爬虫使用代理池

在使用python爬虫的时候，经常会遇见所要爬取的网站采取了反爬取技术，高强度、高效率地爬取网页信息常常会给网站服务器带来巨大压力，所以同一个IP反复爬取同一个网页，就很可能被封，那如何解决呢？使用代理ip，设置代理ip池。

这个代码首先获取 http://www.xicidaili.com/nn/网站中的一个随机的代理ip。然后就是刷自己的CSDN访问量的，，，，，（为了学习，为了学习）

from bs4 import BeautifulSoup
import requests
import random
def get_ip_list(url, headers):
  web_data = requests.get(url, headers=headers)
  soup = BeautifulSoup(web_data.text, 'lxml')
  ips = soup.find_all('tr')
  ip_list = []
  for i in range(1, len(ips)):
    ip_info = ips[i]
    tds = ip_info.find_all('td')
    ip_list.append(tds[1].text + ':' + tds[2].text)
  return ip_list
def get_random_ip(ip_list):
  proxy_list = []
  for ip in ip_list:
    proxy_list.append('http://' + ip)
  proxy_ip = random.choice(proxy_list)
  proxies = {'http': proxy_ip}
  return proxies


if __name__ == '__main__':
  url = 'http://www.xicidaili.com/nn/'
  headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36'
  }#请求头
  ip_list = get_ip_list(url, headers=headers)
  proxies = get_random_ip(ip_list) #获取一个随机的ip
  url = ['https://blog.csdn.net/T_I_A_N_/article/list/1?', 'https://blog.csdn.net/T_I_A_N_/article/list/2?',
         'https://blog.csdn.net/T_I_A_N_/article/list/3?', 'https://blog.csdn.net/T_I_A_N_/article/list/4?']
  for i in url:
      response = requests.get(i, headers=headers, proxies=proxies)
      soup = BeautifulSoup(response.text, 'html.parser')
      div = soup.find(name='div', attrs={'class': 'article-list'})
      href = div.find_all(name='h4')
      a = []
      for link in href:
          b = link.find(name='a')
          hr = b.attrs.get('href')
          a.append(hr)
      for i in a:
          response = requests.get(i)