python读取并解析邮件
很久以前写的还是 python2.7的
#-*- encoding: utf-8 -*-
#读取邮件导入到mysql数据库
import os
import imaplib
import email
import MySQLdb
import MySQLdb.cursors
import time
from datetime import datetime
#设置命令窗口输出使用中文编码
import sys
import re
import logging
import socket
import base64
import chardet
import ssl
socket.setdefaulttimeout(60)
log_file='/log/maillog.log'
logging.basicConfig(format = '%(asctime)s %(filename)s : %(levelname)s %(message)s',datefmt = '%Y-%m-%d %A %H:%M:%S',filename=log_file,level=logging.ERROR)
reload(sys)
sys.setdefaultencoding('gbk')
import ConfigParser
cp = ConfigParser.SafeConfigParser()
cp.read('my.conf')
att_path = cp.get('email_att', 'att_path')
def filter_html(s):
if s==None:
return ''
if(len(s)>10):
d = re.compile(r'' ,re.S|re.IGNORECASE)
s = d.sub(' ',s)
d = re.compile(r'' ,re.S|re.IGNORECASE)
s = d.sub(' ',s)
d = re.compile(r'' ,re.S|re.IGNORECASE)
s = d.sub(' ',s)
d = re.compile(r'',re.S|re.IGNORECASE)
s = d.sub(' ',s)
return s
#保存文件方法（都是保存在指定的根目录下）
def savefile(filename, data, path):
filepath = path + filename
f = open(filepath, 'wb')
f.write(data)
f.close()
#字符编码转换方法
def my_unicode(s, encoding):
ss = ''
#ss = unicode(s,'utf-8')
#print ss
#exit()
if encoding==None:encoding = chardet.detect(s)
try:
ss = unicode(s, encoding)
except:
try:
ss = unicode(s,'gbk')
except:
try:
ss = unicode(s,'utf-8')
except:
ss = ''
return ss
#获得字符编码方法
def get_charset(message, default="ascii"):
#Get themessage charset
charset=message.get_charset()
return charset
def my_get_payload(part,charset):
if charset==None:
try:
mailContent = part.get_payload(decode=True)
except:
mailContent = ''
else:
try:
mailContent =part.get_payload(decode=True).decode(charset,'ignore')
except:
mailContent = ''
return mailContent
#解析邮件方法（区分出正文与附件）
def parseEmail(msg, mychar,path):
mailContent= None
contenttype= None
ym = time.strftime('%Y%m%d',time.localtime(time.time()))
mypath = path+"/"+str(ym)+"/"
if os.path.exists(mypath)==False:
os.mkdir(mypath)
atts = ''
attarr = []
atterr = []
suffix=None
fnum = 0
for part in msg.walk():
if not part.is_multipart():
contenttype =part.get_content_type()
mptype = part.get_content_maintype()
filename = part.get_filename()
charset = get_charset(part)
#是否有附件
if filename or mptype=='image':
if filename:
h = email.Header.Header(filename)
dh = email.Header.decode_header(h)
fname = dh[0][0]
encodeStr = dh[0][1]
try:
if encodeStr != None:
if charset == None:
try:
fname = fname.decode(encodeStr, 'gbk')
except:
fname = fname.decode(encodeStr, 'ignore')
else:
fname = fname.decode(encodeStr, charset)
except:
fname = ''
elif mptype=='image':
content_id = part.get('Content-ID')
fname = content_id+".jpg"
#print fname
data = part.get_payload(decode=True)
#print('Attachment : ' + fname)
#保存附件
if fname != None and len(fname)>0:
fnameid = str(time.strftime('%H%M%S',time.localtime(time.time())))+str(fnum)
ext = ''
if "." in fname:
fnamearr = fname.split('.')
ext = fnamearr[len(fnamearr)-1]
#下载图片附件
ext = ext.lower()
if ext=='gif' or ext=='png' or ext=='jpg' or ext=='bmp' or ext=='jpeg' or ext=='webp':
fnewname = fnameid+"."+ext+".att"
try:
savefile(fnewname, data,mypath)
attarr.append(fnewname)
except:
atterr.append(fnewname)
fnum=fnum+1
else:
if contenttype in ['text/plain']:
suffix = '.txt'
if contenttype in ['text/html']:
suffix = '.htm'
mailchar = part.get_content_charset()
if contenttype in ['text/plain','text/html']:
if charset == None:
if mailchar!=None:
mailContent = my_get_payload(part,mailchar)
elif mychar!=None:
mailContent = my_get_payload(part,mychar)
else:
mailContent = my_get_payload(part,mychar)
else:
mailContent = my_get_payload(part,charset)
atts = ';'.join(attarr)
#exit()
if mailContent!=None:
mailContent = mailContent.encode('utf-8','ignore')
return (mailContent, suffix,atts)
def get_line_char(s):
#print s
arr = s.split('?')
