2014-01-07 09:04:48 +00:00
|
|
|
from __future__ import unicode_literals
|
2013-12-16 21:18:27 +00:00
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class AcademicEarthCourseIE(InfoExtractor):
|
2013-12-17 01:41:34 +00:00
|
|
|
_VALID_URL = r'^https?://(?:www\.)?academicearth\.org/(?:courses|playlists)/(?P<id>[^?#/]+)'
|
2014-01-07 09:04:48 +00:00
|
|
|
IE_NAME = 'AcademicEarth:Course'
|
2013-12-16 21:18:27 +00:00
|
|
|
|
|
|
|
|
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,
|
|
|
|
|
}
|
