闲来无事，找点段子一乐呵，就逛到糗事百科，这次爬取没有什么难度，唯一值得说道的是增加了一点点的代码健壮性。

import requestsfrom lxml import etreeclass Spider():    def __get_page(self,url,headers):        try:            response = requests.get(url,headers=headers)            if response.status_code == 200:                return response.text            else:                return None        except Exception:            return None    def __parse_page(self,html):        results = []        data = etree.HTML(html)        items = data.xpath('//div[@id="content-left"]/div')        for item in items:            #获取作者            author = item.xpath('./div[1]/a[2]/h2/text()')            if author:                results.append(author[0].strip())            else:                results.append('匿名用户')            #获取内容            content = item.xpath('./a[1]/div/span/text()')            if content:                results.append(''.join(content).replace('\n',''))            else:                results.append('此用户没有内容')            #获取好笑数            number = item.xpath('./div[2]/span[1]/i/text()')            if number:                results.append(number[0])            else:                results.append('0')        return results    def __save_to_txt(self,data):        with open('data.txt','w',encoding='utf-8') as f:            f.write(data)    def run(self):        for i in range(1,13):            url ='https://www.qiushibaike.com/text/page/' + str(i)            headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64)'                                     ' AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'                       }            html = self.get_page(url,headers)            result = self.parse_page(html)            self.save_to_txt(str(result))#实例化类spider = Spider()spider.run()

• 其中类里的方法是私有方法，外部不可调用。
• 解析网页部分增加了判断获取字段为空的处理方法。
• 欢迎大家跟我交流学习。