Merge tag 'upstream/2015.07.21'

[youtubedl] / youtube_dl / extractor / keek.py

diff --git a/youtube_dl/extractor/keek.py b/youtube_dl/extractor/keek.py
index e2093a0be92dd700002a20c00dd93f6e525e6da1..c0956ba0902be3b8fd9a9188872eb90ab9acdefa 100644 (file)
--- a/youtube_dl/extractor/keek.py
+++ b/youtube_dl/extractor/keek.py
@@ -1,32 +1,46 @@
-import re
+from __future__ import unicode_literals

 
 from .common import InfoExtractor
 
 
 class KeekIE(InfoExtractor):
 
 from .common import InfoExtractor
 
 
 class KeekIE(InfoExtractor):

-    _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
-    IE_NAME = u'keek'
+    _VALID_URL = r'https?://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<id>\w+)'
+    IE_NAME = 'keek'
+    _TEST = {
+        'url': 'https://www.keek.com/ytdl/keeks/NODfbab',
+        'md5': '09c5c109067536c1cec8bac8c21fea05',
+        '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 .',
+        },
+    }

 
     def _real_extract(self, url):
 
     def _real_extract(self, url):

-        m = re.match(self._VALID_URL, url)
-        video_id = m.group('videoID')
+        video_id = self._match_id(url)

 
 

-        video_url = u'http://cdn.keek.com/keek/video/%s' % video_id
-        thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
+        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)
 
         webpage = self._download_webpage(url, video_id)
 

-        video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
-            webpage, u'title')
-
-        uploader = self._html_search_regex(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
-            webpage, u'uploader', fatal=False)
-
-        info = {
-                'id': video_id,
-                'url': video_url,
-                'ext': 'mp4',
-                'title': video_title,
-                'thumbnail': thumbnail,
-                'uploader': uploader
+        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,
+            'ext': 'mp4',
+            'title': self._og_search_title(webpage),
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_id': uploader_id,

         }
         }

-        return [info]