Merge tag 'upstream/2015.07.21'

[youtubedl] / youtube_dl / extractor / qqmusic.py

diff --git a/youtube_dl/extractor/qqmusic.py b/youtube_dl/extractor/qqmusic.py
index f773332a895b1b147ae9609229700a0c887a362f..1654a641f00db6833056571394b4dbe0b2856150 100644 (file)
--- a/youtube_dl/extractor/qqmusic.py
+++ b/youtube_dl/extractor/qqmusic.py
@@ -9,26 +9,48 @@ from .common import InfoExtractor
 from ..utils import (
     strip_jsonp,
     unescapeHTML,
 from ..utils import (
     strip_jsonp,
     unescapeHTML,

+    clean_html,

 )
 from ..compat import compat_urllib_request
 
 
 class QQMusicIE(InfoExtractor):
     IE_NAME = 'qqmusic'
 )
 from ..compat import compat_urllib_request
 
 
 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]+)'
     _TESTS = [{
         'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
     _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
     _TESTS = [{
         'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',

-        'md5': 'bed90b6db2a7a7a7e11bc585f471f63a',
+        'md5': '9ce1c1c8445f561506d2e3cfb0255705',

         'info_dict': {
             'id': '004295Et37taLD',
         'info_dict': {
             'id': '004295Et37taLD',

-            'ext': 'm4a',
+            'ext': 'mp3',

             'title': '可惜没如果',
             'upload_date': '20141227',
             'creator': '林俊杰',
             'description': 'md5:d327722d0361576fde558f1ac68a7065',
             'title': '可惜没如果',
             'upload_date': '20141227',
             'creator': '林俊杰',
             'description': 'md5:d327722d0361576fde558f1ac68a7065',

+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }, {
+        'note': 'There is no mp3-320 version of this song.',
+        'url': 'http://y.qq.com/#type=song&mid=004MsGEo3DdNxV',
+        'md5': 'fa3926f0c585cda0af8fa4f796482e3e',
+        'info_dict': {
+            'id': '004MsGEo3DdNxV',
+            'ext': 'mp3',
+            'title': '如果',
+            'upload_date': '20050626',
+            'creator': '李季美',
+            'description': 'md5:46857d5ed62bc4ba84607a805dccf437',
+            'thumbnail': 're:^https?://.*\.jpg$',

         }
     }]
 
         }
     }]
 

+    _FORMATS = {
+        'mp3-320': {'prefix': 'M800', 'ext': 'mp3', 'preference': 40, 'abr': 320},
+        'mp3-128': {'prefix': 'M500', 'ext': 'mp3', 'preference': 30, 'abr': 128},
+        'm4a': {'prefix': 'C200', 'ext': 'm4a', 'preference': 10}
+    }
+

     # Reference: m_r_GetRUin() in top_player.js
     # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
     @staticmethod
     # Reference: m_r_GetRUin() in top_player.js
     # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
     @staticmethod


@@ -62,21 +84,42 @@ class QQMusicIE(InfoExtractor):
         if lrc_content:
             lrc_content = lrc_content.replace('\\n', '\n')
 
         if lrc_content:
             lrc_content = lrc_content.replace('\\n', '\n')
 

+        thumbnail_url = None
+        albummid = self._search_regex(
+            [r'albummid:\'([0-9a-zA-Z]+)\'', r'"albummid":"([0-9a-zA-Z]+)"'],
+            detail_info_page, 'album mid', default=None)
+        if albummid:
+            thumbnail_url = "http://i.gtimg.cn/music/photo/mid_album_500/%s/%s/%s.jpg" \
+                            % (albummid[-2:-1], albummid[-1], albummid)
+

         guid = self.m_r_get_ruin()
 
         vkey = self._download_json(
             'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid,
             mid, note='Retrieve vkey', errnote='Unable to get vkey',
             transform_source=strip_jsonp)['key']
         guid = self.m_r_get_ruin()
 
         vkey = self._download_json(
             'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid,
             mid, note='Retrieve vkey', errnote='Unable to get vkey',
             transform_source=strip_jsonp)['key']

