使用Python的imap和email模块读取邮件

SMTP发送邮件的博文很多，但完整读取邮件的较少，本文主要是Python3读取邮件的编码，同时使用BeautifulSoup解析邮件内容。
Python版本信息，如下：
Python 3.8.2 (tags/v3.8.2:7b3ab59, Feb 25 2020, 23:03:10) [MSC v.1916 64 bit (AMD64)] on win32

代码

import email
import imaplib

from bs4 import BeautifulSoup


def main():
    try:
		# 填写需要读取邮件服务器的imap的host和port，不知道请联系管理员
        conn = imaplib.IMAP4_SSL(host='imap.xxx.com', port='993')
		# 读取邮件的用户名和密码
        conn.login('xxx@qq.com', 'your password')
        # 默认选择收件箱 INBOX
        conn.select()
		# Recent\Seen参数不起作用，暂先读取所有邮件
        status, data = conn.search(None, 'ALL')  
        if status != 'OK':
            raise Exception('读取邮件发生错误')
        emailids = data[0].split()
        # 倒序读取邮件
        mail_counts = len(emailids)
        for i in range(mail_counts-1, 0, -1):
			# 获取邮件信息
            status, edata = conn.fetch(emailids[i], '(RFC822)')
            # Message对象
            msg = email.message_from_bytes(edata[0][1])
            # 标题
            subject = email.header.decode_header(msg.get('subject'))
            # subject包含文档编码
            default_code = subject[0][1]
            print('subject', subject[0][0].decode(default_code))
            # print('Content_Type', msg.get_content_type())
			# 是否multipart类型，分别处理
            if msg.is_multipart():
                pl = msg.get_payload()
                for m in pl:
                    ctype = m.get_content_type()
                    if 'html' in ctype:
						# 注意decode参数，如果是True将解码base64/quoted-printable等格式编码内容，否则不解码
                        html = str(m.get_payload(decode=True), m.get('content-type').split('=')[1])
                    else:
                        txt = msg.get_payload(decode=True)
                        html = str(txt, default_code) if txt else ''
                    # BeautifulSoup解析网页
                    soup = BeautifulSoup(html, "lxml")
                    divs = soup.select('body')
                    for d in divs:
						# 提取所有文本内容
                        text = d.get_text(strip=True)  
                        print(text)
            else:
                html = str(msg.get_payload(decode=True), default_code)
                # BeautifulSoup解析网页
                soup = BeautifulSoup(html, "lxml")
				# 提取body标签里面的所有文本内容
                divs = soup.select('body')  
                for d in divs:
                    text = d.get_text(strip=True)
                    print(text)
    except Exception as ex:
        print(ex)

    finally:
        # close
        conn.close()
        conn.logout()


if __name__ == "__main__":
    main()