From 5f3e0b69efa8ae80f536fb54ace4bb4d9c667d2e Mon Sep 17 00:00:00 2001
From: Entropy <0fiscalentropy@users.noreply.github.com>
Date: Fri, 7 Apr 2017 21:52:48 +0200
Subject: [PATCH] [TheSun] Add new extractor

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/thesun.py     | 27 +++++++++++++++++++++++++++
 2 files changed, 28 insertions(+)
 create mode 100644 youtube_dl/extractor/thesun.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 72728d919..01865479c 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -983,6 +983,7 @@ from .theplatform import (
 from .thescene import TheSceneIE
 from .thesixtyone import TheSixtyOneIE
 from .thestar import TheStarIE
+from .thesun import TheSunIE
 from .theweatherchannel import TheWeatherChannelIE
 from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
diff --git a/youtube_dl/extractor/thesun.py b/youtube_dl/extractor/thesun.py
new file mode 100644
index 000000000..7f96bf8c9
--- /dev/null
+++ b/youtube_dl/extractor/thesun.py
@@ -0,0 +1,27 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .ooyala import OoyalaIE
+
+
+class TheSunIE(InfoExtractor):
+    _VALID_URL = r'https://(?:www\.)?thesun\.co\.uk/\w+/(?P<id>\d+)/[\w-]'
+    _TEST = {
+        'url': 'https://www.thesun.co.uk/tvandshowbiz/2261604/orlando-bloom-and-katy-perry-post-adorable-instagram-video-together-celebrating-thanksgiving-after-split-rumours/',
+        'md5': '5667123b24f25f43f4c4f381ef34c5c2',
+        'info_dict': {
+            'id': 'h4OXN0NzE6rv6ObkEifKcNA-gYUw4xFf',
+            'ext': 'mp4',
+            'title': 'Katy Perry and Orlando Bloom shut down split rumours with cute Thanksgiving video',
+            'description': 'Still going strong',
+            'duration': 31.28,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        ooyala_id = self._search_regex(r'id\s*=\s*"thesun-ooyala-player-([^"]+)"', webpage, 'ooyala id')
+
+        return OoyalaIE._build_url_result(ooyala_id)