[kuwo] Merge KuwoSingerMusicIE into KuwoSingerIE (missed kuwo.py)

This commit is contained in:
ping 2015-07-10 15:19:07 +08:00
parent 2b0fa1f7dd
commit 1633491bff

View File

@ -180,15 +180,22 @@ def _real_extract(self, url):
class KuwoSingerIE(InfoExtractor): class KuwoSingerIE(InfoExtractor):
IE_NAME = 'kuwo:singer' IE_NAME = 'kuwo:singer'
_VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P<id>[^/]+?)/$' _VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
_TEST = { _TESTS = [{
'url': 'http://www.kuwo.cn/mingxing/bruno+mars/', 'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
'info_dict': { 'info_dict': {
'id': 'bruno+mars', 'id': 'bruno+mars',
'title': 'Bruno Mars', 'title': 'Bruno Mars',
}, },
'playlist_count': 10, 'playlist_count': 10,
} }, {
'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
'info_dict': {
'id': 'Ali',
'title': 'Ali',
},
'playlist_mincount': 95,
}]
def _real_extract(self, url): def _real_extract(self, url):
singer_id = self._match_id(url) singer_id = self._match_id(url)
@ -197,54 +204,28 @@ def _real_extract(self, url):
errnote='Unable to get singer info') errnote='Unable to get singer info')
singer_name = self._html_search_regex( singer_name = self._html_search_regex(
r'姓名:<span>(.+?)</span>', webpage, 'singer name') r'<div class="title clearfix">[\n\s\t]*?<h1>(.+?)<span', webpage, 'singer name'
)
entries = [
self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id)
for song_id in re.findall(
r'<a href="http://www\.kuwo\.cn/yinyue/([0-9]+)/" .+?>.+?</a>',
webpage, flags=re.DOTALL)
]
return self.playlist_result(entries, singer_id, singer_name)
class KuwoSingerMusicIE(InfoExtractor):
IE_NAME = 'kuwo:singermusic'
_VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P<id>[^/]+?)/music(_[0-9]+)?.htm'
_TEST = {
'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
'info_dict': {
'id': 'Ali',
'title': 'Ali的热门歌曲',
},
'playlist_mincount': 95,
}
def _real_extract(self, url):
singer_id = self._match_id(url)
list_name = None
entries = [] entries = []
first_page_only = False if re.match(r'.+/music(?:_[0-9]+)?\.htm', url) else True
for page_num in itertools.count(1): for page_num in itertools.count(1):
webpage = self._download_webpage( webpage = self._download_webpage(
'http://www.kuwo.cn/mingxing/%s/music_%d.htm' % (singer_id, page_num), 'http://www.kuwo.cn/mingxing/%s/music_%d.htm' % (singer_id, page_num),
singer_id, note='Download song list page #%d' % page_num, singer_id, note='Download song list page #%d' % page_num,
errnote='Unable to get song list page #%d' % page_num) errnote='Unable to get song list page #%d' % page_num)
if list_name is None:
list_name = self._html_search_regex(
r'<h1>([^<>]+)<span>', webpage, 'list name')
entries.extend([ entries.extend([
self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id) self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id)
for song_id in re.findall( for song_id in re.findall(
r'<p class="m_name"><a href="http://www\.kuwo\.cn/yinyue/([0-9]+)/', r'<p class="m_name"><a href="http://www\.kuwo\.cn/yinyue/([0-9]+)/',
webpage) webpage)
]) ][:10 if first_page_only else None])
if not re.search(r'<a href="[^"]+">下一页</a>', webpage):
if first_page_only or not re.search(r'<a href="[^"]+">下一页</a>', webpage):
break break
return self.playlist_result(entries, singer_id, list_name) return self.playlist_result(entries, singer_id, singer_name)
class KuwoCategoryIE(InfoExtractor): class KuwoCategoryIE(InfoExtractor):