于八十年代的回忆！',
        },
        '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': 'PM02:00',
        },
        # 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	query = {
	30	'format': file_format['ext'],
	31	'br': file_format.get('br', ''),
	32	'rid': 'MUSIC_%s' % song_id,
	33	'type': 'convert_url',
	34	'response': 'url'
	35	}
	36
8f73e89c	37	song_url = self._download_webpage(
e621a344	38	'http://antiserver.kuwo.cn/anti.s',
cf2c5fda	39	song_id, note='Download %s url info' % file_format['format'],
38cce791	40	query=query, headers=self.geo_verification_headers(),
8f73e89c	41	)
58be9220	42
3ff8279e	43	if song_url == 'IPDeny' and not tolerate_ip_deny:
58be9220 YCH	44	raise ExtractorError('This song is blocked in this region', expected=True)
58be9220 YCH	45
8f73e89c	46	if song_url.startswith('http://') or song_url.startswith('https://'):
	47	formats.append({
	48	'url': song_url,
	49	'format_id': file_format['format'],
	50	'format': file_format['format'],
	51	'preference': file_format['preference'],
	52	'abr': file_format.get('abr'),
	53	})
3ff8279e	54
8f73e89c	55	return formats
8f73e89c	56
a9684c0d YCH	57
	58	class KuwoIE(KuwoBaseIE):
	59	IE_NAME = 'kuwo:song'
0f08d7f8	60	IE_DESC = '酷我音乐'
597d52fa	61	_VALID_URL = r'https?://www\.kuwo\.cn/yinyue/(?P<id>\d+)'
a9684c0d YCH	62	_TESTS = [{
	63	'url': 'http://www.kuwo.cn/yinyue/635632/',
	64	'info_dict': {
	65	'id': '635632',
	66	'ext': 'ape',
	67	'title': '爱我别走',
	68	'creator': '张震岳',
	69	'upload_date': '20080122',
	70	'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c'
	71	},
c44c7895	72	'skip': 'this song has been offline because of copyright issues',
a9684c0d YCH	73	}, {
	74	'url': 'http://www.kuwo.cn/yinyue/6446136/',
	75	'info_dict': {
	76	'id': '6446136',
	77	'ext': 'mp3',
	78	'title': '心',
a82398bd	79	'description': 'md5:5d0e947b242c35dc0eb1d2fce9fbf02c',
a9684c0d YCH	80	'creator': 'IU',
	81	'upload_date': '20150518',
	82	},
	83	'params': {
	84	'format': 'mp3-320'
	85	},
daef04a4 YCH	86	}, {
	87	'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016',
	88	'only_matching': True,
a9684c0d YCH	89	}]
a9684c0d YCH	90
8f73e89c	91	def _real_extract(self, url):
	92	song_id = self._match_id(url)
	93	webpage = self._download_webpage(
	94	url, song_id, note='Download song detail info',
	95	errnote='Unable to get song detail info')
5db34f68	96	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	97	raise ExtractorError('this song has been offline because of copyright issues', expected=True)
8f73e89c	98
8f73e89c	99	song_name = self._html_search_regex(
a82398bd YCH	100	r'<p[^>]+id="lrcName">([^<]+)</p>', webpage, 'song name')
	101	singer_name = remove_start(self._html_search_regex(
	102	r'<a[^>]+href="http://www\.kuwo\.cn/artist/content\?name=([^"]+)">',
	103	webpage, 'singer name', fatal=False), '歌手')
cf2c5fda	104	lrc_content = clean_html(get_element_by_id('lrcContent', webpage))
8f73e89c	105	if lrc_content == '暂无': # indicates no lyrics
	106	lrc_content = None
	107
	108	formats = self._get_formats(song_id)
3ae6f8fe	109	self._sort_formats(formats)
8f73e89c	110
8f73e89c	111	album_id = self._html_search_regex(
a82398bd	112	r'<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
094790d2	113	webpage, 'album id', fatal=False)
8f73e89c	114
	115	publish_time = None
	116	if album_id is not None:
	117	album_info_page = self._download_webpage(
cf2c5fda	118	'http://www.kuwo.cn/album/%s/' % album_id, song_id,
8f73e89c	119	note='Download album detail info',
	120	errnote='Unable to get album detail info')
	121
	122	publish_time = self._html_search_regex(
	123	r'发行时间：(\d{4}-\d{2}-\d{2})', album_info_page,
094790d2	124	'publish time', fatal=False)
8f73e89c	125	if publish_time:
	126	publish_time = publish_time.replace('-', '')
	127
	128	return {
	129	'id': song_id,
	130	'title': song_name,
	131	'creator': singer_name,
	132	'upload_date': publish_time,
	133	'description': lrc_content,
