爬取酷狗音乐top500榜

import requests
from bs4 import BeautifulSoup
import time
headers={"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36 Edg/89.0.774.57"}
def get_info(url):
    wb_data=requests.get(url,headers=headers)
    soup=BeautifulSoup(wb_data.text,'lxml')
    ranks=soup.select('span.pc_temp_num')
    titles=soup.select('div.pc_temp_songlist>ul>li>a')
    times=soup.select('span.pc_temp_tips_r>span')
    for rank,title,time in zip(ranks,titles,times):
        data={
            'rank':rank.get_text().strip(),
            'singer':title.get_text().split('-')[0],
            'song':title.get_text().split('-')[1],
            'time':time.get_text().strip()
        }
        print(data)
if __name__ in "__main__":
    urls=['https://www.kugou.com/yy/rank/home/{}-8888.html'.format(str(i)) for i in range(1,24)]
    for url in urls:
        get_info(url)
        time.sleep(1)

我觉得这是比较简单的了，有不懂的下方留言或者关注我的公共号，我为你解答

python爬虫架构学习.

别问我为什么想些这代码（今天看了一本数据清洗的书，我看看有多少人因这个爬酷狗。发现这个爬虫还能爬）