[kwuo:song] Fix extraction and update the test
This commit is contained in:
		
							parent
							
								
									c14dc00df3
								
							
						
					
					
						commit
						a82398bd72
					
				
					 1 changed files with 6 additions and 6 deletions
				
			
		| 
						 | 
				
			
			@ -81,7 +81,7 @@ class KuwoIE(KuwoBaseIE):
 | 
			
		|||
            'id': '6446136',
 | 
			
		||||
            'ext': 'mp3',
 | 
			
		||||
            'title': '心',
 | 
			
		||||
            'description': 'md5:b2ab6295d014005bfc607525bfc1e38a',
 | 
			
		||||
            'description': 'md5:5d0e947b242c35dc0eb1d2fce9fbf02c',
 | 
			
		||||
            'creator': 'IU',
 | 
			
		||||
            'upload_date': '20150518',
 | 
			
		||||
        },
 | 
			
		||||
| 
						 | 
				
			
			@ -102,10 +102,10 @@ class KuwoIE(KuwoBaseIE):
 | 
			
		|||
            raise ExtractorError('this song has been offline because of copyright issues', expected=True)
 | 
			
		||||
 | 
			
		||||
        song_name = self._html_search_regex(
 | 
			
		||||
            r'(?s)class="(?:[^"\s]+\s+)*title(?:\s+[^"\s]+)*".*?<h1[^>]+title="([^"]+)"', webpage, 'song name')
 | 
			
		||||
        singer_name = self._html_search_regex(
 | 
			
		||||
            r'<div[^>]+class="s_img">\s*<a[^>]+title="([^>]+)"',
 | 
			
		||||
            webpage, 'singer name', fatal=False)
 | 
			
		||||
            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
 | 
			
		||||
| 
						 | 
				
			
			@ -114,7 +114,7 @@ class KuwoIE(KuwoBaseIE):
 | 
			
		|||
        self._sort_formats(formats)
 | 
			
		||||
 | 
			
		||||
        album_id = self._html_search_regex(
 | 
			
		||||
            r'<p[^>]+class="album"[^<]+<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
 | 
			
		||||
            r'<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
 | 
			
		||||
            webpage, 'album id', fatal=False)
 | 
			
		||||
 | 
			
		||||
        publish_time = None
 | 
			
		||||
| 
						 | 
				
			
			
 | 
			
		|||
		Loading…
	
	Add table
		Add a link
		
	
		Reference in a new issue