feat(convert): sanitarisation html avec bs

drupal2spip_lal/base/convert.py

@@ -2,6 +2,8 @@ from datetime import datetime
 
 from django.utils.timezone import make_aware, now
 
+from bs4 import BeautifulSoup as bs
+
 from drupal2spip_lal.drupal import models as drupal
 from drupal2spip_lal.spip import models as spip
 
@@ -16,8 +18,8 @@ def convert_timestamp(timestamp):
 
 
 def sanitarize_html(html):
-    # FIXME: bs4
-    return html
+    soup = bs(html, 'html.parser')
+    return soup.prettify(formatter="html5")
 
 
 def convert_node(node, update=False):

requirements/base.txt

@@ -6,3 +6,7 @@ django-environ ==0.4.5  # https://github.com/joke2k/django-environ
 # PHP
 # ------------------------------------------------------------------------------
 phpserialize
+
+# HTML
+# ------------------------------------------------------------------------------
+beautifulsoup4