mbox2pdf/mbox2pdf.py

#!/bin/env python

import mailbox
import codecs
from bs4 import BeautifulSoup
from weasyprint import HTML
from datetime import datetime
import sys
import os
import logging
from slugify import slugify

logging.getLogger('fontTools').setLevel(logging.ERROR)
logging.getLogger('weasyprint').setLevel(logging.ERROR)
logging.basicConfig(format='%(levelname)s:%(message)s', level=logging.ERROR)

def extract_and_convert_email(message, output_file_base, i):
    logging.debug(f"Extraction du mail {i}")
    for part in message.walk():
        if part.get_content_maintype() == 'text' and part.get_content_subtype() == 'html':
            charset = part.get_content_charset('windows-1252')
            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
                date_header = message.get('Date')
                from_header = message.get('From')
                to_header = message.get('To')
                if date_header:
                    try:
                        date_object = datetime.strptime(date_header, "%a, %d %b %Y %H:%M:%S %z")
                        date_iso = date_object.isoformat().replace(":", "-")  # Remplace les ":" par "-" pour les noms de fichiers
                        date_simple = date_object.strftime("%d/%m/%Y, %H:%M:%S")
                        output_file = os.path.join(output_file_base, f"{date_iso}") # Chemin complet du fichier
                    except ValueError:
                        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 = "<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 /></div>"
                # Conversion en PDF
                try:
                    html_content = html_header + html_content
                    HTML(string=html_content).write_pdf(output_file + ".pdf")
                    logging.info(f"Email converti en PDF : {output_file}.pdf")
                except Exception as e:
                    logging.debug(f"Erreur lors de la conversion PDF : {e}")

            except Exception as e:
                logging.error(f"Erreur de décodage: {e}")
                logging.debug(f"Contenu brut (non décodé): {part.get_payload(decode=False)}")


def process_mbox(mbox_file):
    mbox = mailbox.mbox(mbox_file)
    logging.info(f"Traitement de {mbox_file}")

    # Création du répertoire de sortie
    output_dir_name = slugify(os.path.splitext(os.path.basename(mbox_file))[0])
    output_dir = os.path.join(os.getcwd(), output_dir_name)
    os.makedirs(output_dir, exist_ok=True)
    logging.debug(f"Extraction dans le dossier {output_dir}")

    for i, message in enumerate(mbox):
        extract_and_convert_email(message, output_dir, i)


if __name__ == "__main__":
    if len(sys.argv) > 1:
        mbox_file = sys.argv[1]
        process_mbox(mbox_file)
    else:
        print("Veuillez fournir le fichier mbox en argument.")