python爬贴吧修改版本

Posted 2020-12-18 名狐1993

#coding=utf-8
#Version:python3.7.4
#Tools:Pycharm 2018.3.5
_date_ = ‘2020/7/13 23:42 ‘
import urllib.request
import  urllib.parse
url="https://tieba.baidu.com/f"
name=str(input("请输入贴吧名称"))
#将贴吧名称变为url码
word=urllib.parse.quote(name)
num1=int(input("请输入开始页面数"))
num2=int(input("请输入结束页面数"))
ua_headers= {"User-Agent" : "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"}
for i in(num1,num2+1):
    #贴吧每也pn要加上50，首页为0
    num=(i-1)*50
    page=str(num)
    #完整url
    newUrl = url + "?kw=" + word+"&pn="+page
    print(newUrl)
    req=urllib.request.Request(newUrl,headers=ua_headers)
    req1=urllib.request.urlopen(req)
    html=req1.read().decode()
    print(html)
    print("--------%d打印完毕---------------",i)