从邮箱中获取平安银行信用卡的账单信息并解析

import chardet,poplib,email.parser,email.policy,base64
from email.parser import  Parser
from email.header import  decode_header
from email.utils  import  parseaddr
from bs4 import BeautifulSoup

"""
Author: Thomas zhu
Date:2023-11-18
 Funcaiton：Parsing the inform from Emailbox by POP3 
"""
 
value = ['','','']
#Parsing the head content from message
def parsse_heard(msg):
    global  value
    i=0
    for header in ['From','To','Subject']:    #解析邮件头部
        value[i] = msg.get(header,'')
        if value[i]:
            if header == 'Subject':          #解析主题
                value[i] = decode_str(value[i])
            else:
               hdr,addr = parseaddr(value[i])
               name=decode_str(hdr)
               value[i]=u'%s<%s>'%(name,addr)
        i=i+1
    print("parsse hearder:" + value.__getitem__(0) + "  " + value.__getitem__(2))
#Decoding the string 
def decode_str(s):  
    value3,charset = decode_header(s)[0]
    if charset:
        value3 = value3.decode(charset)  
    return value3
def set_charset(msg):  # 设置字符集
    charset=msg.get_charset() #获取字符集
    if charset is None:
        content_type = msg.get('Content-type','').lower()
        pos=content_type.find('charset=')
        if pos>=0:
            charset = content_type[pos + 8:].strip()
    return charset
#解析邮件
def parsse_body_msg(msg):
    v3=['','','']
    i=0
    #解析邮件头部
    for header in ['From','To','Subject']:    #解析邮件头部
        v3[i] = msg.get(header,'')
        if v3[i]:
            if header == 'Subject':          #解析主题
                v3[i] = decode_str(v3[i])
              #  print('标题 %s:%s' % (header, v3[i]))
            else:
               hdr,addr = parseaddr(v3[i])
               name=decode_str(hdr)
               v3[i]=u'%s<%s>'%(name,addr)
        i+=1

    print("{} ".format(i)+"=====From: {}    ".format(v3.__getitem__(0))+"To: {}   ".format(v3.__getitem__(1))+ "Subject: {}    ".format(v3.__getitem__(2)))

    if (msg.is_multipart()):  #如果邮件有多个部分组成则返回ture
        parts = msg.get_payload()  #返回一个包含邮件所有子对象的列表
        for n, part in enumerate(parts): #枚举，遍历各子对象
            parsse_body_msg(part)
    else:
        content_type = msg.get_content_type() #获取邮件信息内容的编码类型
        if content_type == 'text/plain' or content_type == 'text/html':  #如果是纯文本或html类型
            print('22222part')
            contentStr = msg.get_payload(decode=True)  #返回一个包含邮件所有子对象（已经解码）的列表
            charset = set_charset(msg)  #设置字符集
            if charset:  # 字符集不为空
                contentStr = contentStr.decode(charset)  # 解码
        else:
            print('Attachement:%s' % (content_type))  # 附件

    #print('方法中封装的字符串  htmlstr.....' + contentStr+" The end for String in fundation")
    soup = BeautifulSoup(contentStr, 'html.parser')
    attrstr1 ="font-size: 13px;width: 540px; color: #222222;padding-left: 20px;word-break: break-all;"
    attrstr2="font-size: 13px\s+\d+px\s+padding-left: 20px;word-break: break-all;"
    attrstr3= "font-size: 13px;width: 130px; color: #222222;"
    attrstr4="font-size: 13px; width: 130px;color: #222222;padding-right: 20px"
    attrstr5="font-size: 13px;width: 90px;color: #222222;padding-left: 10px;"
    nm = 0
    subjectList,date1,date2,price=[],[],[],[]
    for link in soup.find_all('td',style=attrstr1):
        #print(link.get_text())
        subjectList.append(link.get_text())
    for link in soup.find_all('td', style=attrstr3):
        #print(link.get_text())
        date1.append(link.get_text())
    for link in soup.find_all('td', style=attrstr4):
        #print(link.get_text())
        date2.append(link.get_text())
    for link in soup.find_all('td', style=attrstr5):
        #print(link.get_text())
        price.append(link.get_text())
    for link in soup.find_all('td', style=attrstr1):
        print(date1[nm]+"  "+ date2[nm]+"    "+price[nm]+"    "+subjectList[nm])
        nm=nm+1

#Connect to 126 mail server
server =poplib.POP3_SSL('pop.126.com',995);
#server=poplib.POP3('pop.126.com',110)
server.user("liuhu@126.com");
server.pass_('SDOPOPSOIVKNMBCC');

emailNum,size =server.stat()
numEmail = len(server.list()[1]) # 另一种获取邮件列表的方法
print("Messages:%s. size:%s"%(emailNum,size))  #邮件数量和占用空间
print（"numEmail=",numEmail+="");
response,maillist,r=server.list() # Get mail list
#print("response",response)
#print("maillist",maillist)  #’the content of print is：[b'1 329199', b'2 54441', b'3 39162', b'4 38935', b'5 39137', b'6 38943', b'7 40960', ]

bankstr1='creditcard@service.pingan'
bankstr2='cebbank@cd'
bankstr3='95574@'
bankstr4='creditcard@message'
bankstr5="95555@me"
b6="master@"

for i in range(emailNum,emailNum-500, -1):
   try:
      response,message,octets = server.retr(i)   # 返回 状态信息，邮件  ，邮件大小  Message中存储了邮件原始文本中的每一行
      email_content = b'\r\n'.join(message).decode('utf-8')  # b 表示后面的字符串为Bytes类型
      msg = Parser().parsestr(email_content)    #msg =邮件内容
      mailbankstr= msg['from']

      if bankstr1 in mailbankstr:    # or bankstr2 in mailbankstr or bankstr3 in mailbankstr or bankstr4 in mailbankstr or bankstr5 in mailbankstr or b6 in mailbankstr:  #拣选所需要的邮件
         parsse_body_msg(msg)
   except Exception as e:
      pass
   finally:
      pass
server.quit()