-        song_url = 'http://cc.stream.qqmusic.qq.com/C200%s.m4a?vkey=%s&guid=%s&fromtag=0' % (mid, vkey, guid)
+
+        formats = []
+        for format_id, details in self._FORMATS.items():
+            formats.append({
+                'url': 'http://cc.stream.qqmusic.qq.com/%s%s.%s?vkey=%s&guid=%s&fromtag=0'
+                       % (details['prefix'], mid, details['ext'], vkey, guid),
+                'format': format_id,
+                'format_id': format_id,
+                'preference': details['preference'],
+                'abr': details.get('abr'),
+            })
+        self._check_formats(formats, mid)
+        self._sort_formats(formats)

 
         return {
             'id': mid,
 
         return {
             'id': mid,

-            'url': song_url,
+            'formats': formats,

             'title': song_name,
             'upload_date': publish_time,
             'creator': singer,
             'description': lrc_content,
             'title': song_name,
             'upload_date': publish_time,
             'creator': singer,
             'description': lrc_content,

+            'thumbnail': thumbnail_url,

         }
 
 
         }
 
 


@@ -100,6 +143,7 @@ class QQPlaylistBaseIE(InfoExtractor):
 
 class QQMusicSingerIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:singer'
 
 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]+)'
     _TEST = {
         'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
     _VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
     _TEST = {
         'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',


@@ -144,39 +188,50 @@ class QQMusicSingerIE(QQPlaylistBaseIE):
 
 class QQMusicAlbumIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:album'
 
 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'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
 

-    _TEST = {
-        'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1&play=0',
+    _TESTS = [{
+        'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1',

         'info_dict': {
             'id': '000gXCTb2AhRR1',
             'title': '我们都是这样长大的',
         'info_dict': {
             'id': '000gXCTb2AhRR1',
             'title': '我们都是这样长大的',

-            'description': 'md5:d216c55a2d4b3537fe4415b8767d74d6',
+            'description': 'md5:179c5dce203a5931970d306aa9607ea6',

         },
         'playlist_count': 4,
         },
         'playlist_count': 4,

-    }
+    }, {
+        'url': 'http://y.qq.com/#type=album&mid=002Y5a3b3AlCu3',
+        'info_dict': {
+            'id': '002Y5a3b3AlCu3',
+            'title': '그리고...',
+            'description': 'md5:a48823755615508a95080e81b51ba729',
+        },
+        'playlist_count': 8,
+    }]

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

-        album_page = self._download_webpage(
-            self.qq_static_url('album', mid), mid, 'Download album page')
-
-        entries = self.get_entries_from_page(album_page)
+        album = self._download_json(
+            'http://i.y.qq.com/v8/fcg-bin/fcg_v8_album_info_cp.fcg?albummid=%s&format=json' % mid,
+            mid, 'Download album page')['data']

 
 

-        album_name = self._html_search_regex(
-            r"albumname\s*:\s*'([^']+)',", album_page, 'album name',
-            default=None)
-
-        album_detail = self._html_search_regex(
-            r'<div class="album_detail close_detail">\s*<p>((?:[^<>]+(?:<br />)?)+)</p>',
-            album_page, 'album details', default=None)
+        entries = [
+            self.url_result(
+                'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
+            ) for song in album['list']
+        ]
+        album_name = album.get('name')
+        album_detail = album.get('desc')
+        if album_detail is not None:
+            album_detail = album_detail.strip()

 
         return self.playlist_result(entries, mid, album_name, album_detail)
 
 
 class QQMusicToplistIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:toplist'
 
         return self.playlist_result(entries, mid, album_name, album_detail)
 
 
 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]+)'
 
     _TESTS = [{
     _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
 
     _TESTS = [{


@@ -226,3 +281,37 @@ class QQMusicToplistIE(QQPlaylistBaseIE):
         list_name = topinfo.get('ListName')
         list_description = topinfo.get('info')
         return self.playlist_result(entries, list_id, list_name, list_description)
         list_name = topinfo.get('ListName')
         list_description = topinfo.get('info')
         return self.playlist_result(entries, list_id, list_name, list_description)

+
+
+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]+)'
+
+    _TEST = {
+        'url': 'http://y.qq.com/#type=taoge&id=3462654915',
+        'info_dict': {
+            'id': '3462654915',
+            'title': '韩国5月新歌精选下旬',
+            'description': 'md5:d2c9d758a96b9888cf4fe82f603121d4',
+        },
+        'playlist_count': 40,
+    }
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+
+        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]
+
+        entries = [
+            self.url_result(
+                'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
+            ) for song in list_json['songlist']
+        ]
+
+        list_name = list_json.get('dissname')
+        list_description = clean_html(unescapeHTML(list_json.get('desc')))
+        return self.playlist_result(entries, list_id, list_name, list_description)