if len(arr)>3 and arr[2].lower()=='b':return arr[1]
else:return None
#获取邮件方法
def getMail(cfgname, attpath):
mailhost = cp.get(cfgname, 'imaphost')
password = cp.get(cfgname, 'psswd')
account = cp.get(cfgname, 'account')
password = cp.get(cfgname, 'psswd')
port = int(cp.get(cfgname, 'port'))
ssl = int(cp.get(cfgname, 'ssl'))
classarr = cfgname.split('_')
mailclass = classarr[1]
#是否采用ssl
if ssl ==1:
#sslcontext = ssl.SSLContext(ssl.PROTOCOL_TLSv1_2)
#imapServer = imaplib.IMAP4_SSL(mailhost, port,ssl_context=sslcontext)
imapServer = imaplib.IMAP4_SSL(mailhost, port)
else:
imapServer = imaplib.IMAP4(mailhost, port)
imapServer.login(account, password)
#"Junk"
imapServer.select()
#邮件状态设置，新邮件为Unseen
#Messagestatues = 'All,Unseen,Seen,Recent,Answered, Flagged'
resp, items= imapServer.search(None, "Unseen")
midarr = items[0].split()
midarr.reverse()
if len(midarr)>10:midarr=midarr[0:10]
midarr.reverse()
number =1
#maillimit = 20
for i in midarr:
#get information of email
resp, mailData = imapServer.fetch(i,"(RFC822)")
#if resp != 'OK':contiue
if mailData[0] and mailData[0][1]:
mailText = mailData[0][1]
else:continue
msg = email.message_from_string(mailText)
subject = ''
sub = ''
subchar = None
if msg["Subject"]:
subject = email.Header.decode_header(msg["Subject"].replace('\r\n','\t'))
subchar = subject[0][1]
#print msg["Subject"]
if subchar==None:subchar=get_line_char(msg["Subject"])
#sub = my_unicode(subject[0][0],subchar).encode('gbk','ignore')
sub = my_unicode(subject[0][0],subchar).encode('utf-8','ignore')
strsub = 'Subject : ' + sub
#ls = msg["From"].split(' ')
strfrom = ''
#print sub
datestr = msg["Date"]
#print datestr
if datestr!=None:datestr = datestr.strip()
#strdate = 'Date : ' + datestr
ccstr = msg["CC"]
ccret = []
if ccstr!=None:
ccarr1 = ccstr.split('>')
for ci in ccarr1:
if '<' in ci:
ccarr2 = ci.split('<')
ccret.append(ccarr2[1])
cc = ''
if len(ccret)>0:cc=','.join(ccret)
received = msg["Received"]
if received:
rec_arr = received.split('>;')
if len(rec_arr)==2 and rec_arr[1]:
datestr = rec_arr[1].strip()
try:
maildate = time.strptime(datestr[5:24],'%d %b %Y %H:%M:%S')
mailtime = time.strftime("%Y-%m-%d %H:%M:%S",maildate)
except:
mailtime = time.strftime("%Y-%m-%d %H:%M:%S")
msgid = msg["X-QQ-mid"]
fromemail = ''
fromstr = msg["From"]
if fromstr!=None:
fromarr = fromstr.split('<')
fromstr2 = fromarr[len(fromarr)-1]
fromarr2 = fromstr2.split('>')
fromemail = fromarr2[0]
mailContent, suffix ,atts= parseEmail(msg, subchar,attpath)
#命令窗体输出邮件基本信息
#保存邮件正文
if atts==None:atts=''
if mailContent==None:mailContent=''
if suffix==None:suffix=''
if msgid==None:msgid=''
if ( suffix != '') and ( msgid != ''):
#html过滤
mailContent = filter_html(mailContent)
#savefile(str(number) + suffix, mailContent, mypath)
#保存数据
#save_to_db(cp,msgid,sub,mailContent,fromemail,atts,mailtime,mailclass,cc)
number = number + 1
#if number>maillimit:break
imapServer.close()
imapServer.logout()
#smtp发送邮件
import smtplib
from email.mime.text import MIMEText
from email.header import Header
def send_mail(cfgname,subject,msg,receiver,msgtype,cc):
mailhost = cp.get(cfgname, 'smtphost')
password = cp.get(cfgname, 'psswd')
sender = cp.get(cfgname, 'account')
receivers = [receiver] # 接收邮件，可设置为你的QQ邮箱或者其他邮箱
if msgtype=='HTML':
message = MIMEText(msg, 'html', 'gbk')
else:
message = MIMEText(msg, 'plain', 'gbk')
message['From'] = Header(u'邮件收发测试'.encode('gbk',"ignore"), 'gbk')
#message['To'] = Header("测试", 'gbk')
message['Subject'] = Header(subject, 'gbk')
ccarr = []
if len(cc)>1:
message['Cc'] = cc
ccarr = cc.split(',')
success = 0
try:
smtpObj = smtplib.SMTP()
smtpObj.connect(mailhost, 25) # 25 为 SMTP 端口号
smtpObj.login(sender,password)
smtpObj.sendmail(sender, receivers+ccarr, message.as_string())
#print "邮件发送成功"
success = 1
except:
#print "Error: 无法发送邮件"
success = 0
return success
if __name__ =="__main__":
getMail('email_info', att_path)