aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/academicearth.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/academicearth.py')
-rw-r--r--youtube_dl/extractor/academicearth.py36
1 files changed, 36 insertions, 0 deletions
diff --git a/youtube_dl/extractor/academicearth.py b/youtube_dl/extractor/academicearth.py
new file mode 100644
index 000000000..5045e7332
--- /dev/null
+++ b/youtube_dl/extractor/academicearth.py
@@ -0,0 +1,36 @@
+import datetime
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ remove_start,
+)
+
+
+class AcademicEarthCourseIE(InfoExtractor):
+ _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/courses/(?P<id>[^?#/]+)'
+ IE_NAME = u'AcademicEarth:Course'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ playlist_id = m.group('id')
+
+ webpage = self._download_webpage(url, playlist_id)
+ title = self._html_search_regex(
+ r'<h1 class="playlist-name">(.*?)</h1>', webpage, u'title')
+ description = self._html_search_regex(
+ r'<p class="excerpt">(.*?)</p>',
+ webpage, u'description', fatal=False)
+ urls = re.findall(
+ r'<h3 class="lecture-title"><a target="_blank" href="([^"]+)">',
+ webpage)
+ entries = [self.url_result(u) for u in urls]
+
+ return {
+ '_type': 'playlist',
+ 'id': playlist_id,
+ 'title': title,
+ 'description': description,
+ 'entries': entries,
+ }