select

最新推荐文章于 2022-11-24 14:56:41 发布

王蔚来

最新推荐文章于 2022-11-24 14:56:41 发布

阅读量115

点赞数 1

本文链接：https://blog.csdn.net/weixin_42518256/article/details/87073327

版权

import requests,bs4


class web():
    def __init__(self):
        self.headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'}
        self.seek_list=[]
        self.Spider()

    def Spider(self):
        url= 'https://wordpress-edu-3autumn.localprod.forc.work/'
        res=requests.get(url,headers=self.headers)
        soup1=bs4.BeautifulSoup(res.text,'html.parser')
        for i in range(4):
            soup = soup1.select('h2[class="entry-title"]')[i]
            title = soup.select('a')[0].getText()
            link = soup.select('a')[0].get('href')
            time_soup = soup1.select('time[class="entry-date published"]')[i].getText()
            self.seek_list.append([title,link,time_soup])
        print(self.seek_list)

web()