1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-05 06:37:54 +01:00
youtube-dl/youtube_dl/extractor/academicearth.py

42 lines
1.4 KiB
Python
Raw Normal View History

2014-01-07 10:04:48 +01:00
from __future__ import unicode_literals
2014-11-26 12:35:57 +01:00
import re
from .common import InfoExtractor
class AcademicEarthCourseIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
2014-01-07 10:04:48 +01:00
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.',
},
2015-09-06 05:52:27 +02:00
'playlist_count': 3,
}
def _real_extract(self, url):
2014-11-26 12:35:57 +01:00
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
title = self._html_search_regex(
2014-11-26 12:35:57 +01:00
r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, 'title')
description = self._html_search_regex(
r'<p class="excerpt"[^>]*?>(.*?)</p>',
2014-11-26 12:35:57 +01:00
webpage, '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,
}