Merge tag 'upstream/2016.06.25'

[youtubedl] / youtube_dl / extractor / qqmusic.py

diff --git a/youtube_dl/extractor/qqmusic.py b/youtube_dl/extractor/qqmusic.py
index c98539f6a63c05fd99e0758fe38295afce2304a2..ff0af9543c2b5e5527f406958e9ae5ae4d1adbda 100644 (file)
--- a/youtube_dl/extractor/qqmusic.py
+++ b/youtube_dl/extractor/qqmusic.py
@@ -7,17 +7,18 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

+    sanitized_Request,

     strip_jsonp,
     unescapeHTML,
     clean_html,
     strip_jsonp,
     unescapeHTML,
     clean_html,

+    ExtractorError,

 )
 )

-from ..compat import compat_urllib_request

 
 
 class QQMusicIE(InfoExtractor):
     IE_NAME = 'qqmusic'
     IE_DESC = 'QQ音乐'
 
 
 class QQMusicIE(InfoExtractor):
     IE_NAME = 'qqmusic'
     IE_DESC = 'QQ音乐'

-    _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
+    _VALID_URL = r'https?://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'

     _TESTS = [{
         'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
         'md5': '9ce1c1c8445f561506d2e3cfb0255705',
     _TESTS = [{
         'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
         'md5': '9ce1c1c8445f561506d2e3cfb0255705',


@@ -171,13 +172,13 @@ class QQPlaylistBaseIE(InfoExtractor):
 class QQMusicSingerIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:singer'
     IE_DESC = 'QQ音乐 - 歌手'
 class QQMusicSingerIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:singer'
     IE_DESC = 'QQ音乐 - 歌手'

-    _VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
+    _VALID_URL = r'https?://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'

     _TEST = {
         'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
         'info_dict': {
             'id': '001BLpXF2DyJe2',
             'title': '林俊杰',
     _TEST = {
         'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
         'info_dict': {
             'id': '001BLpXF2DyJe2',
             'title': '林俊杰',

-            'description': 'md5:2a222d89ba4455a3af19940c0481bb78',
+            'description': 'md5:870ec08f7d8547c29c93010899103751',

         },
         'playlist_count': 12,
     }
         },
         'playlist_count': 12,
     }


@@ -201,7 +202,7 @@ class QQMusicSingerIE(QQPlaylistBaseIE):
         singer_desc = None
 
         if singer_id:
         singer_desc = None
 
         if singer_id:

-            req = compat_urllib_request.Request(
+            req = sanitized_Request(

                 'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg?utf8=1&outCharset=utf-8&format=xml&singerid=%s' % singer_id)
             req.add_header(
                 'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html')
                 'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg?utf8=1&outCharset=utf-8&format=xml&singerid=%s' % singer_id)
             req.add_header(
                 'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html')


@@ -216,7 +217,7 @@ class QQMusicSingerIE(QQPlaylistBaseIE):
 class QQMusicAlbumIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:album'
     IE_DESC = 'QQ音乐 - 专辑'
 class QQMusicAlbumIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:album'
     IE_DESC = 'QQ音乐 - 专辑'

-    _VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
+    _VALID_URL = r'https?://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'

 
     _TESTS = [{
         'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1',
 
     _TESTS = [{
         'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1',


@@ -259,7 +260,7 @@ class QQMusicAlbumIE(QQPlaylistBaseIE):
 class QQMusicToplistIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:toplist'
     IE_DESC = 'QQ音乐 - 排行榜'
 class QQMusicToplistIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:toplist'
     IE_DESC = 'QQ音乐 - 排行榜'

-    _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
+    _VALID_URL = r'https?://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'

 
     _TESTS = [{
         'url': 'http://y.qq.com/#type=toplist&p=global_123',
 
     _TESTS = [{
         'url': 'http://y.qq.com/#type=toplist&p=global_123',


@@ -272,7 +273,7 @@ class QQMusicToplistIE(QQPlaylistBaseIE):
         'url': 'http://y.qq.com/#type=toplist&p=top_3',
         'info_dict': {
             'id': 'top_3',
         'url': 'http://y.qq.com/#type=toplist&p=top_3',
         'info_dict': {
             'id': 'top_3',

