diff options
author | Yen Chi Hsuan <yan12125@gmail.com> | 2015-09-26 19:28:16 +0800 |
---|---|---|
committer | Yen Chi Hsuan <yan12125@gmail.com> | 2015-09-26 19:28:16 +0800 |
commit | fe6ad195ae734951c879be41036cadbcf84eb8a7 (patch) | |
tree | 2f30ea57e78d7c3b983b35690e3068ff4d6c3c6d | |
parent | a82ba8d0ce8cf5daee9acff7a9f4a7238b2f1113 (diff) | |
parent | 7193650641f3fd84872b231e48263752d10b37b7 (diff) |
Merge pull request #6966 from remitamine/kuwo
[kuwo] fix title extraction and update test
-rw-r--r-- | youtube_dl/extractor/kuwo.py | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/youtube_dl/extractor/kuwo.py b/youtube_dl/extractor/kuwo.py index fa233377d..0c8ed5d07 100644 --- a/youtube_dl/extractor/kuwo.py +++ b/youtube_dl/extractor/kuwo.py @@ -57,6 +57,7 @@ class KuwoIE(KuwoBaseIE): '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': { @@ -76,9 +77,11 @@ class KuwoIE(KuwoBaseIE): 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'<h1[^>]+title="([^"]+)">', webpage, 'song name') + 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) |