Python爬虫UA伪装爬取的实例讲解

import requests
if __name__=="__main__":
  headers={
    "User-Agent":"Mozilla/5.0(Windows NT 10.0;Win64;x64) AppleWebKit / 537.36(KHTML, likeGecko) 
    Chrome / 88.0.4324.150 Safari / 537.36"
  }
  url="https://www.sogou.com/web"
  queryword=input("输出关键字")
  param={
    "query":queryword
  }
  res=requests.get(url=url,params=param,headers=headers)
  res.encoding="utf-8"
  page_text=res.text
  fileName=queryword+".html"
  with open(fileName,"w",encoding="utf-8") as fs:
    fs.write(page_text)
  print(page_text+"爬取结束")

import requests
#UA:User—Agent(请求载体的身份标识)
# UA检测：门户网站的服务器会检测对应请求的载体身份标识，如果检测到请求的载体身份标识为某一款浏览器，说明该请求是一个正常的请求。
# 如果检测到请求的载体身份标识不是基于某一款浏览器的。则表示该请求为不正常的请求，则服务器端就很有可能会拒绝该次请求
if __name__=="__main__":
  headers={
    "User-Agent":"Mozilla/5.0(Windows NT 10.0;Win64;x64) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 88.0.4324.150 Safari / 537.36"
  }
  url="https://www.sogou.com/web"
  queryword=input("输出关键字")
  param={
    "query":queryword
  }
  res=requests.get(url=url,params=param,headers=headers)
  res.encoding="utf-8"
  page_text=res.text
  fileName=queryword+".html"
  with open(fileName,"w",encoding="utf-8") as fs:
    fs.write(page_text)
  print(page_text+"爬取结束")