[engadget] remove support for legacy urls
authorremitamine <remitamine@gmail.com>
Fri, 4 Mar 2016 09:40:39 +0000 (10:40 +0100)
committerremitamine <remitamine@gmail.com>
Fri, 4 Mar 2016 09:40:39 +0000 (10:40 +0100)
youtube_dl/extractor/engadget.py

index e4180701d7d5fe7f538d029e8ffb27235b6135df..e5e57d48518d3dd3999dad650d0c32406079ce33 100644 (file)
@@ -1,21 +1,13 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import (
-    url_basename,
-)
 
 
 class EngadgetIE(InfoExtractor):
-    _VALID_URL = r'''(?x)https?://www.engadget.com/
-        (?:video(?:/5min)?/(?P<id>\d+)|
-            [\d/]+/.*?)
-        '''
+    _VALID_URL = r'https?://www.engadget.com/video/(?P<id>\d+)'
 
     _TEST = {
-        'url': 'http://www.engadget.com/video/5min/518153925/',
+        'url': 'http://www.engadget.com/video/518153925/',
         'md5': 'c6820d4828a5064447a4d9fc73f312c9',
         'info_dict': {
             'id': '518153925',
@@ -27,15 +19,4 @@ class EngadgetIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
-        if video_id is not None:
-            return self.url_result('5min:%s' % video_id)
-        else:
-            title = url_basename(url)
-            webpage = self._download_webpage(url, title)
-            ids = re.findall(r'<iframe[^>]+?playList=(\d+)', webpage)
-            return {
-                '_type': 'playlist',
-                'title': title,
-                'entries': [self.url_result('5min:%s' % vid) for vid in ids]
-            }
+        return self.url_result('5min:%s' % video_id)