Annotate changelog with bugs closed.

[youtubedl] / youtube_dl / extractor / gamekings.py

diff --git a/youtube_dl/extractor/gamekings.py b/youtube_dl/extractor/gamekings.py
index c91669b0ebaeac6085ba010c242dc571b28e57e1..027f55eb2b7338dd2459c8128d587c0ac858434e 100644 (file)
--- a/youtube_dl/extractor/gamekings.py
+++ b/youtube_dl/extractor/gamekings.py
@@ -1,38 +1,67 @@
-import re
+# coding: utf-8
+from __future__ import unicode_literals

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

+from ..utils import (
+    xpath_text,
+    xpath_with_ns,
+)

 
 
 class GamekingsIE(InfoExtractor):
 
 
 class GamekingsIE(InfoExtractor):

-    _VALID_URL = r'http?://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)'
-    _TEST = {
-        u"url": u"http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/",
-        u'file': u'20130811.mp4',
+    _VALID_URL = r'http://www\.gamekings\.tv/(?:videos|nieuws)/(?P<id>[^/]+)'
+    _TESTS = [{
+        'url': 'http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/',

         # MD5 is flaky, seems to change regularly
         # MD5 is flaky, seems to change regularly

-        #u'md5': u'2f32b1f7b80fdc5cb616efb4f387f8a3',
-        u'info_dict': {
-            u"title": u"Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review",
-            u"description": u"Melle en Steven hebben voor de review een week in de rechtbank doorbracht met Phoenix Wright: Ace Attorney - Dual Destinies.",
-        }
-    }
+        # 'md5': '2f32b1f7b80fdc5cb616efb4f387f8a3',
+        'info_dict': {
+            'id': 'phoenix-wright-ace-attorney-dual-destinies-review',
+            'ext': 'mp4',
+            'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review',
+            'description': 'md5:36fd701e57e8c15ac8682a2374c99731',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }, {
+        # vimeo video
+        'url': 'http://www.gamekings.tv/videos/the-legend-of-zelda-majoras-mask/',
+        'md5': '12bf04dfd238e70058046937657ea68d',
+        'info_dict': {
+            'id': 'the-legend-of-zelda-majoras-mask',
+            'ext': 'mp4',
+            'title': 'The Legend of Zelda: Majora’s Mask',
+            'description': 'md5:9917825fe0e9f4057601fe1e38860de3',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }, {
+        'url': 'http://www.gamekings.tv/nieuws/gamekings-extra-shelly-en-david-bereiden-zich-voor-op-de-livestream/',
+        'only_matching': True,
+    }]

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

+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)

 
 

-        mobj = re.match(self._VALID_URL, url)
-        name = mobj.group('name')
-        webpage = self._download_webpage(url, name)
-        video_url = self._og_search_video_url(webpage)
+        playlist_id = self._search_regex(
+            r'gogoVideo\(\s*\d+\s*,\s*"([^"]+)', webpage, 'playlist id')

 
 

-        video = re.search(r'[0-9]+', video_url)
-        video_id = video.group(0)
+        playlist = self._download_xml(
+            'http://www.gamekings.tv/wp-content/themes/gk2010/rss_playlist.php?id=%s' % playlist_id,
+            video_id)

 
 

-        # Todo: add medium format
-        video_url = video_url.replace(video_id, 'large/' + video_id)
+        NS_MAP = {
+            'jwplayer': 'http://rss.jwpcdn.com/'
+        }
+
+        item = playlist.find('./channel/item')
+
+        thumbnail = xpath_text(item, xpath_with_ns('./jwplayer:image', NS_MAP), 'thumbnail')
+        video_url = item.find(xpath_with_ns('./jwplayer:source', NS_MAP)).get('file')

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,

-            'ext': 'mp4',

             'url': video_url,
             'title': self._og_search_title(webpage),
             'description': self._og_search_description(webpage),
             'url': video_url,
             'title': self._og_search_title(webpage),
             'description': self._og_search_description(webpage),

+            'thumbnail': thumbnail,

         }
         }