0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-24 02:35:12 +00:00
yt-dlp/youtube_dl/extractor/academicearth.py

33 lines
1 KiB
Python
Raw Normal View History

2014-01-07 09:04:48 +00:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class AcademicEarthCourseIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
2014-01-07 09:04:48 +00:00
IE_NAME = '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'<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,
}