python3爬虫伪装代理IP

在爬取类似 起点 色魔张大妈 这样的网站时，会被网站看出是爬虫机制，这时需要伪装成浏览器以及使用IP代理的方式来爬去正常内容。

 

• 实例

• import re
  import requests
  import urllib.request
  from lxml import etree
  
  url='https://www.qidian.com/rank/hotsales'
  #浏览器伪装
  # opener=urllib.request.build_opener()
  
  #设置代理
  proxy = {'http': '125.127.24.239:808'}
  proxy_support = urllib.request.ProxyHandler(proxy)
  opener=urllib.request.build_opener(proxy_support)
  opener.addheaders=[('User-Agent','Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36')]
  urllib.request.install_opener(opener)
  html=urllib.request.urlopen(url).read().decode('utf-8')
  
  # html=requests.get(url).text
  # f = open('FC.html','w')
  # f.write(str(html))
  # f.close()
  # print(html)
  
  selector=etree.HTML(html)
  info = selector.xpath('//div[@class="book-mid-info"]')
  
  for each in info:
      name=each.xpath('h4/a[@data-eid="qd_C40"]/text()')
      author=each.xpath('p[@class="author"]/a[@class="name"]/text()')
      target=each.xpath('p[@class="author"]/a[@data-eid="qd_C42"]/text()')
      intro=each.xpath('p[@class="intro"]/text()')[0]
      print(name)
      print(author)
      print(target)
      print(intro+'\n')

 

 

 

• 爬虫浏览器伪装

• #导入urllib.request模块
  import urllib.request
  
  #设置请求头
  headers=("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0")
  #创建一个opener
  opener=urllib.request.build_opener()
  #将headers添加到opener中
  opener.addheaders=[headers]
  #将opener安装为全局
  urllib.request.install_opener(opener)
  #用urlopen打开网页
  data=urllib.request.urlopen(url).read().decode('utf-8','ignore')

• 设置代理

• #定义代理ip
  proxy_addr="122.241.72.191:808"
  #设置代理
  proxy=urllib.request.ProxyHandle({'http':proxy_addr})
  #创建一个opener
  opener=urllib.request.build_opener(proxy,urllib.request.HTTPHandle)
  #将opener安装为全局
  urllib.request.install_opener(opener)
  #用urlopen打开网页
  data=urllib.request.urlopen(url).read().decode('utf-8','ignore')

 

• 同时设置用代理和模拟浏览器访问

• #定义代理ip
  proxy_addr="122.241.72.191:808"
  #创建一个请求
  req=urllib.request.Request(url)
  #添加headers
  req.add_header("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko)
  #设置代理
  proxy=urllib.request.ProxyHandle("http":proxy_addr)
  #创建一个opener
  opener=urllib.request.build_opener(proxy,urllib.request.HTTPHandle)
  #将opener安装为全局
  urllib.request.install_opener(opener)
  #用urlopen打开网页
  data=urllib.request.urlopen(req).read().decode('utf-8','ignore')

  
   

代理用IP可以参考http://www.xicidaili.com/

 

内容参考于http://blog.csdn.net/d1240673769/article/details/74295148 感谢