	134	'formats': formats,
	135	}
	136
	137
	138	class KuwoAlbumIE(InfoExtractor):
	139	IE_NAME = 'kuwo:album'
edd66be5	140	IE_DESC = '酷我音乐 - 专辑'
5886b38d	141	_VALID_URL = r'https?://www\.kuwo\.cn/album/(?P<id>\d+?)/'
8f73e89c	142	_TEST = {
	143	'url': 'http://www.kuwo.cn/album/502294/',
	144	'info_dict': {
	145	'id': '502294',
7aab3696 YCH	146	'title': 'Made\xa0Series\xa0《M》',
7aab3696 YCH	147	'description': 'md5:d463f0d8a0ff3c3ea3d6ed7452a9483f',
8f73e89c	148	},
	149	'playlist_count': 2,
	150	}
	151
	152	def _real_extract(self, url):
	153	album_id = self._match_id(url)
	154
	155	webpage = self._download_webpage(
	156	url, album_id, note='Download album info',
	157	errnote='Unable to get album info')
	158
	159	album_name = self._html_search_regex(
a31e3e7d YCH	160	r'<div[^>]+class="comm"[^<]+<h1[^>]+title="([^"]+)"', webpage,
	161	'album name')
	162	album_intro = remove_start(
cf2c5fda	163	clean_html(get_element_by_id('intro', webpage)),
a31e3e7d	164	'%s简介：' % album_name)
8f73e89c	165
8f73e89c	166	entries = [
d3b89088 YCH	167	self.url_result(song_url, 'Kuwo') for song_url in re.findall(
d3b89088 YCH	168	r'<p[^>]+class="listen"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"',
8f73e89c	169	webpage)
	170	]
	171	return self.playlist_result(entries, album_id, album_name, album_intro)
	172
	173
	174	class KuwoChartIE(InfoExtractor):
	175	IE_NAME = 'kuwo:chart'
edd66be5	176	IE_DESC = '酷我音乐 - 排行榜'
5886b38d	177	_VALID_URL = r'https?://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
8f73e89c	178	_TEST = {
	179	'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
	180	'info_dict': {
	181	'id': '香港中文龙虎榜',
8f73e89c	182	},
	183	'playlist_mincount': 10,
	184	}
	185
	186	def _real_extract(self, url):
	187	chart_id = self._match_id(url)
	188	webpage = self._download_webpage(
	189	url, chart_id, note='Download chart info',
	190	errnote='Unable to get chart info')
	191
8f73e89c	192	entries = [
d3b89088	193	self.url_result(song_url, 'Kuwo') for song_url in re.findall(
daef04a4	194	r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)', webpage)
8f73e89c	195	]
daef04a4	196	return self.playlist_result(entries, chart_id)
8f73e89c	197
	198
	199	class KuwoSingerIE(InfoExtractor):
	200	IE_NAME = 'kuwo:singer'
edd66be5	201	IE_DESC = '酷我音乐 - 歌手'
5886b38d	202	_VALID_URL = r'https?://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
1633491b	203	_TESTS = [{
8f73e89c	204	'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
	205	'info_dict': {
	206	'id': 'bruno+mars',
7aab3696	207	'title': 'Bruno\xa0Mars',
8f73e89c	208	},
daef04a4	209	'playlist_mincount': 329,
1633491b	210	}, {
8f73e89c	211	'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
	212	'info_dict': {
	213	'id': 'Ali',
1633491b	214	'title': 'Ali',
8f73e89c	215	},
8f73e89c	216	'playlist_mincount': 95,
12bbd32a	217	'skip': 'Regularly stalls travis build', # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540
1633491b	218	}]
8f73e89c	219
daef04a4 YCH	220	PAGE_SIZE = 15
daef04a4 YCH	221
8f73e89c	222	def _real_extract(self, url):
8f73e89c	223	singer_id = self._match_id(url)
1633491b	224	webpage = self._download_webpage(
	225	url, singer_id, note='Download singer info',
	226	errnote='Unable to get singer info')
	227
	228	singer_name = self._html_search_regex(
daef04a4 YCH	229	r'<h1>([^<]+)</h1>', webpage, 'singer name')
	230
	231	artist_id = self._html_search_regex(
	232	r'data-artistid="(\d+)"', webpage, 'artist id')
	233
	234	page_count = int(self._html_search_regex(
	235	r'data-page="(\d+)"', webpage, 'page count'))
8f73e89c	236
daef04a4	237	def page_func(page_num):
8f73e89c	238	webpage = self._download_webpage(
daef04a4 YCH	239	'http://www.kuwo.cn/artist/contentMusicsAjax',
	240	singer_id, note='Download song list page #%d' % (page_num + 1),
	241	errnote='Unable to get song list page #%d' % (page_num + 1),
	242	query={'artistId': artist_id, 'pn': page_num, 'rn': self.PAGE_SIZE})
