Amélioration de l'entête

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
@@ -38,11 +43,11 @@ def extract_and_convert_email(message, output_file_base, i):
                         logging.warning(f"Format de date invalide: {date_header}")
                         output_file = os.path.join(output_file_base, f"email_{i}") # Nom par défaut si date invalide
                         date_simple = "<i>date inconnue</i>"
-                html_header = "<p><ul>"
+                html_header = "<div style=\"border: thick double black;\"><ul>"
                 html_header += f"<li>De : {from_header}</li>"
                 html_header += f"<li>&#192; : {to_header}</li>"
                 html_header += f"<li>Date : {date_simple}</li>"
-                html_header += "</ul><br /></p>"
+                html_header += "</ul><br /></div>"
                 # Conversion en PDF
                 try:
                     html_content = html_header + html_content