python爬取百度贴吧，任意吧任意页数的网页源代码

python爬取百度贴吧，任意吧任意页数的网页源代码

from urllib import request
import urllib
import time
from urllib import parse
header = {'User-Agent':'(Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.36 Safari/537.36'}


# https://tieba.baidu.com/f?kw=python&ie=utf-8&pn=0
# https://tieba.baidu.com/f?kw=python&ie=utf-8&pn=50
# https://tieba.baidu.com/f?kw=python&ie=utf-8&pn=100
def loadpage(fullurl,filename):
    print("正在下载：")
    req = request.Request(fullurl,headers=header)
    res = request.urlopen(req).read()
    return res


def writepage(html,filename):
    print("正在保存",filename)
    with open (filename,"wb")as f:
        f.write(html)
    print("---------------------------------------")
#构造url
def tiebaspider (url,begin,end):
    for page in range(begin,end+1):
        pn = (page-1)*50
        fullurl = url + "&pn"+str(pn)
        filename = "D:/第"+str(page)+"页.html"
        html = loadpage(fullurl,filename)
        writepage(html,filename)

if __name__ == '__main__':
    kw = input("请输入贴吧名字：")
    begin = int(input("请输入起始页："))
    end = int(input("请输入结束页："))

    url = (r"https://tieba.baidu.com/")
    key = urllib.parse.urlencode({"kw":kw})
    url = url + key


    tiebaspider(url, begin, end)
    time.sleep(10)