1. import urllib.request
    2. import urllib.parse
    4. class BaiduSpider:
    5.     def __init__(self):
    6.         self.headers = {
    7.             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36'
    8.         }
    9.     def readPage(self,url):   # 发请求获取响应
    10.         rep = urllib.request.Request(url, headers=self.headers)
    11.         response = urllib.request.urlopen(rep)
    12.         html = response.read().decode('utf-8')
    13.         return html
    14.     def writePage(self,filename,html):
    15.         with open(filename, 'w', encoding='utf-8') as f:
    16.             f.write(html)
    17.     def main(self):
    18.         name = input('请输入贴吧名称：')  # 1-5 , 2-3
    19.         begin = int(input('请输入开始页：'))
    20.         end = int(input('请输入结束页：'))
    21.         name1 = urllib.parse.quote(name)
    22.         for page in range(begin, end + 1):  # range:左闭右开
    23.             pn = (page - 1) * 50
    24.             url = f'https://tieba.baidu.com/f?kw={name1}&pn={pn}'
    25.             html = self.readPage(url)  # 目的：获取页面内容
    26.             filename = f'第{page}页.html'
    27.             self.writePage(filename, html)
    29. d = BaiduSpider()
    30. d.main()