Nettoyage du HTML

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