[kuwo] fix title extraction and update test

[youtube-dl] / youtube_dl / extractor / kuwo.py

diff --git a/youtube_dl/extractor/kuwo.py b/youtube_dl/extractor/kuwo.py
index a021f3cdf49b02bc88afbf05412f255885d74f49..51137a982a9581fc6e2e39a1dafdc47351282b3a 100644 (file)
--- a/youtube_dl/extractor/kuwo.py
+++ b/youtube_dl/extractor/kuwo.py
@@ -45,6 +45,7 @@ class KuwoBaseIE(InfoExtractor):
 
 class KuwoIE(KuwoBaseIE):
     IE_NAME = 'kuwo:song'
+    IE_DESC = '酷我音乐'
     _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P<id>\d+?)/'
     _TESTS = [{
         'url': 'http://www.kuwo.cn/yinyue/635632/',
@@ -56,6 +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': {
@@ -77,7 +79,7 @@ class KuwoIE(KuwoBaseIE):
             errnote='Unable to get song detail info')
 
         song_name = self._html_search_regex(
-            r'<h1[^>]+title="([^"]+)">', webpage, 'song name')
+            r'(?s)class="[^"]*title[^"]*".*?<h1[^>]+title="([^"]+)"', webpage, 'song name')
         singer_name = self._html_search_regex(
             r'<div[^>]+class="s_img">\s*<a[^>]+title="([^>]+)"',
             webpage, 'singer name', fatal=False)
@@ -116,6 +118,7 @@ class KuwoIE(KuwoBaseIE):
 
 class KuwoAlbumIE(InfoExtractor):
     IE_NAME = 'kuwo:album'
+    IE_DESC = '酷我音乐 - 专辑'
     _VALID_URL = r'http://www\.kuwo\.cn/album/(?P<id>\d+?)/'
     _TEST = {
         'url': 'http://www.kuwo.cn/album/502294/',
@@ -151,6 +154,7 @@ class KuwoAlbumIE(InfoExtractor):
 
 class KuwoChartIE(InfoExtractor):
     IE_NAME = 'kuwo:chart'
+    IE_DESC = '酷我音乐 - 排行榜'
     _VALID_URL = r'http://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
     _TEST = {
         'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
@@ -183,6 +187,7 @@ class KuwoChartIE(InfoExtractor):
 
 class KuwoSingerIE(InfoExtractor):
     IE_NAME = 'kuwo:singer'
+    IE_DESC = '酷我音乐 - 歌手'
     _VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
     _TESTS = [{
         'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
@@ -198,6 +203,7 @@ class KuwoSingerIE(InfoExtractor):
             'title': 'Ali',
         },
         'playlist_mincount': 95,
+        'skip': 'Regularly stalls travis build',  # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540
     }]
 
     def _real_extract(self, url):
@@ -232,6 +238,7 @@ class KuwoSingerIE(InfoExtractor):
 
 class KuwoCategoryIE(InfoExtractor):
     IE_NAME = 'kuwo:category'
+    IE_DESC = '酷我音乐 - 分类'
     _VALID_URL = r'http://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
     _TEST = {
         'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
@@ -268,6 +275,7 @@ class KuwoCategoryIE(InfoExtractor):
 
 class KuwoMvIE(KuwoBaseIE):
     IE_NAME = 'kuwo:mv'
+    IE_DESC = '酷我音乐 - MV'
     _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
     _TEST = {
         'url': 'http://www.kuwo.cn/mv/6480076/',