爬取百度贴吧

from urllib import request
import urllib
import time

#构造请求头信息
header={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Safari/537.36 Edg/92.0.902.62",
	"cokie":"BAIDUID_BFESS=C21E87F3A6141FEB572318C6401DB7F7:FG=1; __yjs_duid=1_f40a3356560e7cb76db7f507636f39241627698973259; BIDUPSID=D0964D17E35A3545AC619ADA558551F9; PSTM=1627874092; BAIDUID=D0964D17E35A35450EB2B011CB5E575B:FG=1; ab_sr=1.0.1_ZTNiYTdjNjVmNjA2NTZlYWNkODZhZjBmNmMxMzJlZWUxZGJiMGFhZTBmN2M3N2EzNjAyMTdlMGM4MDIxNjA2ZGQ4NDRkNzNhMmZmMmM2NTFlMDFiYTBhMGEyYWYzNTYwZjY3ZDg5NzE0MDQwMDVmZjNlM2M1NDQ1ZWIzMTVmZWJhYjU5Y2MwMDA2M2M5YmFhNmExMWRhY2FhYTVlODhlNw==",
		}

#https://tieba.baidu.com/f?kw=python&ie=utf-8    第一页
#https://tieba.baidu.com/f?kw=python&ie=utf-8&pn=0  第一页
#https://tieba.baidu.com/f?kw=python&ie=utf-8&pn=50   第二页
#https://tieba.baidu.com/f?kw=python&ie=utf-8&pn=100    第三页

def loadpage(fullurl,filname):
	print("正在下载：",filname)
	req=request.Request(fullurl,headers=header)
	response=request.urlopen(req).read()
	return response

def writepage(html,filname):
	print("正在保存：",filname)

	with open(filname,"wb") as f:
		f.write(html)

	print("-------------------")


#构造url
def tiezi(url,begin,end):
	for page in range(begin,end+1):
		pn=(page-1)*50
		fullurl=url+"&pn="+str(pn)  #贴吧每一页的网址
		filname="D:/第"+str(page)+"页.html"  #每次请求保存文件名

		html=loadpage(fullurl,filname)  #调用爬虫，爬取网页
		writepage(html,filname)   #把获取的网页信息写入本地


if __name__ == '__main__':
	
	kw=input("请输入贴吧名：")
	begin=int(input("请输入起始页："))
	end=int(input("请输入结束页："))
	url="http://tieba.baidu.com/f?"
	#构造url编码
	key=urllib.parse.urlencode({"kw":kw})

	url=url+key
	tiezi(url,begin,end)
	time.sleep(10)