]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/keek.py
Prepare to release.
[youtubedl] / youtube_dl / extractor / keek.py
index e2093a0be92dd700002a20c00dd93f6e525e6da1..94a03d277a227733480b8a73f5535f9f3410be15 100644 (file)
@@ -1,32 +1,39 @@
-import re
+# coding: utf-8
+from __future__ import unicode_literals
 
 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/keek/(?P<id>\w+)'
+    IE_NAME = 'keek'
+    _TEST = {
+        'url': 'https://www.keek.com/keek/NODfbab',
+        'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83',
+        'info_dict': {
+            'id': 'NODfbab',
+            'ext': 'mp4',
+            'title': 'md5:35d42050a3ece241d5ddd7fdcc6fd896',
+            'uploader': 'ytdl',
+            'uploader_id': 'eGT5bab',
+        },
+    }
 
     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
         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
+        return {
+            'id': video_id,
+            'url': self._og_search_video_url(webpage),
+            'ext': 'mp4',
+            'title': self._og_search_description(webpage).strip(),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'uploader': self._search_regex(
+                r'data-username=(["\'])(?P<uploader>.+?)\1', webpage,
+                'uploader', fatal=False, group='uploader'),
+            'uploader_id': self._search_regex(
+                r'data-user-id=(["\'])(?P<uploader_id>.+?)\1', webpage,
+                'uploader id', fatal=False, group='uploader_id'),
         }
-        return [info]