X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fkuwo.py;h=11b31a69943e3252597a433b69e9ddeb471527fa;hb=6461f2b7ec5fa0114d4bb38ca27c0f72edff8e23;hp=86c17c931f1d41f8276f5883ed2139f6348759c2;hpb=e621a344e6ec3518420f0b13577726615c2f4485;p=youtube-dl diff --git a/youtube_dl/extractor/kuwo.py b/youtube_dl/extractor/kuwo.py index 86c17c931..11b31a699 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 @@ -268,7 +268,7 @@ class KuwoCategoryIE(InfoExtractor): 'title': '八十年代精选', 'description': '这些都是属于八十年代的回忆!', }, - 'playlist_count': 30, + 'playlist_mincount': 24, } def _real_extract(self, url): @@ -283,6 +283,8 @@ class KuwoCategoryIE(InfoExtractor): category_desc = remove_start( get_element_by_id('intro', webpage).strip(), '%s简介:' % category_name) + if category_desc == '暂无': + category_desc = None jsonm = self._parse_json(self._html_search_regex( r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)