1,超时处理
from urllib import request for i in range(0,50): #爬取50次 try: data = request.urlopen('https://read.douban.com/provider/all',timeout=1) #爬取时间为一秒 data=data.read() print(len(data)) except Exception as e: #否则异常 print("出现异常:"+str(e))
2,get请求
from urllib import request neirong="python" #要搜索的内容,如果是中文,则用request.quote转码 url="http://www.baidu.com/s?wd="+neirong #get请求格式 req= request.Request(url) #封装为get请求 data=request.urlopen(req).read() fh=open("D:/新建文本文档.html","wb") #如果没有,自动创建 fh.write(data) fh.close()
3,post请求
from urllib import request,parse url="http://www.iqianyue.com/mypost" mydata=parse.urlencode({ "name":"shaufhias", #输入的数据用urlencode设置 "pass":"hfjukafhj" }).encode("utf-8") req=request.Request(url,mydata) data=request.urlopen(req).read() fh=open("D:/新建文本文档1.html","wb") fh.write(data) fh.close()