2
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-14 23:32:33 +00:00
yt-dlp/yt_dlp/extractor/kuwo.py

353 lines
12 KiB
Python
Raw Normal View History

2015-06-18 06:15:54 +00:00
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2016-08-07 14:59:34 +00:00
from ..compat import compat_urlparse
2015-06-18 06:15:54 +00:00
from ..utils import (
get_element_by_id,
clean_html,
ExtractorError,
InAdvancePagedList,
remove_start,
2015-06-18 06:15:54 +00:00
)
2015-07-10 15:46:44 +00:00
class KuwoBaseIE(InfoExtractor):
2015-06-18 06:15:54 +00:00
_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):
2015-06-18 06:15:54 +00:00
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'
}
2015-06-18 06:15:54 +00:00
song_url = self._download_webpage(
'http://antiserver.kuwo.cn/anti.s',
2015-07-10 15:48:48 +00:00
song_id, note='Download %s url info' % file_format['format'],
query=query, headers=self.geo_verification_headers(),
2015-06-18 06:15:54 +00:00
)
2016-02-03 17:26:25 +00:00
if song_url == 'IPDeny' and not tolerate_ip_deny:
2016-02-03 17:26:25 +00:00
raise ExtractorError('This song is blocked in this region', expected=True)
2015-06-18 06:15:54 +00:00
if song_url.startswith('http://') or song_url.startswith('https://'):
formats.append({
'url': song_url,
'format_id': file_format['format'],
'format': file_format['format'],
'quality': file_format['preference'],
2015-06-18 06:15:54 +00:00
'abr': file_format.get('abr'),
})
2015-06-18 06:15:54 +00:00
return formats
2015-07-10 15:46:44 +00:00
class KuwoIE(KuwoBaseIE):
IE_NAME = 'kuwo:song'
2015-07-10 16:51:14 +00:00
IE_DESC = '酷我音乐'
2016-09-08 11:29:05 +00:00
_VALID_URL = r'https?://(?:www\.)?kuwo\.cn/yinyue/(?P<id>\d+)'
2015-07-10 15:46:44 +00:00
_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',
2015-07-10 15:46:44 +00:00
}, {
'url': 'http://www.kuwo.cn/yinyue/6446136/',
'info_dict': {
'id': '6446136',
'ext': 'mp3',
'title': '',
'description': 'md5:5d0e947b242c35dc0eb1d2fce9fbf02c',
2015-07-10 15:46:44 +00:00
'creator': 'IU',
'upload_date': '20150518',
},
'params': {
2016-09-14 16:53:04 +00:00
'format': 'mp3-320',
2015-07-10 15:46:44 +00:00
},
}, {
'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016',
'only_matching': True,
2015-07-10 15:46:44 +00:00
}]
2015-06-18 06:15:54 +00:00
def _real_extract(self, url):
song_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(
2015-06-18 06:15:54 +00:00
url, song_id, note='Download song detail info',
errnote='Unable to get song detail info')
if song_id not in urlh.geturl() or '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)
2015-06-18 06:15:54 +00:00
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')
2015-07-10 15:48:48 +00:00
lrc_content = clean_html(get_element_by_id('lrcContent', webpage))
2015-06-18 06:15:54 +00:00
if lrc_content == '暂无': # indicates no lyrics
lrc_content = None
formats = self._get_formats(song_id)
self._sort_formats(formats)
2015-06-18 06:15:54 +00:00
album_id = self._html_search_regex(
r'<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
webpage, 'album id', fatal=False)
2015-06-18 06:15:54 +00:00
publish_time = None
if album_id is not None:
album_info_page = self._download_webpage(
2015-07-10 15:48:48 +00:00
'http://www.kuwo.cn/album/%s/' % album_id, song_id,
2015-06-18 06:15:54 +00:00
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)
2015-06-18 06:15:54 +00:00
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'
2015-07-10 17:21:04 +00:00
IE_DESC = '酷我音乐 - 专辑'
2016-09-08 11:29:05 +00:00
_VALID_URL = r'https?://(?:www\.)?kuwo\.cn/album/(?P<id>\d+?)/'
2015-06-18 06:15:54 +00:00
_TEST = {
'url': 'http://www.kuwo.cn/album/502294/',
'info_dict': {
'id': '502294',
2016-06-11 07:37:04 +00:00
'title': 'Made\xa0Series\xa0《M》',
'description': 'md5:d463f0d8a0ff3c3ea3d6ed7452a9483f',
2015-06-18 06:15:54 +00:00
},
'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(
2015-07-10 15:48:48 +00:00
clean_html(get_element_by_id('intro', webpage)),
'%s简介:' % album_name)
2015-06-18 06:15:54 +00:00
entries = [
2015-07-10 15:53:48 +00:00
self.url_result(song_url, 'Kuwo') for song_url in re.findall(
r'<p[^>]+class="listen"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"',
2015-06-18 06:15:54 +00:00
webpage)
]
return self.playlist_result(entries, album_id, album_name, album_intro)
class KuwoChartIE(InfoExtractor):
IE_NAME = 'kuwo:chart'
