From 31ca3c4c6f4773629be2d91267987be606fce8a4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?D=C3=A9stin=20Reed?= <trox1972@users.noreply.github.com>
Date: Sun, 26 Jun 2016 17:31:10 +0200
Subject: [PATCH] [OReilly] Add new extractor

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/oreilly.py    | 38 ++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)
 create mode 100644 youtube_dl/extractor/oreilly.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 9f98a14908d..cdbb1be900d 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -575,6 +575,7 @@
 )
 from .openload import OpenloadIE
 from .ora import OraTVIE
+from .oreilly import OReillyIE
 from .orf import (
     ORFTVthekIE,
     ORFOE1IE,
diff --git a/youtube_dl/extractor/oreilly.py b/youtube_dl/extractor/oreilly.py
new file mode 100644
index 00000000000..a8da14f1771
--- /dev/null
+++ b/youtube_dl/extractor/oreilly.py
@@ -0,0 +1,38 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+
+
+class OReillyIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?player\.oreilly\.com/(?:videos|embed)/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://player.oreilly.com/videos/9781491944639',
+        'md5': '6382439f4bc1195bf395c91bd62b5671',
+        'info_dict': {
+            'id': '0_tz5u5q67',
+            'title': '01_modern_data_strategy_mike_olson_cloudera_manuel_martin_marquez_cern',
+            'ext': 'mp4',
+            'upload_date': '20160602',
+            'timestamp': 1464888738,
+        }
+    }, {
+        'url': 'https://player.oreilly.com/embed/9781491944639',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        url = 'https://player.oreilly.com/embed/%s' % video_id
+
+        webpage = self._download_webpage(url, video_id)
+
+        partner_id = self._search_regex(r'var partnerId = \'([^\']+)\';',
+            webpage, 'partner ID')
+        kaltura_id = self._search_regex(r'var externalId = \'([^\']+)\';',
+            webpage, 'Kaltura ID')
+        title = self._search_regex(r'var title = \'([^\']+)\';',
+            webpage, 'title')
+
+        return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id),
+            'Kaltura', video_title=title)