AntoineVe/mbox2pdf
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Nettoyage du HTML

Browse Source
This commit is contained in:
Antoine Van Elstraete
2025-02-13 17:01:17 +01:00
parent 584a5e82b1
commit 220b102830
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
mbox2pdf.py
View File

@@ -22,6 +22,11 @@ def extract_and_convert_email(message, output_file_base, i):
try: try:
payload = part.get_payload(decode=True).decode(charset, errors='replace') payload = part.get_payload(decode=True).decode(charset, errors='replace')
soup = BeautifulSoup(payload, 'html.parser') 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) html_content = str(soup)
# Extraction de la date et formatage ISO # Extraction de la date et formatage ISO