Function for reading email (*.eml only) files using python - https://informationcorners.com/read-send-emails-python/

read_email.py

# -*- coding: utf-8 -*-

import re
import email
import smtplib
import mimetypes
from email.mime.multipart import MIMEMultipart
from email import encoders
from email.mime.audio import MIMEAudio
from email.mime.base import MIMEBase
from email.mime.image import MIMEImage
from email.mime.text import MIMEText
import ntpath
import nltk
import datetime

def read_email(email_file):
    fp = open(email_file, encoding='utf8')
    try:
        email_dump = email.message_from_file(fp)
        email_details = {}
        fetch_items = ['From', 'To', 'Subject', 'Date']
        for key in fetch_items:
            if key in ['From']:
                from_ = email_dump[key]
                email_details['Sender_Email_Address'] = ', '.join(list(set(re.findall(r'<([^<]*)>', from_))))
                email_details['Sender_Name'] = ', '.join(re.findall(r'"([^"]*)"', from_))
            elif key in ['To']:
                to = email_dump[key]
                email_details['Received_By_Name'] = re.sub(r'<([^<]*)>', '', to).strip()
                email_details['Received_Email_Address'] = ', '.join(list(set(re.findall(r'<([^<]*)>', to))))
            elif key in ['Subject']:
                decode = email.header.decode_header(email_dump['Subject'])[0]
                subject = decode[0]
                if type(subject) is bytes:
                    email_details['Subject'] = subject.decode('unicode_escape')
                else:
                    email_details['Subject'] = subject
            elif key in ['Date']:
                date_stamp = re.sub(' (\+|\-).*', '', str(email_dump[key]))
                email_details['Date'] = date_stamp
                email_details['Date_Created'] = datetime.datetime.strptime(date_stamp.strip(), '%a, %d %b %Y %H:%M:%S')

        message = ''
        if email_dump.is_multipart():
            for part in email_dump.walk():
                ctype = part.get_content_type()
                cdispo = str(part.get('Content-Disposition'))
                # skip any text/plain (txt) attachments
                if ctype == 'text/plain' and 'attachment' not in cdispo:
                    message = part.get_payload(decode=True)  # decode
                    break
        # not multipart - i.e. plain text, no attachments, keeping fingers crossed
        else:
            message = email_dump.get_payload(decode=True)
        if type(message) is bytes:
            message = message.decode('unicode_escape')
            if '<html' in message:
                message = re.sub('<[^<]+?>', '', message)
                message = re.sub(' +', ' ', message)
            email_details['Message'] = message
        else:
            if '<html' in message:
                message = nltk.clean_html(message)
                message = re.sub('<[^<]+?>', '', message)
                message = re.sub(r'[^\x00-\x7F]+', ' ', message)
                message = re.sub(' +', ' ', message)
            email_details['Message'] = message
        # pprint.pprint(email_details)
        return email_details
    except Exception as error:
        print('Unable to read Email - ' + str(error))
        return {}