From 79bfaa2556fa699acd053be4f99cd795d2634c87 Mon Sep 17 00:00:00 2001 From: PinieP <59698589+PinieP@users.noreply.github.com> Date: Sat, 2 Nov 2024 22:30:06 +0100 Subject: [PATCH] Join URLs with urljoin again The base URL needs a trailing "/", so the part after the first "/" won't be ignored. --- PFERD/crawl/ilias/ilias_web_crawler.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/PFERD/crawl/ilias/ilias_web_crawler.py b/PFERD/crawl/ilias/ilias_web_crawler.py index e6887c3..66b6f54 100644 --- a/PFERD/crawl/ilias/ilias_web_crawler.py +++ b/PFERD/crawl/ilias/ilias_web_crawler.py @@ -209,7 +209,7 @@ instance's greatest bottleneck. async def _crawl_course(self, course_id: int) -> None: # Start crawling at the given course root_url = url_set_query_param( - self._base_url + "/goto.php", + urljoin(self._base_url + "/", "goto.php"), "target", f"crs_{course_id}", )