yt-dlp/yt_dlp/extractor/academicearth.py
bashonly c6387abc1a
[cleanup] Misc (#10807)
Closes #10751, Closes #10769, Closes #10791
Authored by: bashonly, Codenade, pzhlkj6612, seproDev, coletdjnz, grqz, Grub4K

Co-authored-by: Codenade <amadeus.dorian04@gmail.com>
Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>
Co-authored-by: sepro <4618135+seproDev@users.noreply.github.com>
Co-authored-by: coletdjnz <coletdjnz@protonmail.com>
Co-authored-by: N/Ame <173015200+grqz@users.noreply.github.com>
Co-authored-by: Simon Sawicki <contact@grub4k.xyz>
2024-09-27 22:46:22 +00:00

40 lines
1.3 KiB
Python

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': 3,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
title = self._html_search_regex(
r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, 'title')
description = self._html_search_regex(
r'<p class="excerpt"[^>]*?>(.*?)</p>',
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,
}