From 220b1028309e8e42a9b4fa0ffa9213a7904cdb9a Mon Sep 17 00:00:00 2001
From: Antoine Van Elstraete <antoine@van-elstraete.net>
Date: Thu, 13 Feb 2025 17:01:17 +0100
Subject: [PATCH] Nettoyage du HTML

---
 mbox2pdf.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/mbox2pdf.py b/mbox2pdf.py
index e8d7384..cc1a964 100755
--- a/mbox2pdf.py
+++ b/mbox2pdf.py
@@ -22,6 +22,11 @@ def extract_and_convert_email(message, output_file_base, i):
             try:
                 payload = part.get_payload(decode=True).decode(charset, errors='replace')
                 soup = BeautifulSoup(payload, 'html.parser')
+                # Nettoyage de l'HTML
+                attr_whitelist = ("style")
+                for tag in soup.findAll(True):
+                    for attr in [attr for attr in tag.attrs if attr not in attr_whitelist]:
+                        del tag[attr]
                 html_content = str(soup)
 
                 # Extraction de la date et formatage ISO