From a82398bd72272987133c4b81cad46139ec4b5359 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Sun, 24 Apr 2016 22:19:26 +0800 Subject: [PATCH] [kwuo:song] Fix extraction and update the test --- youtube_dl/extractor/kuwo.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/kuwo.py b/youtube_dl/extractor/kuwo.py index a02638665..3740869c7 100644 --- a/youtube_dl/extractor/kuwo.py +++ b/youtube_dl/extractor/kuwo.py @@ -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]+)*".*?]+title="([^"]+)"', webpage, 'song name') - singer_name = self._html_search_regex( - r']+class="s_img">\s*]+title="([^>]+)"', - webpage, 'singer name', fatal=False) + r']+id="lrcName">([^<]+)

', webpage, 'song name') + singer_name = remove_start(self._html_search_regex( + r']+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']+class="album"[^<]+]+href="http://www\.kuwo\.cn/album/(\d+)/"', + r']+href="http://www\.kuwo\.cn/album/(\d+)/"', webpage, 'album id', fatal=False) publish_time = None