from imap_tools import MailBox

with MailBox("imap服務器名").login("賬號", "密碼") as mailbox:
    for msg in mailbox.fetch(limit=2,reverse=True):  # 我這里為了避免讀取全部的郵件,加上了limit=2的匹配參數(shù),讀取兩封郵件,按照最新接收的次序排序,進行測試; 
        for att in msg.attachments:  # msg為上一行取得的全部郵件
            if att.filename:    # 如果附件的文件名不為空
                att_data = att.payload # 獲得附件的內(nèi)容
                f = open(att.filename,'wb') # 用二進制打開,一般郵件附件都是二進制的.
                f.write(att_data)
                f.close()

import email
import imaplib
from bs4 import BeautifulSoup
def main():
    try:
		# 填寫需要讀取郵件服務器的imap的host和port，不知道請聯(lián)系管理員
        conn = imaplib.IMAP4_SSL(host='imap.xxx.com', port='993')
		# 讀取郵件的用戶名和密碼
        conn.login('xxx@qq.com', 'your password')
        # 默認選擇收件箱 INBOX
        conn.select()
		# Recent\Seen參數(shù)不起作用，暫先讀取所有郵件
        status, data = conn.search(None, 'ALL')  
        if status != 'OK':
            raise Exception('讀取郵件發(fā)生錯誤')
        emailids = data[0].split()
        # 倒序讀取郵件
        mail_counts = len(emailids)
        for i in range(mail_counts-1, 0, -1):
			# 獲取郵件信息
            status, edata = conn.fetch(emailids[i], '(RFC822)')
            # Message對象
            msg = email.message_from_bytes(edata[0][1])
            # 標題
            subject = email.header.decode_header(msg.get('subject'))
            # subject包含文檔編碼
            default_code = subject[0][1]
            # print('Content_Type', msg.get_content_type())
            ctype = msg.get_content_type()
			# 是否multipart類型，分別處理
            if msg.is_multipart():
                pl = msg.get_payload()
                for m in pl:
                    ctype = m.get_content_type()
                    if 'html' in ctype:
						# 注意decode參數(shù)，如果是True將解碼base64/quoted-printable等格式編碼內(nèi)容，否則不解碼
                        html = str(m.get_payload(decode=True), m.get('content-type').split('=')[1])
                    # BeautifulSoup解析網(wǎng)頁
                    soup = BeautifulSoup(html, "lxml")
                    divs = soup.select('body')
                    for d in divs:
						# 提取所有文本內(nèi)容
                        text = d.get_text(strip=True)  
                        print(text)
            else:
                html = str(msg.get_payload(decode=True), default_code)
                # BeautifulSoup解析網(wǎng)頁
                soup = BeautifulSoup(html, "lxml")
				# 提取body標簽里面的所有文本內(nèi)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()