python实现扫描论坛回帖，自动发附件(应对求种之类的)

#!/usr/bin/python

import sys, urllib, re
from email.Header import Header
from email.MIMEText import MIMEText
from email.MIMEMultipart import MIMEMultipart
import smtplib, datetime


def sendMail(toWho,fromWho,bookName,text):
    msg = MIMEMultipart()
    
    ## fill your BT torrent or eBook ...
    att = MIMEText(open(bookName, ‘rb‘).read(), ‘base64‘, ‘gb2312‘)
    att["Content-Type"] = ‘application/octet-stream‘
    att["Content-Disposition"] = ‘attachment; filename="Redis_shejiyushixian.mobi"‘
    msg.attach(att)
    
    msg[‘from‘] = fromWho
    msg[‘subject‘] = Header(bookName + ‘(‘ + str(datetime.date.today()) + ‘)‘,‘gb2312‘)
    msg.attach(MIMEText(text))

    server = smtplib.SMTP(‘smtp.qq.com‘)
    ## fill your QQ number and password
    server.login(‘1234567‘,‘xxxxxxxxxxxx‘)
    error=server.sendmail(msg[‘from‘],toWho,msg.as_string())
    server.close
    print error

dicSave = {}
for line in open("log"):
    dicSave[line.rstrip()] = 1


dic = {}
preDic = {}

## grep Email format string
pattern = re.compile(r‘[_.0-9a-z-]+@(?:[0-9a-z][0-9a-z-]+.)+[a-z]{2,3}\b‘)

## please enhance this script to mark stop page as next start page
for x in range(1,100):

    ## fill forum url which need scan
    url="http://www.kindle114.com/thread-4567-%d-1.html" % x
    print "%s" % url
    
    wp = urllib.urlopen(url)
    content = wp.read()

    ## get mail list
    m = pattern.findall(content)
    
    stopFlag = 1
    for i in m:
        ## if page is duplicate means scan is wasting time and need stop
        if i not in preDic:
            stopFlag = 0

        ## only new mail address is needed to deliver
        if i not in dicSave:
            dic[i] = 1

    if stopFlag == 1:
        print "Scan Page Over %d\n" % x
        break

    preDic = m


mailList = []

## write deliver mail address to log to avoid duplicate deliver in next run
file_object = open("log", ‘a+‘)
for k,v in dic.items():
    print k
    mailList.append(k)
    file_object.write(k+"\n")

file_object.close()

if mailList:
    print "Delivering...\n";
    sendMail(mailList,‘77167680@qq.com‘,‘Redis_shejiyushixian.mobi‘,‘What are you interested in ?‘)
    print "Deliver is completed...\n";
else:
    print "Mail List is empty\n";