From 1456a62b2596f66b80caf095393a9300e7518998 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Fran=C3=A7ois=20Poulain?= <fpoulain@metrodore.fr>
Date: Mon, 3 Aug 2020 18:18:12 +0200
Subject: [PATCH] feat(convert): sanitarisation html avec bs

---
 drupal2spip_lal/base/convert.py | 6 ++++--
 requirements/base.txt           | 4 ++++
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drupal2spip_lal/base/convert.py b/drupal2spip_lal/base/convert.py
index 9d90f98..c28a866 100644
--- a/drupal2spip_lal/base/convert.py
+++ b/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):
diff --git a/requirements/base.txt b/requirements/base.txt
index 0444250..4f842d5 100644
--- a/requirements/base.txt
+++ b/requirements/base.txt
@@ -6,3 +6,7 @@ django-environ ==0.4.5  # https://github.com/joke2k/django-environ
 # PHP
 # ------------------------------------------------------------------------------
 phpserialize
+
+# HTML
+# ------------------------------------------------------------------------------
+beautifulsoup4