2015-07-10 17:21:04 +00:00
IE_DESC = '酷我音乐 - 排行榜'
_VALID_URL = r'https?://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
2015-06-18 06:15:54 +00:00
_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',
},
2016-09-14 16:53:04 +00:00
'playlist_mincount': 7,
2015-06-18 06:15:54 +00:00
}
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 = [
2015-07-10 15:53:48 +00:00
self.url_result(song_url, 'Kuwo') for song_url in re.findall(
r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)', webpage)
2015-06-18 06:15:54 +00:00
]
return self.playlist_result(entries, chart_id)
2015-06-18 06:15:54 +00:00
class KuwoSingerIE(InfoExtractor):
IE_NAME = 'kuwo:singer'
2015-07-10 17:21:04 +00:00
IE_DESC = '酷我音乐 - 歌手'
2016-09-08 11:29:05 +00:00
_VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mingxing/(?P<id>[^/]+)'
_TESTS = [{
2015-06-18 06:15:54 +00:00
'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
'info_dict': {
'id': 'bruno+mars',
2016-06-11 07:37:04 +00:00
'title': 'Bruno\xa0Mars',
2015-06-18 06:15:54 +00:00
},
'playlist_mincount': 329,
}, {
2015-06-18 06:15:54 +00:00
'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
'info_dict': {
'id': 'Ali',
'title': 'Ali',
2015-06-18 06:15:54 +00:00
},
'playlist_mincount': 95,
2019-03-09 12:14:41 +00:00
'skip': 'Regularly stalls travis build', # See https://travis-ci.org/ytdl-org/youtube-dl/jobs/78878540
}]
2015-06-18 06:15:54 +00:00
PAGE_SIZE = 15
2015-06-18 06:15:54 +00:00
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'))
2015-06-18 06:15:54 +00:00
def page_func(page_num):
2015-06-18 06:15:54 +00:00
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})
2015-06-18 06:15:54 +00:00
return [
2016-08-07 14:59:34 +00:00
self.url_result(compat_urlparse.urljoin(url, song_url), 'Kuwo')
for song_url in re.findall(
r'<div[^>]+class="name"><a[^>]+href="(/yinyue/\d+)',
2015-06-18 06:15:54 +00:00
webpage)
]
entries = InAdvancePagedList(page_func, page_count, self.PAGE_SIZE)
2015-06-18 06:15:54 +00:00
return self.playlist_result(entries, singer_id, singer_name)
2015-06-18 06:15:54 +00:00
class KuwoCategoryIE(InfoExtractor):
IE_NAME = 'kuwo:category'
2015-07-10 17:21:04 +00:00
IE_DESC = '酷我音乐 - 分类'
_VALID_URL = r'https?://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
2015-06-18 06:15:54 +00:00
_TEST = {
'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
'info_dict': {
'id': '86375',
'title': '八十年代精选',
2016-05-05 12:06:59 +00:00
'description': '这些都是属于八十年代的回忆!',
2015-06-18 06:15:54 +00:00
},
'playlist_mincount': 24,
2015-06-18 06:15:54 +00:00
}
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')
2015-07-10 11:13:52 +00:00
category_desc = remove_start(
2015-07-10 15:48:48 +00:00
get_element_by_id('intro', webpage).strip(),
'%s简介:' % category_name)
if category_desc == '暂无':
category_desc = None
2015-07-10 11:13:52 +00:00
2015-06-18 06:15:54 +00:00
jsonm = self._parse_json(self._html_search_regex(
r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)
2015-06-18 06:15:54 +00:00
entries = [
2015-07-10 15:53:48 +00:00
self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo')
2015-06-18 06:15:54 +00:00
for song in jsonm['musiclist']
]
return self.playlist_result(entries, category_id, category_name, category_desc)
2015-07-10 15:46:44 +00:00
class KuwoMvIE(KuwoBaseIE):
2015-06-18 06:15:54 +00:00
IE_NAME = 'kuwo:mv'
2015-07-10 17:21:04 +00:00
IE_DESC = '酷我音乐 - MV'
2016-09-08 11:29:05 +00:00
_VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mv/(?P<id>\d+?)/'
2015-07-10 15:46:44 +00:00
_TEST = {
2015-06-18 06:15:54 +00:00
'url': 'http://www.kuwo.cn/mv/6480076/',
'info_dict': {
'id': '6480076',
'ext': 'mp4',
'title': 'My HouseMV',
2016-09-14 16:53:04 +00:00
'creator': '2PM',
2015-06-18 06:15:54 +00:00
},
# 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',
},
2015-07-10 15:46:44 +00:00
}
_FORMATS = KuwoBaseIE._FORMATS + [
2015-06-18 06:15:54 +00:00
{'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>[^"]+)"',
2015-06-18 06:15:54 +00:00
webpage)
if mobj:
song_name = mobj.group('song')
singer_name = mobj.group('singer')
else:
2015-07-10 15:48:48 +00:00
raise ExtractorError('Unable to find song or singer names')
2015-06-18 06:15:54 +00:00
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)
2015-06-18 06:15:54 +00:00
return {
'id': song_id,
'title': song_name,
'creator': singer_name,
'formats': formats,
}