Merge branch 'dcn' of github.com:remitamine/youtube-dl into remitamine-dcn

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

diff --git a/youtube_dl/extractor/kuwo.py b/youtube_dl/extractor/kuwo.py
index 2b5321cc25b2d74715d18db90c766e0fd465727e..0c8ed5d07258d463375c2848d2f93c79885bdaae 100644 (file)
--- a/youtube_dl/extractor/kuwo.py
+++ b/youtube_dl/extractor/kuwo.py
@@ -45,7 +45,8 @@ class KuwoBaseIE(InfoExtractor):
 
 class KuwoIE(KuwoBaseIE):
     IE_NAME = 'kuwo:song'
-    _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P<id>[0-9]+?)/'
+    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/',
         'info_dict': {
@@ -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': {
@@ -75,12 +77,14 @@ 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', default=None)
+            webpage, 'singer name', fatal=False)
         lrc_content = clean_html(get_element_by_id('lrcContent', webpage))
         if lrc_content == '暂无':     # indicates no lyrics
             lrc_content = None
@@ -89,7 +93,7 @@ class KuwoIE(KuwoBaseIE):
 
         album_id = self._html_search_regex(
             r'<p[^>]+class="album"[^<]+<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
-            webpage, 'album id', default=None, fatal=False)
+            webpage, 'album id', fatal=False)
 
         publish_time = None
         if album_id is not None:
@@ -100,7 +104,7 @@ class KuwoIE(KuwoBaseIE):
 
             publish_time = self._html_search_regex(
                 r'发行时间：(\d{4}-\d{2}-\d{2})', album_info_page,
-                'publish time', default=None)
+                'publish time', fatal=False)
             if publish_time:
                 publish_time = publish_time.replace('-', '')
 
@@ -116,7 +120,8 @@ class KuwoIE(KuwoBaseIE):
 
 class KuwoAlbumIE(InfoExtractor):
     IE_NAME = 'kuwo:album'
-    _VALID_URL = r'http://www\.kuwo\.cn/album/(?P<id>[0-9]+?)/'
+    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/',
         'info_dict': {
@@ -142,9 +147,8 @@ class KuwoAlbumIE(InfoExtractor):
             '%s简介：' % album_name)
 
         entries = [
-            self.url_result('http://www.kuwo.cn/yinyue/%s/' % song_id, 'Kuwo', song_id)
-            for song_id in re.findall(
-                r'<p[^>]+class="listen"><a[^>]+href="http://www\.kuwo\.cn/yinyue/(\d+)/"',
+            self.url_result(song_url, 'Kuwo') for song_url in re.findall(
+                r'<p[^>]+class="listen"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"',
                 webpage)
         ]
         return self.playlist_result(entries, album_id, album_name, album_intro)
@@ -152,13 +156,14 @@ 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',
         'info_dict': {
             'id': '香港中文龙虎榜',
             'title': '香港中文龙虎榜',
-            'description': 're:[0-9]{4}第[0-9]{2}期',
+            'description': 're:\d{4}第\d{2}期',
         },
         'playlist_mincount': 10,
     }
@@ -176,15 +181,15 @@ class KuwoChartIE(InfoExtractor):
             r'<p[^>]+class="tabDef">(\d{4}第\d{2}期)</p>', webpage, 'chart desc')
 
         entries = [
-            self.url_result('http://www.kuwo.cn/yinyue/%s/' % song_id, 'Kuwo', song_id)
-            for song_id in re.findall(
-                r'<a[^>]+href="http://www\.kuwo\.cn/yinyue/(\d+)/"', webpage)
+            self.url_result(song_url, 'Kuwo') for song_url in re.findall(
+                r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/"', webpage)
         ]
         return self.playlist_result(entries, chart_id, chart_name, chart_desc)
 
 
 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/',
@@ -200,6 +205,7 @@ 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):
@@ -213,7 +219,7 @@ class KuwoSingerIE(InfoExtractor):
         )
 
         entries = []
-        first_page_only = False if re.search(r'/music(?:_[0-9]+)?\.htm', url) else True
+        first_page_only = False if re.search(r'/music(?:_\d+)?\.htm', url) else True
         for page_num in itertools.count(1):
             webpage = self._download_webpage(
                 'http://www.kuwo.cn/mingxing/%s/music_%d.htm' % (singer_id, page_num),
@@ -221,9 +227,8 @@ class KuwoSingerIE(InfoExtractor):
                 errnote='Unable to get song list page #%d' % page_num)
 
             entries.extend([
-                self.url_result('http://www.kuwo.cn/yinyue/%s/' % song_id, 'Kuwo', song_id)
-                for song_id in re.findall(
-                    r'<p[^>]+class="m_name"><a[^>]+href="http://www\.kuwo\.cn/yinyue/([0-9]+)/',
+                self.url_result(song_url, 'Kuwo') for song_url in re.findall(
+                    r'<p[^>]+class="m_name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/',
                     webpage)
             ][:10 if first_page_only else None])
 
@@ -235,7 +240,8 @@ class KuwoSingerIE(InfoExtractor):
 
 class KuwoCategoryIE(InfoExtractor):
     IE_NAME = 'kuwo:category'
-    _VALID_URL = r'http://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>[0-9]+?).htm'
+    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',
         'info_dict': {
@@ -263,9 +269,7 @@ class KuwoCategoryIE(InfoExtractor):
             r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)
 
         entries = [
-            self.url_result(
-                'http://www.kuwo.cn/yinyue/%s/' % song['musicrid'],
-                'Kuwo', song['musicrid'])
+            self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo')
             for song in jsonm['musiclist']
         ]
         return self.playlist_result(entries, category_id, category_name, category_desc)
@@ -273,7 +277,8 @@ class KuwoCategoryIE(InfoExtractor):
 
 class KuwoMvIE(KuwoBaseIE):
     IE_NAME = 'kuwo:mv'
-    _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P<id>[0-9]+?)/'
+    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/',
         'info_dict': {