Improve some _VALID_URLs

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

diff --git a/youtube_dl/extractor/kuwo.py b/youtube_dl/extractor/kuwo.py
index c0ece51133a441629a0272757f1a5e8157f671f6..ba621ca7b5edb205f83e3cc42d3596d3c332e23f 100644 (file)
--- a/youtube_dl/extractor/kuwo.py
+++ b/youtube_dl/extractor/kuwo.py
@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     get_element_by_id,
     clean_html,
@@ -26,11 +27,6 @@ class KuwoBaseIE(InfoExtractor):
     def _get_formats(self, song_id, tolerate_ip_deny=False):
         formats = []
         for file_format in self._FORMATS:
-            headers = {}
-            cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
-            if cn_verification_proxy:
-                headers['Ytdl-request-proxy'] = cn_verification_proxy
-
             query = {
                 'format': file_format['ext'],
                 'br': file_format.get('br', ''),
@@ -42,7 +38,7 @@ class KuwoBaseIE(InfoExtractor):
             song_url = self._download_webpage(
                 'http://antiserver.kuwo.cn/anti.s',
                 song_id, note='Download %s url info' % file_format['format'],
-                query=query, headers=headers,
+                query=query, headers=self.geo_verification_headers(),
             )
 
             if song_url == 'IPDeny' and not tolerate_ip_deny:
@@ -63,7 +59,7 @@ class KuwoBaseIE(InfoExtractor):
 class KuwoIE(KuwoBaseIE):
     IE_NAME = 'kuwo:song'
     IE_DESC = '酷我音乐'
-    _VALID_URL = r'https?://www\.kuwo\.cn/yinyue/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/yinyue/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.kuwo.cn/yinyue/635632/',
         'info_dict': {
@@ -81,7 +77,7 @@ class KuwoIE(KuwoBaseIE):
             'id': '6446136',
             'ext': 'mp3',
             'title': '心',
-            'description': 'md5:b2ab6295d014005bfc607525bfc1e38a',
+            'description': 'md5:5d0e947b242c35dc0eb1d2fce9fbf02c',
             'creator': 'IU',
             'upload_date': '20150518',
         },
@@ -102,10 +98,10 @@ 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]+)*".*?<h1[^>]+title="([^"]+)"', webpage, 'song name')
-        singer_name = self._html_search_regex(
-            r'<div[^>]+class="s_img">\s*<a[^>]+title="([^>]+)"',
-            webpage, 'singer name', fatal=False)
+            r'<p[^>]+id="lrcName">([^<]+)</p>', webpage, 'song name')
+        singer_name = remove_start(self._html_search_regex(
+            r'<a[^>]+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 +110,7 @@ class KuwoIE(KuwoBaseIE):
         self._sort_formats(formats)
 
         album_id = self._html_search_regex(
-            r'<p[^>]+class="album"[^<]+<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
+            r'<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
             webpage, 'album id', fatal=False)
 
         publish_time = None
@@ -143,13 +139,13 @@ class KuwoIE(KuwoBaseIE):
 class KuwoAlbumIE(InfoExtractor):
     IE_NAME = 'kuwo:album'
     IE_DESC = '酷我音乐 - 专辑'
-    _VALID_URL = r'https?://www\.kuwo\.cn/album/(?P<id>\d+?)/'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/album/(?P<id>\d+?)/'
     _TEST = {
         'url': 'http://www.kuwo.cn/album/502294/',
         'info_dict': {
             'id': '502294',
-            'title': 'M',
-            'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c',
+            'title': 'Made\xa0Series\xa0《M》',
+            'description': 'md5:d463f0d8a0ff3c3ea3d6ed7452a9483f',
         },
         'playlist_count': 2,
     }
@@ -204,12 +200,12 @@ class KuwoChartIE(InfoExtractor):
 class KuwoSingerIE(InfoExtractor):
     IE_NAME = 'kuwo:singer'
     IE_DESC = '酷我音乐 - 歌手'
-    _VALID_URL = r'https?://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mingxing/(?P<id>[^/]+)'
     _TESTS = [{
         'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
         'info_dict': {
             'id': 'bruno+mars',
-            'title': 'Bruno Mars',
+            'title': 'Bruno\xa0Mars',
         },
         'playlist_mincount': 329,
     }, {
@@ -247,8 +243,9 @@ class KuwoSingerIE(InfoExtractor):
                 query={'artistId': artist_id, 'pn': page_num, 'rn': self.PAGE_SIZE})
 
             return [
-                self.url_result(song_url, 'Kuwo') for song_url in re.findall(
-                    r'<div[^>]+class="name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)',
+                self.url_result(compat_urlparse.urljoin(url, song_url), 'Kuwo')
+                for song_url in re.findall(
+                    r'<div[^>]+class="name"><a[^>]+href="(/yinyue/\d+)',
                     webpage)
             ]
 
@@ -268,7 +265,7 @@ 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': 24,
+        'playlist_mincount': 24,
     }
 
     def _real_extract(self, url):
@@ -283,6 +280,8 @@ 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)
@@ -297,14 +296,14 @@ class KuwoCategoryIE(InfoExtractor):
 class KuwoMvIE(KuwoBaseIE):
     IE_NAME = 'kuwo:mv'
     IE_DESC = '酷我音乐 - MV'
-    _VALID_URL = r'https?://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mv/(?P<id>\d+?)/'
     _TEST = {
         'url': 'http://www.kuwo.cn/mv/6480076/',
         'info_dict': {
             'id': '6480076',
             'ext': 'mp4',
             'title': 'My HouseMV',
-            'creator': '2PM',
+            'creator': 'PM02:00',
         },
         # In this video, music URLs (anti.s) are blocked outside China and
         # USA, while the MV URL (mvurl) is available globally, so force the MV