报废选定内容的gmail并获取附件

如何解决报废选定内容的gmail并获取附件

我在报废Gmail时遇到问题。 候选人应从Gmail中提取或提取与金融交易有关的信息。这些信息可以是发票，订阅警报，账单等。我们希望您与Gmail帐户建立关联，并剪贴或提取发票，订阅，即将到来的账单数据。您可以在电子邮件中删除即将到来的发票或订阅或发票等字词，然后拉出 金额，日期，附件（如果有的话）。

我必须收集信息并存储所有附件。有什么具体的简单方法吗？

我的代码

import imaplib
import os
import email,getpass
import sys
import json

class GmailFinin():
    def helloWorld(self):
        print("\nHello I'm here to help you")

    def initializeVariables(self):
        self.usr = ""
        self.pwd = ""
        self.mail = object
        self.mailbox = ""
        self.mailCount = 0
        self.destFolder = ""
        self.data = []
        self.ids = []
        self.idsList = []

    def getLogin(self):
        print("\nPlease enter your Gmail login details below.")
        self.usr = input("Email: ")
        # self.pwd = input("Password: ")
        self.pwd = getpass.getpass("Enter your password --> ")

    def attemptLogin(self):
        self.mail = imaplib.IMAP4_SSL("imap.gmail.com",993)
        if self.mail.login(self.usr,self.pwd):
            print("\nLogon SUCCESSFUL")
            self.destFolder = input("\nPlease choose a destination folder in the form of /Users/username/dest/ (do not forget trailing slash!): ")
            if not self.destFolder.endswith("/"): self.destFolder+="/"
            return True
        else:
            print("\nLogon FAILED")
            return False

    def checkIfUsersWantsToContinue(self):
        print("\nWe have found "+str(self.mailCount)+" emails in the mailbox "+self.mailbox+".")
        return True if input("Do you wish to continue extracting all the emails into "+self.destFolder+"? (y/N) ").lower().strip()[:1] == "y" else False       
        
    def selectMailbox(self):
        # self.mailbox = input("\nPlease type the name of the mailbox you want to extract,e.g. Inbox: ")
        self.mailbox = "Inbox"
        bin_count = self.mail.select(self.mailbox)[1]
        self.mailCount = int(bin_count[0].decode("utf-8"))
        return True if self.mailCount > 0 else False

    def searchThroughMailbox(self):
        type,self.data = self.mail.search(None,"ALL")
        self.ids = self.data[0]
        self.idsList = self.ids.split()

    def parseEmails(self):
        jsonOutput = {}
        for anEmail in self.data[0].split():
            type,self.data = self.mail.fetch(anEmail,'(UID RFC822)')
            raw = self.data[0][1]
            try:
                raw_str = raw.decode("utf-8")
            except UnicodeDecodeError:
                try:
                    raw_str = raw.decode("ISO-8859-1") # ANSI support
                except UnicodeDecodeError:
                    try:
                        raw_str = raw.decode("ascii") # ASCII ?
                    except UnicodeDecodeError:
                        pass
                        
            msg = email.message_from_string(raw_str)

            jsonOutput['subject'] = msg['subject']
            jsonOutput['from'] = msg['from']
            jsonOutput['date'] = msg['date']
            
            raw = self.data[0][0]
            raw_str = raw.decode("utf-8")


            uid = raw_str.split()[2]
            # Body #
            if msg.is_multipart():
                for part in msg.walk():
                    partType = part.get_content_type()
                    ## Get Body ##
                    if partType == "text/plain" and "attachment" not in part:
                        jsonOutput['body'] = part.get_payload()
                    ## Get Attachments ##
                    if part.get('Content-Disposition') is not None:
                        attchName = part.get_filename()
                        print(attchName)
                        if bool(attchName):
                            attchFilePath = str(self.destFolder)+str(uid)+str("/")+str(attchName)
                            print(attchFilePath)
                            os.makedirs(os.path.dirname(attchFilePath),exist_ok=True)
                            with open(attchFilePath,"wb") as f:
                                f.write(part.get_payload(decode=True))
            else:
                # jsonOutput['body'] = msg.get_payload(decode=True).decode("utf-8") # Non-multipart email,perhaps no attachments or just text.
                jsonOutput['body'] = msg.get_payload()


            outputDump = json.dumps(jsonOutput)
            emailInfoFilePath = str(self.destFolder)+str(uid)+str("/")+str(uid)+str(".json")
            os.makedirs(os.path.dirname(emailInfoFilePath),exist_ok=True)
            print(emailInfoFilePath)
            with open(emailInfoFilePath,"w") as f:
                f.write(outputDump)

    def __init__(self):
        self.initializeVariables()
        self.helloWorld()
        self.getLogin()
        if self.attemptLogin():
            not self.selectMailbox() and sys.exit()
        else:
            sys.exit()
        not self.checkIfUsersWantsToContinue() and sys.exit()
        self.searchThroughMailbox()
        self.parseEmails()

if __name__ == "__main__":
    run = GmailFinin()

我尝试使用下面的内容进行搜索，但我认为它不是最佳选择，因为它仅在主题以及如何为关键字列表添加多个或条件的条件下进行搜索。

                type,'(OR TEXT "bill" SUBJECT "bill")')