import urllib.request
import urllib.parse

http://so.1ppt.com/cse/search?s=18142763795818420485&entry=1&ie=gbk&nsid=3&ie=gbk&q=%D0%C2%C4%EA%BC%C6%BB%AEppt
# http://so.1ppt.com/cse/search?s=18142763795818420485&entry=1&ie=gbk&nsid=3&ie=gbk&q=%BF%AA%D1%A7%BC%D2%B3%A4%BB%E1ppt
class BaiduSpider(object):

def __init__(self):<br />        self.headers = {<br />            'User-Agent': ' Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 Safari/537.36'<br />        }<br />        self.base_url = 'https://www.1ppt.com/moban/ppt_moban_'<br />   # 发请求 获得响应<br />    def readPage(self,url):<br />        # 发请求<br />        req = urllib.request.Request(url, headers=self.headers)<br />        res = urllib.request.urlopen(req)  # 发请求，获得响应<br />        html = res.read().decode('gbk')
    return html
def writePage(self,filename,html,i):    # 写入到文件里<br />        with open(filename, 'w', encoding='gbk') as f:<br />            f.write(html)<br />            print(f'正在爬取{i}页')
def main(self):
    name = input('请输ppt名称：')
    # 起始页<br />        begin = int(input('请输入起始页：'))
    # 结束页<br />        end = int(input('请输入结束页：'))
    # # 中文网址有问题，需要对naem处理<br />        # kw = {'q': name}<br />        # result = urllib.parse.urlencode(kw)<br />        for i in range(begin, end + 1):
        url = self.base_url + str(i)+'.html'<br />            # 函数调用<br />            html = self.readPage(url)<br />            filename = '第' + str(i) + '页.html'<br />            self.writePage(filename, html, i)<br />        print('爬取结束')

if name == ‘main‘:
spider = BaiduSpider() # 创建实例对象
spider.main()