玩渗透玩爬虫怎么能没有代理池

抓取西刺免费代理ip（未完成版，没加代理，没加验证）

import urllib2
import urllib
import re
num=50
for m in range(1,num):
    url='http://www.xicidaili.com/nn/'+str(m)
    user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:54.0) Gecko/20100101 Firefox/54.0'
    headers={'User-agent':user_agent}
    httpHandler = urllib2.HTTPHandler(debuglevel=1)
    httpsHandler = urllib2.HTTPSHandler(debuglevel=1)
    opener = urllib2.build_opener(httpHandler, httpsHandler)
    urllib2.install_opener(opener)
    req=urllib2.Request(url,headers=headers)
    try:
        r=urllib2.urlopen(req,timeout=30000)
        #print r.read()
    except urllib2.URLError,e:
        print url
        print e.code
        continue
    tmp=r.read()
    zzip='<td>[0-9]*.[0-9]*.[0-9]*.[0-9]*</td>\s*<td>[0-9]*</td>'
    zzport='<td>[0-9]*</td>'
    ip=re.findall(zzip,tmp)
    port=re.findall(zzport,tmp)
    lip=[]
    lport=[]
    for i in ip:
        lip.append(i.replace('<td>','').replace('</td>\s*<td>[0-9]*</td>',''))
    for j in port:
        lport.append(j.replace('<td>','').replace('</td>',''))
    d={}
    n=0
    for i in ip:
        d[n]=dict(ip=lip[n],port=lport[n])
        n=n+1
    print d

 

转载于:https://www.cnblogs.com/Entr0py/p/7357267.html