如何用python爬虫抓取音乐

阿里云国内75折回扣微信号：monov8

阿里云国际，腾讯云国际，低至75折。AWS 93折免费开户实名账号代冲值优惠多多微信号：monov8 飞机：@monov6

优美的音乐可以让人的心情放松愉悦，喜欢听音乐的小伙伴经常苦恼无法获取热门音乐追赶时尚潮流。下面几行简单的代码轻松爬取你想要的音乐，大家可以一起试试看！

# coding=utf-8
  
import os.path
import pprint
import re

import requests


if not os.path.exists('music/'):
    os.mkdir('music/')
url = 'https://www.kugou.com/yy/html/rank.html'

headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.93 Safari/537.36'
}

rsp = requests.get(url, headers=headers)
# print(rsp.text)
hash_list = re.findall('"Hash":"(.*?)"', rsp.text)
album_list = re.findall('"album_id":(.*?),', rsp.text)
# print(rsp.text)
zip_list = zip(hash_list, album_list)
for hash1, album_id in zip_list:
    # print(hash1, album_id)

    index_url = 'https://wwwapi.kugou.com/yy/index.php'
    data = {
        'r': 'play/getdata',
        'hash': hash1,
        'dfid': '34dlds4MjPyk0XgC5n0MobxL',
        'appid': '1014',
        'mid': 'fbcb28bbcbd1758696a1eb4363b645d6',
        'platid': '4',
        'album_id': album_id,
        '_': '1649395118742'
    }
    rsp1 = requests.get(url=index_url, params=data, headers=headers)
    # print(rsp1.json())
    # pprint.pprint(rsp1.json())
    audioname = rsp1.json()['data']['audio_name']
    playurl = rsp1.json()['data']['play_url']
    # print(audioname, playurl)
    music_content = requests.get(url=playurl, headers=headers).content
    with open('music\\' + audioname + '.mp3', 'wb') as f:
        print(f'*************************正在爬取歌曲{audioname}中***********************')
        f.write(music_content)