1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
|
import datetime
import json
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'
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,
}
|
