From 27fe903c511691c078942bef5ee9a05a43b15c8f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jes=C3=BAs?= Date: Wed, 9 Jun 2021 17:54:27 -0500 Subject: initial --- hypervideo_dl/extractor/academicearth.py | 41 ++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 hypervideo_dl/extractor/academicearth.py (limited to 'hypervideo_dl/extractor/academicearth.py') diff --git a/hypervideo_dl/extractor/academicearth.py b/hypervideo_dl/extractor/academicearth.py new file mode 100644 index 0000000..3409550 --- /dev/null +++ b/hypervideo_dl/extractor/academicearth.py @@ -0,0 +1,41 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class AcademicEarthCourseIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P[^?#/]+)' + 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'

]*?>(.*?)

', webpage, 'title') + description = self._html_search_regex( + r'

]*?>(.*?)

', + webpage, 'description', fatal=False) + urls = re.findall( + r'
  • \s*?', + webpage) + entries = [self.url_result(u) for u in urls] + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': title, + 'description': description, + 'entries': entries, + } -- cgit v1.2.3