爬取喜马拉雅音频

# https://www.ximalaya.com/revision/play/v1/audio?id=642854823&ptype=1
# https://www.ximalaya.com/revision/play/v1/audio?id=642854713&ptype=1
# 发现id不一样
import requests
from bs4 import BeautifulSoup
import time
import json
# 请求头
header = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36'}
id = input('请输入id号')
# 构造音频页面url
url = f'https://www.ximalaya.com/revision/play/v1/audio?id={id}&ptype=1'
# 请求一级页面响应
response = requests.get(url,headers = header)
# 如果响应成功获取响应数据，响应不成功则停止
if response.status_code == 200:
    # 将网页文本数据转化为json
    html_data = response.json()
    print(html_data)
    # 获取音频的链接
    detail = html_data.get('data').get('src')
    print(detail)
    # 响应音频链接
    detail_music = requests.get(detail)
    # 获取响应数据
    music_data = detail_music.content
    # 将数据写入文件
    with open(f'./{id}的音频.m4a','wb') as fp:
        fp.write(music_data)
else:
    print('首页响应失败')

有缺点，缺点是只能获取已知的id音频。如果想要获取未知的id和名字音频，得进入首页获取相应得id和名字