[academicearth] Fix extraction

The courses seems to be no longer available, changed the test to a playlist.
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-02-24 14:18:12 +01:00
parent cd7ee7aa44
commit 9e57ce716f
2 changed files with 10 additions and 9 deletions

View file

@ -5,7 +5,7 @@ from .common import InfoExtractor
class AcademicEarthCourseIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?academicearth\.org/(?:courses|playlists)/(?P<id>[^?#/]+)'
_VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
IE_NAME = 'AcademicEarth:Course'
def _real_extract(self, url):
@ -14,12 +14,13 @@ 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)
print(description)
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]