Python爬虫实战之酷狗音乐爬取：想下载歌曲，但又要开启“人上人”服务，士可忍孰不可忍!

1.酷狗音乐：酷狗飙升榜_排行榜_乐库频道_酷狗网 (kugou.com)

废话不多说直接上代码：

import requests
import re
from pprint import pprint
import os
import time
import tqdm


headers = {
    'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 14_3 like Mac OS X) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30',
    'cookie': 'kg_mid=2d94fc2f6b14d23d5a9d31c5bbbb6d18; kg_dfid=3x87US2eiEz443jt7n29R06x; kg_dfid_collect=d41d8cd98f00b204e9800998ecf8427e'
}


def request(url):
    html_id = requests.get(url, headers=headers)
    music_id = re.findall('data-eid="(.*?)">', html_id.text)
    name = re.findall('<li class=" " title="(.*?)"', html_id.text)
    date = zip(name, music_id)
    for name, music_id in date:
        html_rexe = 'https://wwwapi.kugou.com/yy/index.php?r=play/getdata&encode_album_audio_id=' + music_id
        html_jiexi = requests.get(url=html_rexe, headers=headers)
        # pprint(html_jiexi.json())
        album_name = html_jiexi.json()['data']['audio_name']
        mice_url = html_jiexi.json()['data']['play_backup_url']
        lyrics = html_jiexi.json()['data']['lyrics']
        # 匹配歌曲信息中的列表部分并替换为空字符串
        song_info_cleaned = re.sub("\[(.*?)\]","", lyrics)
        print(name, mice_url, song_info_cleaned)
        save(album_name, mice_url, song_info_cleaned)

def save(album_name, mice_url, song_info_cleaned):
    with open(f'酷狗音乐\\{album_name}.mp3', 'wb') as f:
        music = requests.get(url=mice_url, headers=headers)
        f.write(music.content)
    with open(f'酷狗音乐\\{album_name}.txt', 'w+',encoding="utf-8")as a:
        a.write(song_info_cleaned)
    print(f'{album_name}下载完成')


if __name__ == '__main__':
    url = 'https://www.kugou.com/yy/rank/home/1-6666.html?from=rank' #  歌曲列表的url
    request(url)
    
    '''
    酷狗飙升榜: https://www.kugou.com/yy/rank/home/1-6666.html?from=rank
    酷狗top500:https://www.kugou.com/yy/rank/home/1-8888.html?from=rank

    '''

可以替换网址链接来爬取你想要爬取的音乐：

制作不易，点个赞再走吧～