Merge branch 'pr-twitter' of https://github.com/atomicdryad/youtube-dl into atomicdry...

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

diff --git a/youtube_dl/extractor/qqmusic.py b/youtube_dl/extractor/qqmusic.py
index 8ead04606e8ac8f1e334248b47916dcf550cf333..c98539f6a63c05fd99e0758fe38295afce2304a2 100644 (file)
--- a/youtube_dl/extractor/qqmusic.py
+++ b/youtube_dl/extractor/qqmusic.py
@@ -25,7 +25,7 @@ class QQMusicIE(InfoExtractor):
             'id': '004295Et37taLD',
             'ext': 'mp3',
             'title': '可惜没如果',
-            'upload_date': '20141227',
+            'release_date': '20141227',
             'creator': '林俊杰',
             'description': 'md5:d327722d0361576fde558f1ac68a7065',
             'thumbnail': 're:^https?://.*\.jpg$',
@@ -38,11 +38,26 @@ class QQMusicIE(InfoExtractor):
             'id': '004MsGEo3DdNxV',
             'ext': 'mp3',
             'title': '如果',
-            'upload_date': '20050626',
+            'release_date': '20050626',
             'creator': '李季美',
             'description': 'md5:46857d5ed62bc4ba84607a805dccf437',
             'thumbnail': 're:^https?://.*\.jpg$',
         }
+    }, {
+        'note': 'lyrics not in .lrc format',
+        'url': 'http://y.qq.com/#type=song&mid=001JyApY11tIp6',
+        'info_dict': {
+            'id': '001JyApY11tIp6',
+            'ext': 'mp3',
+            'title': 'Shadows Over Transylvania',
+            'release_date': '19970225',
+            'creator': 'Dark Funeral',
+            'description': 'md5:ed14d5bd7ecec19609108052c25b2c11',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }]
 
     _FORMATS = {
@@ -58,11 +73,6 @@ class QQMusicIE(InfoExtractor):
         curMs = int(time.time() * 1000) % 1000
         return int(round(random.random() * 2147483647) * curMs % 1E10)
 
-    def _filter_lrc(self, data):
-        lyrics_expr = r'(\[[0-9]{2}:[0-9]{2}\.[0-9]{2,}\][^\n]*|\[[^\]]*\])'
-        texts = re.findall(lyrics_expr, data)
-        return ''.join(i + "\n" for i in texts)
-
     def _real_extract(self, url):
         mid = self._match_id(url)
 
@@ -117,13 +127,15 @@ class QQMusicIE(InfoExtractor):
         self._check_formats(formats, mid)
         self._sort_formats(formats)
 
-        actual_lrc_lyrics = self._filter_lrc(lrc_content)
+        actual_lrc_lyrics = ''.join(
+            line + '\n' for line in re.findall(
+                r'(?m)^(\[[0-9]{2}:[0-9]{2}(?:\.[0-9]{2,})?\][^\n]*|\[[^\]]*\])', lrc_content))
 
         info_dict = {
             'id': mid,
             'formats': formats,
             'title': song_name,
-            'upload_date': publish_time,
+            'release_date': publish_time,
             'creator': singer,
             'description': lrc_content,
             'thumbnail': thumbnail_url