[Restudy] Add new extractor for restudy.dk

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 119ec2044efca360652008105e27772b4fc13033..3ae7a8a527fb024219191b5e933ef3c7e8d3413f 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -316,6 +316,7 @@ from .radiofrance import RadioFranceIE
 from .rai import RaiIE
 from .rbmaradio import RBMARadioIE
 from .redtube import RedTubeIE
+from .restudy import RestudyIE
 from .reverbnation import ReverbNationIE
 from .ringtv import RingTVIE
 from .ro220 import Ro220IE

diff --git a/youtube_dl/extractor/restudy.py b/youtube_dl/extractor/restudy.py
new file mode 100644 (file)
index 0000000..56a6c0f
--- /dev/null
+++ b/youtube_dl/extractor/restudy.py
@@ -0,0 +1,41 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class RestudyIE(InfoExtractor):
+    _VALID_URL = r'https://www.restudy.dk/video/play/id/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://www.restudy.dk/video/play/id/1637',
+        # MD5 sum of first 10241 bytes of the video file, as reported by
+        # head -c 10241 Leiden-frosteffekt-1637.mp4 | md5sum
+        'md5': '4e755c4287f292a1fe5363834a683818',
+        'info_dict': {
+            'id': '1637',
+            'ext': 'mp4',
+            'title': 'Leiden-frosteffekt',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        xml_url = (
+            'https://www.restudy.dk/awsmedia/SmilDirectory/video_%s.xml'
+            % video_id)
+        xml = self._download_webpage(xml_url, video_id)
+
+        base = self._search_regex(
+            r'<meta base="([^"]+)', xml, 'meta base')
+        # TODO: Provide multiple video qualities instead of forcing highest
+        filename = self._search_regex(
+            r'<video src="mp4:([^"]+_high\.mp4)', xml, 'filename')
+        url = '%s%s' % (base, filename)
+        title = self._og_search_title(webpage)
+        return {
+            'id': video_id,
+            'title': title,
+            'url': url,
+            'protocol': 'rtmp',
+        }