Add base info extractor class

youtube_dl/extractor/deezer.py

@@ -10,27 +10,16 @@ from ..utils import (
     orderedSet,
 )
 
-class DeezerPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?playlist/(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://www.deezer.com/playlist/176747451',
-        'info_dict': {
-            'id': '176747451',
-            'title': 'Best!',
-            'uploader': 'anonymous',
-            'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
-        },
-        'playlist_count': 29,
-    }
+class DeezerBaseInfoExtractor(InfoExtractor):
 
-    def _real_extract(self, url):
+    def get_data(self, url):
         if 'test' not in self._downloader.params:
             self._downloader.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
 
         mobj = re.match(self._VALID_URL, url)
-        playlist_id = mobj.group('id')
+        id = mobj.group('id')
 
-        webpage = self._download_webpage(url, playlist_id)
+        webpage = self._download_webpage(url, id)
         geoblocking_msg = self._html_search_regex(
             r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message',
             default=None)
@@ -43,6 +32,23 @@ class DeezerPlaylistIE(InfoExtractor):
              r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n'),
             webpage, 'data JSON')
         data = json.loads(data_json)
+        return id, webpage, data
+
+class DeezerPlaylistIE(DeezerBaseInfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?playlist/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.deezer.com/playlist/176747451',
+        'info_dict': {
+            'id': '176747451',
+            'title': 'Best!',
+            'uploader': 'anonymous',
+            'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
+        },
+        'playlist_count': 29,
+    }
+
+    def _real_extract(self, url):
+        playlist_id, webpage, data = self.get_data(url)
 
         playlist_title = data.get('DATA').get('TITLE')
         playlist_uploader = data.get('DATA').get('PARENT_USERNAME')