import urllib.request
import time
# 使用build_opener()是为了让python程序模仿浏览器进行访问
opener = urllib.request.build_opener()
opener.addheaders = [('User-agent', 'Mozilla/5.0')]
# 专刷某个页面
print('开始刷了哦：')
tempUrl = 'https://blog.csdn.net/Lin_QC/article/details/88966839'
for j in range(2000):
  try:
    opener.open(tempUrl)
    time.sleep(7)
    print('%d %s' % (j, tempUrl))
  except urllib.error.HTTPError:
    print('urllib.error.HTTPError')
    time.sleep(1)
  except urllib.error.URLError:
    print('urllib.error.URLError')
    time.sleep(1)

import urllib2
import BeautifulSoup
User_Agent = 'Mozilla/5.0 (Windows NT 6.3; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0'
header = {}
header['User-Agent'] = User_Agent
url = 'https://www.xicidaili.com/wt/1'
req = urllib2.Request(url, headers=header)
res = urllib2.urlopen(req).read()
soup = BeautifulSoup.BeautifulSoup(res)
ips = soup.findAll('tr')
f = open("proxy", "w")
for x in range(1,len(ips)):
  ip = ips[x]
  tds = ip.findAll("td")
  ip_temp = tds[1].contents[0]+","+tds[2].contents[0]+"\n"
  print tds[1].contents[0]+"\t"+tds[2].contents[0]
  f.write(ip_temp)

import urllib2
import socket
import time
import random
socket.setdefaulttimeout(3)
user_agent_list = [
  'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '
           'Chrome/45.0.2454.85 Safari/537.36 115Browser/6.0.3',
  'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
  'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
  'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)',
  'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)',
  'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
  'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11',
  'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
  'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)',
  'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0',
  'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
]
f = open("proxy")
lines = f.readlines()
proxys = []
 
for i in range(0,len(lines)):
  ip = lines[i].strip().split(",")
  proxy_host = "http://"+ip[0]+":"+ip[1]
  print "http://"+ip[0]+":"+ip[1]
  proxy_temp = {"http": proxy_host}
  proxys.append(proxy_temp)
urls = {"https://blog.csdn.net/Lin_QC/article/details/88966839",
    "https://blog.csdn.net/Lin_QC/article/details/88930018",
    "https://blog.csdn.net/Lin_QC/article/details/88642949",
    "https://blog.csdn.net/Lin_QC/article/details/84568170",
    "https://blog.csdn.net/Lin_QC/article/details/84451279",
    "https://blog.csdn.net/Lin_QC/article/details/84927503",
    }
 
j=1
for i in range(100):
  for proxy in proxys:
    for url in urls:
      try:
        user_agent = random.choice(user_agent_list)
        proxy_support = urllib2.ProxyHandler(proxy)
        opener = urllib2.build_opener(proxy_support, urllib2.HTTPHandler)
        urllib2.install_opener(opener)
        req = urllib2.Request(url)
        c = urllib2.urlopen(req)
        print ("sucessful",j)
        j+=1
        time.sleep(5) 
      except Exception, e:
        print proxy
        print e
        continue