import urllib
import urllib.request

def loadPage(url,filename):
    """
    作用：根據url傳送請求，獲取html資料;
    :param url:
    :return:
    """
    request=urllib.request.Request(url)
    html1= urllib.request.urlopen(request).read()
    return  html1.decode('utf-8')

def writePage(html,filename):
    """
    作用將html寫入本地

    :param html: 伺服器相應的檔案內容
    :return:
    """
 

    with open(filename,'w') as f:
        f.write(html)
    print('-'*30)
def tiebaSpider(url,beginPage,endPage):
    """
    作用貼吧爬蟲排程器，負責處理每一個頁面url;
    :param url:
    :param beginPage:
    :param endPage:
    :return:
    """
    for page in range(beginPage,endPage+1):
        pn=(page - 1)*50
        fullurl=url+"&pn="
 
+str(pn)
        print(fullurl)
        filename='第'+str(page)+'頁.html'
        html= loadPage(url,filename)

        writePage(html,filename)



if __name__=="__main__":
    kw=input('請輸入你要需要爬取的貼吧名:')
    beginPage=int(input('請輸入起始頁'))
    endPage=int(input('請輸入結束頁'))
    url='https://tieba.baidu.com/f?'
 

    kw1={'kw':kw}
    key = urllib.parse.urlencode(kw1)
    fullurl=url+key
    tiebaSpider(fullurl,beginPage,endPage)

為了返回的html一定要進行decode編碼一下。