python 360 社区 监控 爬虫 in not in 问题

发生个特别奇怪的情况,最近老是收到重复邮件,检查爬虫里面有个地方竟然走了两个分支,
如果用in,元素存在的情况下,竟然会走到else里面,用notin,就不会,实在是太奇怪了,写简单的demo的时候不会出现这个情况,不知道是python的问题还是我的问题

#*-coding:utf-8-*-
import urllib2
import re
import smtplib
import time
from email.mime.text import MIMEText

retries1=30
_to = "XXXXXXXXXXXXX@360.cn"

class SendQqMail:
    def getqqmail(self, retries):

        _user = "XXXXXXXXXXXXXX@qq.com"
        _pwd = "XXXXXXXXXXXXXXXXXXX"

        msg = MIMEText(listitem1[74:-4])
        msg["Subject"] = listitem1[0:42]
        msg["From"] = _user
        msg["To"] = _to

        try:
            time.sleep(30)
            s = smtplib.SMTP_SSL("smtp.qq.com", 465)
            s.login(_user, _pwd)
            s.sendmail(_user, _to, msg.as_string())
            s.quit()
            print "Send QQ Email Success!"
        except smtplib.SMTPException, e:
            print "retry.QQ mail.........,%s" % e
            if retries > 0:
                return self.getqqmail(retries - 1)
            else:
                print "Send QQ Email Falied,%s" % e

class Send163Mail:
    def get163mail(self, retries):

        _user = "python_smtp_test@163.com"
        _pwd = "zk199245qqq"

        msg = MIMEText(listitem1[74:-4])
        msg["Subject"] = listitem1[0:42]
        msg["From"] = _user
        msg["To"] = _to

        try:
            time.sleep(30)
            s = smtplib.SMTP_SSL("smtp.163.com", 465)
            s.login(_user, _pwd)
            s.sendmail(_user, _to, msg.as_string())
            s.quit()
            print "Send 163 Email Success!"
        except smtplib.SMTPException, e:
            print "retry.163mail..........,%s" % e
            if retries > 0:
                return self.get163mail(retries - 1)
            else:
                print "Send 163 Email Falied,%s" % e




#卫士板块
req1 = urllib2.Request("http://bbs.360.cn/forum-140-1.html")

class openurlrequest:
    def tryopenurlrequest(self, req, retries):
        try:
            time.sleep(30)
            response = urllib2.urlopen(req)
            bufferread = response.read()
        except Exception, what:
            #print what, req
            if retries > 0:
                return self.tryopenurlrequest(req, retries - 1)
            else:
                print 'open url request Failed', req
    return bufferread


buff = openurlrequest()
buffer = buff.tryopenurlrequest(req1, retries1)
getarticlelist = re.compile(r'http://bbs.360.cn/thread-.+-1-1.html" \s?target="_blank" class="s xst".*\s*</a>')
pagemsg = re.findall(getarticlelist,buffer)

print ("卫士板块监控系统已启动,如果监控到新的信息将会自动发送到您的邮箱").decode("utf-8")
print 'ready variables of num: %s' %len(pagemsg)

allurllist = []
for eveurllist in pagemsg:
    allurllist.append(eveurllist[0:42])
print len(allurllist)

while True:
    time.sleep(30)
    buff1 = openurlrequest()
    buffer1 = buff.tryopenurlrequest(req1, retries1)
    getarticlelist1 = re.compile(r'http://bbs.360.cn/thread-.+-1-1.html" \s?target="_blank" class="s xst".*\s*</a>')
    pagemsg1 = re.findall(getarticlelist1,buffer1)
    for listitem1 in pagemsg1:
    #奇怪的地方就在这里,用in的时候取到的最后一条listitem1[0:42]在allurllist里面,应该不会走到else里面,但是测试的时候,会把两种情况都打印出来,而用not in就不会,这他妈的是因为啥啊
        if (listitem1[0:42] not in allurllist):
            allurllist.append(listitem1[0:42])
            try:
                qqsendmailer = SendQqMail()
                time.sleep(30)
                qqsendmailer.getqqmail(30)
            except:
                print "QQ mail try five times fail,change 163mail"
                neteasysendmailer = Send163Mail()
                time.sleep(30)
                neteasysendmailer.get163mail(30)
        else:
            pass
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值