spider test

import os
import re
import time
import requests
#<p class="name"><a href="/discover/toplist?id=19723756" class="s-fc0">飙升榜</a></p>
#<p class="name"><a href="/discover/toplist?id=7095271308" class="s-fc0">泰语榜</a></p>
url = 'https://music.163.com/discover/toplist'
header = {
    'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36'
}
root_path = 'music/'
if not os.path.exists(root_path):
    os.makedirs('music/')
html = requests.get(url=url, headers=header).text
MS_list = re.findall(r'<p class="name"><a href="/discover/toplist\?id=(\d+)" class="s-fc0">(.*?)</a></p>',html)
for li_id, list_name in MS_list:
    time.sleep(3)
    l_url = f'https://music.163.com/discover/toplist?id={li_id}'
    music_html = requests.get(url=l_url,headers=header).text
    print(list_name,li_id,end='')
    if not os.path.exists(root_path+list_name):
        os.makedirs(root_path+list_name+'/')
    music_list = re.findall(r'<li><a href="/song\?id=(\d+)">(.*?)</a></li>',music_html)
    print(music_list)
    for li_id, li_name in music_list:
        l_url = f'http://music.163.com/song/media/outer/url?id={li_id}.mp3'
        music = requests.get(url=l_url,headers=header).content
        newfile = root_path+'/'+list_name+'/'+ li_name +'.mp3'
        with open(newfile,'wb') as fw:
            fw.write(music)
        print(li_name,'已保存到目录',list_name)
    print(list_name,'spider over')
print('over')

 具备python运行环境
使用到requests re time os 模块