From 6f2c248d1642d0835e94f078538aa463ad19d69b Mon Sep 17 00:00:00 2001
From: Dennis Scheiba <dennis.scheiba@gmx.de>
Date: Sun, 31 Jul 2016 03:39:48 +0200
Subject: [PATCH] Nobelprize Add new extractor

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/nobelprize.py | 45 ++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+)
 create mode 100644 youtube_dl/extractor/nobelprize.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 53fab1a31..dd71a3a96 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -546,6 +546,7 @@ from .ninecninemedia import NineCNineMediaIE
 from .ninegag import NineGagIE
 from .ninenow import NineNowIE
 from .nintendo import NintendoIE
+from .nobelprize import NobelprizeIE
 from .noco import NocoIE
 from .normalboots import NormalbootsIE
 from .nosvideo import NosVideoIE
diff --git a/youtube_dl/extractor/nobelprize.py b/youtube_dl/extractor/nobelprize.py
new file mode 100644
index 000000000..393be1dc7
--- /dev/null
+++ b/youtube_dl/extractor/nobelprize.py
@@ -0,0 +1,45 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+from ..utils import (
+    clean_html,
+    get_element_by_class,
+)
+
+
+class NobelprizeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nobelprize\.org/mediaplayer/.+?id=(?P<id>[0-9]{4})'
+    IE_DESC = 'Nobelprize'
+
+    _TEST = {
+        'url': 'https://www.nobelprize.org/mediaplayer/index.php?id=2028',
+        'md5': '19bb7134879a6e8f0731235f3c076321',
+        'info_dict': {
+            'id': '2028',
+            'ext': 'mp4',
+            'title': 'Acceptance Speech by Elie Wiesel (18 minutes)'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, id)
+
+        # we now do a regex search for a JS variable in our webpage
+        # which will deliver us a m3u8 file with all streams available
+
+        m3u8_playlist = self._search_regex(
+            r"(http://nobelvod-vh.akamaihd.net/i/flashcontent/.+master\.m3u8)",
+            webpage,
+            'm3u8 url',
+        )
+
+        formats = self._extract_m3u8_formats(m3u8_playlist, video_id, 'mp4')
+
+        return {
+            'id': video_id,
+            'title': clean_html(get_element_by_class('video-headline', webpage)),
+            'formats': formats,
+        }