Das deutsche Python-Forum

Code: Alles auswählen

import os
import re
import email
import unicodedata
import shutil
from tkinter import filedialog
import tkinter as tk
from datetime import datetime
from urllib.parse import quote

# Funktion zum Extrahieren des Datums, der Uhrzeit, des Mail-Tags und des Betreffs aus der E-Mail
def extract_email_info(eml_file):
    with open(eml_file, 'r', encoding='cp1252') as file:
        msg = email.message_from_file(file)
        date_str = msg['Date']
        subject = msg['Subject']
        from_field = msg['From']
        
    # with open(eml_file, 'r', encoding='utf-8') as file:    

    # Das Datum und die Uhrzeit aus dem E-Mail-Header extrahieren
    email_date = datetime.strptime(date_str, "%a, %d %b %Y %H:%M:%S %z")
    date_formatted = email_date.strftime("%Y-%m-%d %H%M%S")

    # Den Mail-Tag aus dem 'From:'-Feld extrahieren
    mail_tag = from_field.split('<')[0].strip()
    
    # Diakritische Zeichen normalisieren
    mail_tag = unicodedata.normalize('NFKD', mail_tag).encode('ascii', 'ignore').decode('utf-8')

    # Das Prefix wie 'Re: ' oder 'Aw: ' aus dem Betreff entfernen
    subject = re.sub(r'^re:', "", subject, count = 1, flags = re.I).strip()
    subject = re.sub(r'^aw:', "", subject, count = 1, flags = re.I).strip()
    
   
    # Diakritische Zeichen im Betreff normalisieren
    subject = unicodedata.normalize('NFKD', subject).encode('ascii', 'ignore').decode('utf-8')
    
    # Die Anführungszeichen um den Mail-Tag und entfernen
    
    mail_tag = mail_tag.strip('\"').split('@')[0].replace(".", " ")
    
    # Wenn ein @-Zeichen im Mail-Tag ist, nur den Teil vor dem @-Zeichen verwenden
    # if '@' in mail_tag:
    #    mail_tag = mail_tag.split('@')[0]

    return date_formatted, mail_tag, subject

# Funktion zum Konvertieren der Dateinamen
def rename_eml_files(eml_files):
    for eml_file in eml_files:
        date_formatted, mail_tag, subject = extract_email_info(eml_file)
        _, extension = os.path.splitext(eml_file)
        
       
        subject = subject.replace(':', '').lstrip()  # Doppelpunkte entfernen

        # Das aktuelle Verzeichnis (Verzeichnis der Ausgangsdatei) ermitteln
        current_directory = os.path.dirname(eml_file)
        
        # Den neuen Dateipfad erstellen (mit os.path.join() für Windows-Kompatibilität)
        new_filename = os.path.join(current_directory, f"{date_formatted} [{mail_tag}] {quote(subject.strip())}{extension}")        

        new_filename = new_filename.replace('"', '')  # Anführungszeichen entfernen
        new_filename = new_filename.replace(' .eml', '.eml')  # Leerzeichen vor .eml entfernen
        # new_filename = new_filename.replace('  ', ' ')  # Doppelte Leerzeichen auf ein Leerzeichen reduzieren
        # new_filename = new_filename.replace(':', '')  # Doppelpunkte entfernen

        try:
            os.rename(eml_file, new_filename)
            print(f"Umbenannt: {eml_file} -> {new_filename}")
        except Exception as e:
            print(f"Fehler beim Umbenennen von {eml_file}: {str(e)}")

# GUI zum Auswählen der Dateien
def select_files():
    root = tk.Tk()
    root.withdraw()  # Das Hauptfenster ausblenden

    # Dateiauswahldialog anzeigen und Pfad in Windows-Format konvertieren
    file_paths = filedialog.askopenfilenames(
        title="E-Mails auswählen",
        filetypes=[("EML-Dateien", "*.eml")]
    )

    if file_paths:
        # Konvertiere Pfad zu Windows-Stil
        file_paths = [os.path.normpath(path) for path in file_paths]
        rename_eml_files(file_paths)
    else:
        print("Keine Dateien ausgewählt.")

if __name__ == "__main__":
    select_files()

Code: Alles auswählen

In [578]: "<foo@bar>".split('<')[0].strip()
Out[578]: ''

