aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/academicearth.py
blob: c983ef0f519c303f880f471d357db4b60657ef17 (plain)
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
37
38
39
40
41
from __future__ import unicode_literals
import re

from .common import InfoExtractor


class AcademicEarthCourseIE(InfoExtractor):
    _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')

        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'<li class="lecture-preview">\s*?<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,
        }