简单爬一下糗事百科

简单爬一下糗事百科

整合代码如下

import requests


class QiuShiBaiKe():
    '''
    实现下载糗事百科的指定页码前的内容，存储下载内容
    '''
    def __init__(self,pages):
        '''
        初始化操作
        :param pages:
        '''
        self.pages_download = pages
        self.base_url = "https://www.qiushibaike.com/8hr/page/{}/"

    def make_url_list(self):
        '''
        获取待下载的url
        :return:返回生成的url列表
        '''
        return [self.base_url.format(i) for i in range(1,self.pages_download)]

    def save_url(self,content,file_name):
        '''
        将指定内容进行存储
        :param content:
        :param 无
        :return:
        '''
        with open(file_name,'wb') as f:
            f.write(content)

    def download_url(self,url_strr):
        '''
        下载指定url处的内容
        :param url_strr:
        :return:
        '''
        response = requests.get(url_strr)
        return response.content

    def run(self):
        url_lists = self.make_url_list()
        for url_str in url_lists:
            result_content = self.download_url(url_str)
            file_name = "糗事百科第{}页.html".format(url_lists.index(url_str)+ 1)
            self.save_url(result_content,file_name)

QS = QiuShiBaiKe(5)
QS.run()