python 爬虫案例-1爬取百度贴吧适合小白

import urllib.request
import  urllib.parse
class ABC():
    def __init__(self):
        # 伪装
        self.hede={

            'User-Agent':' Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.5060.114 Safari/537.36 Edg/103.0.1264.49',
         
            }
        # 头
        self.base_url='https://tieba.baidu.com/f?'
    def A(self,url):
        # 对拼接好的网站进行处理
        # 请求头。防止反扒
        req = urllib.request.Request(url, headers=self.hede)
        # 访问urlopen
        res = urllib.request.urlopen(req)
        html = res.read().decode('utf-8')
        return html
    def B(self,filennaem,html):
        # 写入
        with open(filennaem, 'w', encoding='utf_8') as f:
            f.write(html)

    # def C(self):
    #     pass
    def main(self):
        name = input('输入查询内容')
        begin = int(input('输入开始页数'))
        end = int(input('输入结束页'))
        kw = {'kw': name}
        resule = urllib.parse.urlencode(kw)
        for i in range(begin, end + 1):
            pn = (i - 1) * 50
            # print(pn)
            # base_url = 'https://tieba.baidu.com/f?'
            url = self.base_url + resule + '&pn=' + str(pn)
            html=self.A(url)
            filennaem = '第' + str(i) + '页.html'
            self.B(filennaem,html)
if __name__ == '__main__':
    ss=ABC()
    ss.mai

 

 运行过程

 

 运行的结果