-            'title': 'QQ音乐巅峰榜·欧美',
+            'title': '巅峰榜·欧美',

             'description': 'QQ音乐巅峰榜·欧美根据用户收听行为自动生成，集结当下最流行的欧美新歌！:更新时间：每周四22点|统'
                            '计周期：一周（上周四至本周三）|统计对象：三个月内发行的欧美歌曲|统计数量：100首|统计算法：根据'
                            '歌曲在一周内的有效播放次数，由高到低取前100名（同一歌手最多允许5首歌曲同时上榜）|有效播放次数：'
             'description': 'QQ音乐巅峰榜·欧美根据用户收听行为自动生成，集结当下最流行的欧美新歌！:更新时间：每周四22点|统'
                            '计周期：一周（上周四至本周三）|统计对象：三个月内发行的欧美歌曲|统计数量：100首|统计算法：根据'
                            '歌曲在一周内的有效播放次数，由高到低取前100名（同一歌手最多允许5首歌曲同时上榜）|有效播放次数：'


@@ -313,9 +314,9 @@ class QQMusicToplistIE(QQPlaylistBaseIE):
 class QQMusicPlaylistIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:playlist'
     IE_DESC = 'QQ音乐 - 歌单'
 class QQMusicPlaylistIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:playlist'
     IE_DESC = 'QQ音乐 - 歌单'

-    _VALID_URL = r'http://y\.qq\.com/#type=taoge&id=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://y\.qq\.com/#type=taoge&id=(?P<id>[0-9]+)'

 
 

-    _TEST = {
+    _TESTS = [{

         'url': 'http://y.qq.com/#type=taoge&id=3462654915',
         'info_dict': {
             'id': '3462654915',
         'url': 'http://y.qq.com/#type=taoge&id=3462654915',
         'info_dict': {
             'id': '3462654915',


@@ -323,7 +324,16 @@ class QQMusicPlaylistIE(QQPlaylistBaseIE):
             'description': 'md5:d2c9d758a96b9888cf4fe82f603121d4',
         },
         'playlist_count': 40,
             'description': 'md5:d2c9d758a96b9888cf4fe82f603121d4',
         },
         'playlist_count': 40,

-    }
+        'skip': 'playlist gone',
+    }, {
+        'url': 'http://y.qq.com/#type=taoge&id=1374105607',
+        'info_dict': {
+            'id': '1374105607',
+            'title': '易入人心的华语民谣',
+            'description': '民谣的歌曲易于传唱、、歌词朗朗伤口、旋律简单温馨。属于那种才入耳孔。却上心头的感觉。没有太多的复杂情绪。简单而直接地表达乐者的情绪，就是这样的简单才易入人心。',
+        },
+        'playlist_count': 20,
+    }]

 
     def _real_extract(self, url):
         list_id = self._match_id(url)
 
     def _real_extract(self, url):
         list_id = self._match_id(url)


@@ -331,14 +341,21 @@ class QQMusicPlaylistIE(QQPlaylistBaseIE):
         list_json = self._download_json(
             'http://i.y.qq.com/qzone-music/fcg-bin/fcg_ucc_getcdinfo_byids_cp.fcg?type=1&json=1&utf8=1&onlysong=0&disstid=%s'
             % list_id, list_id, 'Download list page',
         list_json = self._download_json(
             'http://i.y.qq.com/qzone-music/fcg-bin/fcg_ucc_getcdinfo_byids_cp.fcg?type=1&json=1&utf8=1&onlysong=0&disstid=%s'
             % list_id, list_id, 'Download list page',

-            transform_source=strip_jsonp)['cdlist'][0]
-
+            transform_source=strip_jsonp)
+        if not len(list_json.get('cdlist', [])):
+            if list_json.get('code'):
+                raise ExtractorError(
+                    'QQ Music said: error %d in fetching playlist info' % list_json['code'],
+                    expected=True)
+            raise ExtractorError('Unable to get playlist info')
+
+        cdlist = list_json['cdlist'][0]

         entries = [
             self.url_result(
                 'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
         entries = [
             self.url_result(
                 'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']

-            ) for song in list_json['songlist']
+            ) for song in cdlist['songlist']

         ]
 
         ]
 

-        list_name = list_json.get('dissname')
-        list_description = clean_html(unescapeHTML(list_json.get('desc')))
+        list_name = cdlist.get('dissname')
+        list_description = clean_html(unescapeHTML(cdlist.get('desc')))

         return self.playlist_result(entries, list_id, list_name, list_description)
         return self.playlist_result(entries, list_id, list_name, list_description)