Python实现爬虫设置代理IP和伪装成浏览器的方法分享

#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openeropener=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')

#定义代理ipproxy_addr="122.241.72.191:808"#设置代理proxy=urllib.request.ProxyHandle({'http':proxy_addr})#创建一个openeropener=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')

#定义代理ipproxy_addr="122.241.72.191:808"#创建一个请求req=urllib.request.Request(url)#添加headersreq.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openeropener=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')

import urllib.requestpage_headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0",       "Host":"www.baidu.com",       "Cookie":"xxxxxxxx"       }req=urllib.request.Request(url,headers=page_headers)data=urllib.request.urlopen(req).read().decode('utf-8','ignore')

import urllib.requestimport urllib.parse#设置post参数page_data=urllib.parse.urlencode([                  ('pn',page_num),                  ('kd',keywords)                  ])#设置headerspage_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',     'Connection':'keep-alive',     'Host':'www.lagou.com',     'Origin':'https://www.lagou.com',     'Cookie':'JSESSIONID=ABAAABAABEEAAJA8F28C00A88DC4D771796BB5C6FFA2DDA; user_trace_token=20170715131136-d58c1f22f6434e9992fc0b35819a572b',     'Accept':'application/json, text/javascript, */*; q=0.01',     'Content-Type':'application/x-www-form-urlencoded; charset=UTF-8',     'Referer':'https://www.lagou.com/jobs/list_%E6%95%B0%E6%8D%AE%E6%8C%96%E6%8E%98?labelWords=&fromSearch=true&suginput=',     'X-Anit-Forge-Token':'None',     'X-Requested-With':'XMLHttpRequest'     }#打开网页req=urllib.request.Request(url,headers=page_headers)data=urllib.request.urlopen(req,data=page_data.encode('utf-8')).read().decode('utf-8')

#1.下载phantomjs安装到本地,并设置环境变量from selenium import webdriverbs=webdriver.PhantomJS()#打开urlbs.get(url)#获取网页源码url_data=bs.page_source#将浏览到的网页保存为图片bs.get_screenshot_as_file(filename)

from selenium import webdriverfrom selenium.webdriver.common.desired_capabilities import DesiredCapabilitiesdcap = dict(DesiredCapabilities.PHANTOMJS)dcap["phantomjs.page.settings.userAgent"] = ("Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0")bs = webdriver.PhantomJS(desired_capabilities=dcap)bs.get(url)#删除cookiebs.delete_all_cookies()#设置cookie#cookie格式：在浏览器cookie中查看，一个cookie需要包含以下参数，domain、name、value、pathcookie={  'domain':'.www.baidu.com', #注意前面有.  'name':'xxxx',   'value':'xxxx',   'path':'xxxx'  }#向phantomjs中添加cookiebs.add_cookie(cookie)

#1.下载web_driver工具（如chromdriver.exe）及对应的浏览器#2.将chromdriver.exe放到某个目录，如c:/chromdriver.exefrom selenium import webdriverdriver=webdriver.Chrome(executable_path="C:/chromdriver.exe")#打开urldriver.get(url)