From 79a41a0637f2c7287d0a593ead6a1ba555a145d9 Mon Sep 17 00:00:00 2001 From: Fundor333 Date: Mon, 14 Jul 2025 12:46:34 +0200 Subject: [PATCH] Update internal link extraction to filter by class 'interlink-script' --- action_script/internal_link.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/action_script/internal_link.py b/action_script/internal_link.py index ca3f54fa..2eca0434 100644 --- a/action_script/internal_link.py +++ b/action_script/internal_link.py @@ -49,7 +49,9 @@ def get_internal_links_pointing_to_pages(sitemap_url): page_response.raise_for_status() page_soup = BeautifulSoup(page_response.content, "html.parser") - for link in page_soup.find_all("a", href=True): + for link in page_soup.find_all( + "a", {"class": "interlink-script"}, href=True + ): href = link.get("href") absolute_href = urljoin(page_url, href) parsed_absolute_href = urlparse(absolute_href)