From 097b8879c4c8fe6f3c698697e6a0c49e064975b1 Mon Sep 17 00:00:00 2001
From: OndraRehounek <ondra.rehounek@seznam.cz>
Date: Wed, 4 May 2022 11:51:51 +0200
Subject: [PATCH] jekyll-import: clear md from html

---
 shared/jekyll_import.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/shared/jekyll_import.py b/shared/jekyll_import.py
index dc93d2b3..875940de 100644
--- a/shared/jekyll_import.py
+++ b/shared/jekyll_import.py
@@ -14,6 +14,7 @@ from typing import List
 from urllib.error import HTTPError
 from uuid import uuid4
 
+import bleach
 import markdown.serializers
 import yaml
 from django.core.files.images import ImageFile
@@ -571,7 +572,8 @@ class JekyllArticleImporter:
         except (Page.DoesNotExist, Page.MultipleObjectsReturned):
             article = self.page_model()
 
-        md = r[2]
+        md = r[2]  # "raw" markdown z postu
+        md = bleach.clean(md)  # očistíme o případné nechtěné HTML tagy
         html = html_md.convert(md)
         article.perex = self.get_perex(md) or "..."
         self.handle_content(article, meta, html)
-- 
GitLab