[mfs] Modernize

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

diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py
index 1290cd9f7028aace78fc104cceb76b33da6752ca..1c498d8c8fa0cc95a2963a19384201a42ec2fa4b 100644 (file)
--- a/youtube_dl/extractor/empflix.py
+++ b/youtube_dl/extractor/empflix.py
@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import fix_xml_ampersands
 
 
 class EmpflixIE(InfoExtractor):
@@ -35,22 +36,23 @@ class EmpflixIE(InfoExtractor):
             r'flashvars\.config = escape\("([^"]+)"',
             webpage, 'flashvars.config')
 
-        # XML is malformed
-        cfg_xml = self._download_webpage(
-            cfg_url, video_id, note='Downloading metadata')
+        cfg_xml = self._download_xml(
+            cfg_url, video_id, note='Downloading metadata',
+            transform_source=fix_xml_ampersands)
 
         formats = [
             {
-                'url': item[1],
-                'format_id': item[0],
-            } for item in re.findall(
-                r'<item>\s*<res>([^>]+)</res>\s*<videoLink>([^<]+)</videoLink>\s*</item>', cfg_xml)
+                'url': item.find('videoLink').text,
+                'format_id': item.find('res').text,
+            } for item in cfg_xml.findall('./quality/item')
         ]
+        thumbnail = cfg_xml.find('./startThumb').text
 
         return {
             'id': video_id,
             'title': video_title,
             'description': video_description,
+            'thumbnail': thumbnail,
             'formats': formats,
             'age_limit': age_limit,
         }