Code: Alles auswählen

#!/usr/bin/env python3
import email
import re
import tkinter as tk
import unicodedata
from datetime import datetime
from pathlib import Path
from tkinter import filedialog
from urllib.parse import quote


def filter_non_ascii(text):
    return "".join(
        character
        for character in unicodedata.normalize("NFKD", text)
        if character.isascii()
    )


def extract_email_info(file_path):
    """
    Zeitstempel, Empfänger, und Betreff aus der E-Mail auslesen.
    """
    with file_path.open("rb") as file:
        message = email.message_from_binary_file(file)

    return (
        datetime.strptime(message["Date"], "%a, %d %b %Y %H:%M:%S %z"),
        filter_non_ascii(
            message["From"]
            .split("<")[0]
            .strip('"')
            .split("@")[0]
            .replace(".", " ")
        ),
        re.sub(
            r"((re|aw):\s*)*",
            "",
            filter_non_ascii(message["Subject"]),
            flags=re.IGNORECASE,
        ).strip(),
    )


def rename_eml_files(file_paths):
    for file_path in file_paths:
        timestamp, sender, subject = extract_email_info(file_path)
        new_file_path = file_path.with_name(
            f"{timestamp:%Y-%m-%d %H%M%S}"
            f" [{quote(sender)}]"
            f" {quote(subject)}.{file_path.suffix}"
        )
        try:
            file_path.rename(new_file_path)
            print(f"Umbenannt: {file_path} -> {new_file_path}")
        except Exception as error:
            print(f"Fehler beim Umbenennen von {file_path}: {error}")


def main():
    root = tk.Tk()
    root.withdraw()

    file_paths = filedialog.askopenfilenames(
        title="E-Mails auswählen", filetypes=[("EML-Dateien", "*.eml")]
    )
    if file_paths:
        rename_eml_files(map(Path, file_paths))
    else:
        print("Keine Dateien ausgewählt.")


if __name__ == "__main__":
    main()

Code: Alles auswählen

#!/usr/bin/env python3
import email
import re
import tkinter as tk
import unicodedata
from email.header import decode_header
from email.utils import parseaddr, parsedate_to_datetime
from pathlib import Path
from tkinter import filedialog
from urllib.parse import quote


def filter_non_ascii(text):
    return "".join(
        character
        for character in unicodedata.normalize("NFKD", text)
        if character.isascii()
    )


def get_decoded_header(message, header_name):
    return "".join(
        part.decode(encoding or "ascii")
        for part, encoding in decode_header(message[header_name])
    )


def get_sender_name(message):
    name, address = parseaddr(get_decoded_header(message, "From"))
    return (
        name if name else address.split("@", maxsplit=1)[0].replace(".", " ")
    )


def get_subject(message):
    return re.sub(
        r"((re|aw):\s*)*",
        "",
        filter_non_ascii(get_decoded_header(message, "Subject")),
        flags=re.IGNORECASE,
    ).strip()


def extract_email_info(file_path):
    """
    Zeitstempel, Empfänger, und Betreff aus der E-Mail auslesen.
    """
    with file_path.open("rb") as file:
        message = email.message_from_binary_file(file)

    return (
        parsedate_to_datetime(message["Date"]).astimezone(),
        get_sender_name(message),
        get_subject(message),
    )


def rename_eml_files(file_paths):
    for file_path in file_paths:
        timestamp, sender, subject = extract_email_info(file_path)
        new_file_path = file_path.with_name(
            f"{timestamp:%Y-%m-%d %H%M%S}"
            f" [{quote(sender)}]"
            f" {quote(subject)}.{file_path.suffix}"
        )
        try:
            file_path.rename(new_file_path)
            print(f"Umbenannt: {file_path} -> {new_file_path}")
        except Exception as error:
            print(f"Fehler beim Umbenennen von {file_path}: {error}")


def main():
    root = tk.Tk()
    root.withdraw()

    file_paths = filedialog.askopenfilenames(
        title="E-Mails auswählen", filetypes=[("EML-Dateien", "*.eml")]
    )
    if file_paths:
        rename_eml_files(map(Path, file_paths))
    else:
        print("Keine Dateien ausgewählt.")


if __name__ == "__main__":
    main()