mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-11-30 06:01:50 +00:00
22a6f15061
From now on, test_download will run these tests. That means we benefit not only from the networking setup in there, but also from the other tests (for example test_all_urls to find problems with _VALID_URLs).
41 lines
1.4 KiB
Python
41 lines
1.4 KiB
Python
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,
|
|
}
|