如何提取多部分 email 的正文并使用 python IMAP 保存附件？

Question

我正在做一个项目，我会收到带有特定“主题”的电子邮件。 有用户转发给我的。 正文由文本组成，但在原始 email 中，并且在转发行上方没有输入新文本。 email 的任一部分也有附件。

我使用 python 和 IMAP 编写了以下代码，并且仅当 email 是新的而不是转发的 email 时才能存储附件和正文。

def getAllEmails(username, password, subject, fromEmail, folderName):
   
    mail = imaplib.IMAP4_SSL("imap.outlook.com")
    mail.login(username, password)
    print("Login success..........")
    
    mail.select("inbox")
      
    result, data = mail.search(None, 'SUBJECT', '"{}"'.format(subject))
    inbox_item_list_subject = data[0].split()
  
    result, data = mail.search(None, 'FROM', '"{}"'.format(fromEmail))
    inbox_item_list_sender = data[0].split() 
        
    inbox_item_list = list(set(inbox_item_list_subject) & set(inbox_item_list_sender))
    
    counter = 0
    for item in inbox_item_list:
        counter+=1
        
        result2, email_data = mail.fetch(item,'(RFC822)')
        raw_email = email_data[0][1].decode("utf-8")   
        email_message = email.message_from_string(raw_email)

        #getting information about the mail like to, from,subject, date.
        to_ = email_message['To']         
        from_ = email_message['From']
        subject_ = email_message['Subject']
        date_ = email_message['date']
        
        # setting the format to save in text file. 
        to_ = "to: "
        from_ = "from: " + from_ + str("\n")
        date_ = "date: " + date_ + str("\n")
        subject__ = "subject: " + subject_ + str("\n")

        # accessing the subparts of email_message
        for part in email_message.walk():
            if part.get_content_maintype == 'multipart':
                continue
            content_type = part.get_content_type()
            content_disposition = str(part.get("Content-Disposition"))
            
            filename = part.get_filename()

            ext = mimetypes.guess_extension(part.get_content_type())
            # allowing pdf, jpg, png and doc format only
            if ext == '.pdf' or ext == '.csv' or ext == '.png' or ext == '.docx' or ext == '.xlsx':
                if filename:
                    save_path = os.path.join(os.getcwd(), folderName, subject_)
                    
                    if not os.path.exists(save_path):
                        os.makedirs(save_path)
                    
                    with open(os.path.join(save_path, filename), 'wb') as fp:
                        fp.write(part.get_payload(decode=True))
                        fp.close()

        # getting the body part of the mail.
            try:
                body = part.get_payload(decode=True).decode()   
            except:
                pass
        
        
        # saving the required information in a file named as "textfile.txt".
            if content_type == "text/plain" and "attachment" not in content_disposition:
                save_path = os.path.join(os.getcwd(), folderName, subject_)

                if not os.path.exists(save_path):
                    os.makedirs(save_path)

                filename = "textfile.txt"
                with open(os.path.join(save_path, filename), 'w+', encoding='utf-8') as fp:
                    fp.writelines(to_)
                    fp.writelines(from_)
                    fp.writelines(date_)
                    fp.writelines(subject__)
                    fp.writelines(body)
                    fp.close()
    mail.close()
    mail.logout()

我希望存储正文和附件，即使它是前向 email??

Answer 1

似乎您已经拥有要提取附件的部分。 尝试使用此代码检索多部分 email 的主体。

您可能必须弄清楚如何将您的部分与此部分合并。

def getAll(username, password, folderName):

     mail = imaplib.IMAP4_SSL("imap.outlook.com")    
     mail.login(username, password)
     print("Login success..........")
    
     mail.select("INBOX")
    
     result, data = mail.search(None, '(FROM "user@gmail.com" SUBJECT "Subject-Name")')

     for num in data[0].split():
         h, d = mail.fetch(num, '(RFC822)')
         raw_email = d[0][1].decode("utf-8")

         message = email.message_from_string(raw_email)
         email_from = str(make_header(decode_header(message['From'])))
         subject = str(make_header(decode_header(message['Subject'])))

         print("SUBJECT: "+ subject)
         print("FROM: "+ email_from)
        
         msg_encoding = 'iso-2022-jp'

         if message.is_multipart() == False:
             single  = bytearray(message.get_payload(), msg_encoding)
             body = single.decode(encoding = msg_encoding)
        else:  
             multi = message.get_payload()[0]
             body = multi.get_payload(decode=True).decode(encoding = msg_encoding)
             body = re.sub('<[^<]+?>', '', body) # Remove special characters

         print("Printing the body:" + body)