1、get方式:如何为爬虫添加ip代理,设置Request header(请求头) import urllib import urllib.requestimport urllib.parseimport randomimport timefrom fake_useragent import UserAgentua = UserAgent()url = "http://www.baidu.co
1、get方式:如何为爬虫添加ip代理,设置Request header(请求头)
import urllib import urllib.request import urllib.parse import random import time from fake_useragent import UserAgent ua = UserAgent() url = "http://www.baidu.com" ######################################################## ''' 设置ip代理 iplist = [ '127.0.0.1:80'] #可自行上网找一些代理 proxy_support = urllib.request.ProxyHandler({'http':random.choice(iplist)}) #也可以设置为https,要看你的代理支不支持 opener = urllib.request.build_opener(proxy_support) ''' ######################################################## '''无ip代理''' opener = urllib.request.build_opener() '''f12查看请求头添加即可,不一定都需要全添加↓↓↓''' opener.addheaders = [('Host', 'newtab.firefoxchina.cn'), ('User-Agent',ua.random), ('Accept-Encoding','deflate, br'), ('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'), ('Accept-Language', 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2'), ('Connection', 'keep-alive'), ('Upgrade-Insecure-Requests',1), ('Cookie', '__gads=ID=138080209be66bf8:T=1592037395:S=ALNI_Ma-g9wHmfxFL4GCy9veAjJrJRsNmg; Hm_lvt_dd4738b5fb302cb062ef19107df5d2e4=1592449208,1592471447,1592471736,1594001802; uid=rBADnV7m04mi8wRJK3xYAg=='), ] urllib.request.install_opener(opener) while True: try: response = urllib.request.urlopen(url) break except Exception as e: print("错误信息:" + str(e)) time.sleep(3) html = response.read().decode("utf-8") print(html)
2、post方式添加载荷(此处是打比方),修改urllib.request.install_opener(opener)以下的代码即可
urllib.request.install_opener(opener) # data = {} #当页面提交数据是有载荷但是载荷内容为空时,必须以data = {}传参,不然无法获取网页数据 data = {'_csrf':'请把', 'collection-name':'载荷的参数', 'description':'以这种形式', '_csrf':'装载' } data = urllib.parse.urlencode(data).encode('utf-8') req = urllib.request.Request(url,data) while True: try: response = urllib.request.urlopen(req) break except Exception as e: print("错误信息:" + str(e)) time.sleep(3) html = response.read().decode("utf-8")
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持易盾网络。