debian/control: Update list of extractors in long description.

[youtubedl] / youtube_dl / extractor / engadget.py

diff --git a/youtube_dl/extractor/engadget.py b/youtube_dl/extractor/engadget.py
index 4ea37ebd9f2072ea7610cfc4a8630e120fcfa81b..65635c18b7153ec188437f9c24cbe939c65304d7 100644 (file)
--- a/youtube_dl/extractor/engadget.py
+++ b/youtube_dl/extractor/engadget.py
@@ -1,21 +1,14 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 from .common import InfoExtractor

-from ..utils import (
-    url_basename,
-)

 
 
 class EngadgetIE(InfoExtractor):
 
 
 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>[^/?#]+)'

 
 

-    _TEST = {
-        'url': 'http://www.engadget.com/video/5min/518153925/',
+    _TESTS = [{
+        # video with 5min ID
+        'url': 'http://www.engadget.com/video/518153925/',

         'md5': 'c6820d4828a5064447a4d9fc73f312c9',
         'info_dict': {
             'id': '518153925',
         'md5': 'c6820d4828a5064447a4d9fc73f312c9',
         'info_dict': {
             'id': '518153925',


@@ -23,19 +16,12 @@ class EngadgetIE(InfoExtractor):
             'title': 'Samsung Galaxy Tab Pro 8.4 Review',
         },
         'add_ie': ['FiveMin'],
             'title': 'Samsung Galaxy Tab Pro 8.4 Review',
         },
         'add_ie': ['FiveMin'],

-    }
+    }, {
+        # video with vidible ID
+        'url': 'https://www.engadget.com/video/57a28462134aa15a39f0421a/',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     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('aol-video:%s' % video_id)