python简易爬虫-白红宇

python简易爬虫

阅读量：190 次

发布时间：2019-02-28

本文共 1909 字，大约阅读时间需要 6 分钟。

爬取喜马来雅男频小说这几本

在这里插入图片描述

import requestsimport reimport csvheaders = {       'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36','Cookie':'testcookie=yes; Hm_lvt_bc3b748c21fe5cf393d26c12b2c38d99=1619717328; Hm_lpvt_bc3b748c21fe5cf393d26c12b2c38d99=1619717328; JJEVER=%7B%22fenzhan%22%3A%22noyq%22%7D; smidV2=20210430012854effd865c944ddc429b0c481dfef3f31d0035c72a77d581610'}class ximalaiyaSpider:    def getSource(self):        # 获取url数据        # 目标url        url = 'https://www.ximalaya.com/channel/7/'        resp = requests.get(url, headers=headers)        resp.encoding='utf-8'        # print(resp.content.decode('utf-8'))        return resp.text    def parseSource(self):        content =self.getSource()        r =re.match(r'.*?(
   
    .*?
   
).*?',content,re.S)        # print(r.group(1))        # #摸金天师（紫襟演播）        a =r.group(1)        a_all=re.findall(r'',a,re.S)        # print(a_all)  #摸金天师（紫襟演播）'        a_titleall=[]        pattern=re.compile(r'
    
     .*?
    ',re.S)        for i in a_all:            onetitle =pattern.match(i)            # print(type(onetitle.group(1)))#摸金天师（紫襟演播）            # print(onetitle.group(2))            # #[https://www.ximalaya.com/]这段没有要后期拼接url哦，这里group（2）结果是/youshengshu/4756811/            a_titleone=[onetitle.group(1),'https://www.ximalaya.com/'+onetitle.group(2)]            # print(a_titleone)#['"摸金天师（紫襟演播）" ', 'https://www.ximalaya.com/youshengshu/4756811/']            a_titleall.append(a_titleone)        return a_titleall    def saveData(self):        content=self.parseSource()        # 写入csv        with open('喜马来雅.csv','w',encoding='utf-8',newline='')as f:            writer=csv.writer(f)            header1=["作品",'链接']            writer.writerow(header1)            writer.writerows(content)def main():    ximalaiyaSpider().saveData()if __name__ == '__main__':    main()