w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[lecturio] Add support for lecturio.de (closes #18562)

Browse source
This commit is contained in:
Sergey M․ 2018-12-17 23:43:12 +07:00
parent 7216e9bff7
commit 386d1fea79
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 42 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
youtube_dl/extractor/extractors.py
View file

@ -557,6 +557,7 @@ from .lecture2go import Lecture2GoIE
from .lecturio import (
LecturioIE,
LecturioCourseIE,
LecturioDeCourseIE,
)
from .leeco import (
LeIE,

45
youtube_dl/extractor/lecturio.py
View file

@ -64,8 +64,14 @@ class LecturioBaseIE(InfoExtractor):
class LecturioIE(LecturioBaseIE):
_VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.lecture'
_TEST = {
_VALID_URL = r'''(?x)
https://
(?:
app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.lecture|
(?:www\.)?lecturio\.de/[^/]+/(?P<id_de>[^/?#&]+)\.vortrag
)
'''
_TESTS = [{
'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
'md5': 'f576a797a5b7a5e4e4bbdfc25a6a6870',
'info_dict': {
@ -74,7 +80,10 @@ class LecturioIE(LecturioBaseIE):
'title': 'Important Concepts and Terms – Introduction to Microbiology',
},
'skip': 'Requires lecturio account credentials',
}
}, {
'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
'only_matching': True,
}]
_CC_LANGS = {
'German': 'de',
@ -86,7 +95,8 @@ class LecturioIE(LecturioBaseIE):
}
def _real_extract(self, url):
display_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id') or mobj.group('id_de')
webpage = self._download_webpage(
'https://app.lecturio.com/en/lecture/%s/player.html' % display_id,
@ -190,3 +200,30 @@ class LecturioCourseIE(LecturioBaseIE):
'title', default=None)
return self.playlist_result(entries, display_id, title)
class LecturioDeCourseIE(LecturioBaseIE):
_VALID_URL = r'https://(?:www\.)?lecturio\.de/[^/]+/(?P<id>[^/?#&]+)\.kurs'
_TEST = {
'url': 'https://www.lecturio.de/jura/grundrechte.kurs',
'only_matching': True,
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
entries = []
for mobj in re.finditer(
r'(?s)<td[^>]+\bdata-lecture-id=["\'](?P<id>\d+).+?\bhref=(["\'])(?P<url>(?:(?!\2).)+\.vortrag)\b[^>]+>',
webpage):
lecture_url = urljoin(url, mobj.group('url'))
lecture_id = mobj.group('id')
entries.append(self.url_result(
lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
title = self._search_regex(
r'<h1[^>]*>([^<]+)', webpage, 'title', default=None)
return self.playlist_result(entries, display_id, title)