8f73e89c	243
daef04a4	244	return [
d3b89088	245	self.url_result(song_url, 'Kuwo') for song_url in re.findall(
daef04a4	246	r'<div[^>]+class="name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)',
8f73e89c	247	webpage)
daef04a4	248	]
1633491b	249
daef04a4	250	entries = InAdvancePagedList(page_func, page_count, self.PAGE_SIZE)
8f73e89c	251
1633491b	252	return self.playlist_result(entries, singer_id, singer_name)
8f73e89c	253
	254
	255	class KuwoCategoryIE(InfoExtractor):
	256	IE_NAME = 'kuwo:category'
edd66be5	257	IE_DESC = '酷我音乐 - 分类'
5886b38d	258	_VALID_URL = r'https?://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
8f73e89c	259	_TEST = {
	260	'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
	261	'info_dict': {
	262	'id': '86375',
	263	'title': '八十年代精选',
7d08f607	264	'description': '这些都是属于八十年代的回忆！',
8f73e89c	265	},
03dd60ca	266	'playlist_mincount': 24,
8f73e89c	267	}
	268
	269	def _real_extract(self, url):
	270	category_id = self._match_id(url)
	271	webpage = self._download_webpage(
	272	url, category_id, note='Download category info',
	273	errnote='Unable to get category info')
	274
	275	category_name = self._html_search_regex(
a31e3e7d	276	r'<h1[^>]+title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name')
a34af8d0	277
a31e3e7d	278	category_desc = remove_start(
cf2c5fda	279	get_element_by_id('intro', webpage).strip(),
a31e3e7d	280	'%s简介：' % category_name)
a0a309b9 YCH	281	if category_desc == '暂无':
a0a309b9 YCH	282	category_desc = None
a34af8d0	283
8f73e89c	284	jsonm = self._parse_json(self._html_search_regex(
a31e3e7d	285	r'var\s+jsonm\s=\s([^;]+);', webpage, 'category songs'), category_id)
8f73e89c	286
8f73e89c	287	entries = [
d3b89088	288	self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo')
8f73e89c	289	for song in jsonm['musiclist']
	290	]
	291	return self.playlist_result(entries, category_id, category_name, category_desc)
	292
	293
a9684c0d	294	class KuwoMvIE(KuwoBaseIE):
8f73e89c	295	IE_NAME = 'kuwo:mv'
edd66be5	296	IE_DESC = '酷我音乐 - MV'
5886b38d	297	_VALID_URL = r'https?://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
a9684c0d	298	_TEST = {
8f73e89c	299	'url': 'http://www.kuwo.cn/mv/6480076/',
	300	'info_dict': {
	301	'id': '6480076',
3ff8279e YCH	302	'ext': 'mp4',
3ff8279e YCH	303	'title': 'My HouseMV',
7aab3696	304	'creator': 'PM02:00',
8f73e89c	305	},
3ff8279e YCH	306	# In this video, music URLs (anti.s) are blocked outside China and
	307	# USA, while the MV URL (mvurl) is available globally, so force the MV
	308	# URL for consistent results in different countries
	309	'params': {
	310	'format': 'mv',
	311	},
a9684c0d YCH	312	}
a9684c0d YCH	313	_FORMATS = KuwoBaseIE._FORMATS + [
8f73e89c	314	{'format': 'mkv', 'ext': 'mkv', 'preference': 250},
	315	{'format': 'mp4', 'ext': 'mp4', 'preference': 200},
	316	]
	317
	318	def _real_extract(self, url):
	319	song_id = self._match_id(url)
	320	webpage = self._download_webpage(
	321	url, song_id, note='Download mv detail info: %s' % song_id,
	322	errnote='Unable to get mv detail info: %s' % song_id)
	323
	324	mobj = re.search(
a31e3e7d	325	r'<h1[^>]+title="(?P<song>[^"]+)">[^<]+<span[^>]+title="(?P<singer>[^"]+)"',
8f73e89c	326	webpage)
	327	if mobj:
	328	song_name = mobj.group('song')
	329	singer_name = mobj.group('singer')
	330	else:
cf2c5fda	331	raise ExtractorError('Unable to find song or singer names')
8f73e89c	332
3ff8279e YCH	333	formats = self._get_formats(song_id, tolerate_ip_deny=True)
	334
	335	mv_url = self._download_webpage(
	336	'http://www.kuwo.cn/yy/st/mvurl?rid=MUSIC_%s' % song_id,
	337	song_id, note='Download %s MV URL' % song_id)
	338	formats.append({
	339	'url': mv_url,
	340	'format_id': 'mv',
	341	})
	342
	343	self._sort_formats(formats)
8f73e89c	344
	345	return {
	346	'id': song_id,
	347	'title': song_name,
	348	'creator': singer_name,
	349	'formats': formats,
	350	}