Merge remote-tracking branch 'hojel/slutload'

[youtube-dl] / youtube_dl / extractor / academicearth.py

diff --git a/youtube_dl/extractor/academicearth.py b/youtube_dl/extractor/academicearth.py
index 5045e7332a8833984af5d4a74e626b93f520cff6..59d3bbba413c3c256a3f77917708fb171e337b14 100644 (file)
--- a/youtube_dl/extractor/academicearth.py
+++ b/youtube_dl/extractor/academicearth.py
@@ -1,16 +1,12 @@
-import datetime
-import json
+from __future__ import unicode_literals
 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'
+    _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
+    IE_NAME = 'AcademicEarth:Course'
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
@@ -18,12 +14,12 @@ class AcademicEarthCourseIE(InfoExtractor):
 
         webpage = self._download_webpage(url, playlist_id)
         title = self._html_search_regex(
-            r'<h1 class="playlist-name">(.*?)</h1>', webpage, u'title')
+            r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title')
         description = self._html_search_regex(
-            r'<p class="excerpt">(.*?)</p>',
+            r'<p class="excerpt"[^>]*?>(.*?)</p>',
             webpage, u'description', fatal=False)
         urls = re.findall(
-            r'<h3 class="lecture-title"><a target="_blank" href="([^"]+)">',
+            r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">',
             webpage)
         entries = [self.url_result(u) for u in urls]