Python爬虫简单的demo

# -*- coding: utf-8 -*_
__author__ = 'wyz'

import urllib2
import re
import smtplib
import time
from email.mime.text import MIMEText

def sendmailTome(urls, title):
mail_to_list = ["962193430@qq.com"]　#这里是接受的列表

mail_host = "smtp.qq.com"
mail_user = "962193430@qq.com" #这里是你的ｑｑ邮箱
mail_pass = "password" #　这里是密码，不是ｑｑ的密码，你需要开启ｓｍｔｐ服务，他会给你一个１６位的密码，就是那个密码

content = "您关注的死神更新了！！！！\n" + title + "\n地址：" + urls + "\n目录地址：http://ac.qq.com/Comic/comicInfo/id/501661"

msg = MIMEText(content)
msg['Subject'] = "死神更新啦"
msg["From"] = mail_user
msg["TO"] = ";".join(mail_to_list)

try:
s = smtplib.SMTP()
s.connect(mail_host)
s.login(mail_user, mail_pass)
s.sendmail(mail_user, mail_to_list, msg.as_string())
s.close()
return True
except Exception, e:
log.write(str(e) + '\n')
log.write(e)
log.write('\n')
return False

# 打开日志文件，记录时间
log = open('log.log', 'a+')
log.write("###############################################\n")
log.write(time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time())) + "\n")

# 打开配置文件，读取集数和url
config_read = open("config.txt")
news = int(config_read.readline())
url = config_read.readline()
config_read.close()

# 进行内容读取
request = urllib2.Request(url)
response = urllib2.urlopen(request)
mypage = response.read()

# 正则匹配
getitems = re.findall(r'<a.*?title="死神/境·界：第' + str(news) + '话.*?" href="(.*?)">(.*?)</a>', mypage, re.S)

# 判断是否匹配到相应的内容，把相应的内容写到日志文件里
if len(getitems) > 0:
log.write("find" + str(news) + ', and send email.\n')

# 匹配成功，发送邮件
if sendmailTome("http://ac.qq.com" + getitems[0][0], getitems[0][1]):
log.write("send success.\n")

# 更新配置文件，方便下次读取
news += 1
config_write = open('config.txt', 'w')
config_write.write(str(news) + '\n')
config_write.write(str(url) + '\n')
config_write.close()

else:
log.write("send fail!!!!!!!!!!!!!!!!!!!!!!\n")

else:
log.write("not found " + str(news) + ". next find it agein.\n")

log.write('\n')
log.close()