youtube-dl

commit e13b9e7885d83f09d95882a494d5e32153e7baa6
parent dd467d33d0883c0c0c94d7fc5ed041d5c12bb564
Author: remitamine <remitamine@gmail.com>
Date:   Thu, 24 Sep 2015 22:38:00 +0100

[keek] fix info extraction

Diffstat:
M
youtube_dl/extractor/keek.py
 | 
28
++++++----------------------

1 file changed, 6 insertions(+), 22 deletions(-)
diff --git a/youtube_dl/extractor/keek.py b/youtube_dl/extractor/keek.py
@@ -4,43 +4,27 @@ from .common import InfoExtractor
 
 
 class KeekIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<id>\w+)'
+    _VALID_URL = r'https?://(?:www\.)?keek\.com/keek/(?P<id>\w+)'
     IE_NAME = 'keek'
     _TEST = {
-        'url': 'https://www.keek.com/ytdl/keeks/NODfbab',
-        'md5': '09c5c109067536c1cec8bac8c21fea05',
+        'url': 'https://www.keek.com/keek/NODfbab',
+        'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83',
         'info_dict': {
             'id': 'NODfbab',
             'ext': 'mp4',
-            'uploader': 'youtube-dl project',
-            'uploader_id': 'ytdl',
-            'title': 'test chars: "\'/\\\u00e4<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de .',
+            'title': 'test chars: "\'/\\ä<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de . - Video - Videos on Keek',
         },
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        video_url = 'http://cdn.keek.com/keek/video/%s' % video_id
-        thumbnail = 'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
         webpage = self._download_webpage(url, video_id)
 
-        raw_desc = self._html_search_meta('description', webpage)
-        if raw_desc:
-            uploader = self._html_search_regex(
-                r'Watch (.*?)\s+\(', raw_desc, 'uploader', fatal=False)
-            uploader_id = self._html_search_regex(
-                r'Watch .*?\(@(.+?)\)', raw_desc, 'uploader_id', fatal=False)
-        else:
-            uploader = None
-            uploader_id = None
-
         return {
             'id': video_id,
-            'url': video_url,
+            'url': self._og_search_video_url(webpage),
             'ext': 'mp4',
             'title': self._og_search_title(webpage),
-            'thumbnail': thumbnail,
-            'uploader': uploader,
-            'uploader_id': uploader_id,
+            'thumbnail': self._og_search_thumbnail(webpage),
         }