]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/academicearth.py
debian/copyright: Fix missing-license-paragraph-in-dep5-copyright.
[youtubedl] / youtube_dl / extractor / academicearth.py
index ac05f824610a1385b3d2403c3a91ffa8ccc45e8a..47313fba8735902f964c0cd39992f9962e0f47fb 100644 (file)
@@ -1,24 +1,34 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 
 class AcademicEarthCourseIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/(?:courses|playlists)/(?P<id>[^?#/]+)'
-    IE_NAME = u'AcademicEarth:Course'
+    _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
+    IE_NAME = 'AcademicEarth:Course'
+    _TEST = {
+        'url': 'http://academicearth.org/playlists/laws-of-nature/',
+        'info_dict': {
+            'id': 'laws-of-nature',
+            'title': 'Laws of Nature',
+            'description': 'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.',
+        },
+        'playlist_count': 4,
+    }
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
-        playlist_id = m.group('id')
+        playlist_id = self._match_id(url)
 
         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, 'title')
         description = self._html_search_regex(
-            r'<p class="excerpt">(.*?)</p>',
-            webpage, u'description', fatal=False)
+            r'<p class="excerpt"[^>]*?>(.*?)</p>',
+            webpage, '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]