]>
Commit | Line | Data |
---|---|---|
3798eadc | 1 | from __future__ import unicode_literals |
d90df974 PH |
2 | import re |
3 | ||
4 | from .common import InfoExtractor | |
d90df974 PH |
5 | |
6 | ||
7 | class AcademicEarthCourseIE(InfoExtractor): | |
9e57ce71 | 8 | _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)' |
3798eadc | 9 | IE_NAME = 'AcademicEarth:Course' |
d90df974 PH |
10 | |
11 | def _real_extract(self, url): | |
12 | m = re.match(self._VALID_URL, url) | |
13 | playlist_id = m.group('id') | |
14 | ||
15 | webpage = self._download_webpage(url, playlist_id) | |
16 | title = self._html_search_regex( | |
9e57ce71 | 17 | r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title') |
d90df974 | 18 | description = self._html_search_regex( |
9e57ce71 | 19 | r'<p class="excerpt"[^>]*?>(.*?)</p>', |
d90df974 PH |
20 | webpage, u'description', fatal=False) |
21 | urls = re.findall( | |
9e57ce71 | 22 | r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">', |
d90df974 PH |
23 | webpage) |
24 | entries = [self.url_result(u) for u in urls] | |
25 | ||
26 | return { | |
27 | '_type': 'playlist', | |
28 | 'id': playlist_id, | |
29 | 'title': title, | |
30 | 'description': description, | |
31 | 'entries': entries, | |
32 | } |