python爬虫之爬取音频

import json    # 在这个url，音频链接为JSON动态生成，所以用到了json模块
import requests
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36"
}


# 请求网页
def open_url(url):
    r = requests.get(url, headers=headers)
    r.encoding = ‘utf-8‘
    html = r.text
    # 将JSON转化成字符串
    html = json.loads(html)
    return html


# 得到所有音频的链接
def get_urls(url):
    us = url[‘data‘][‘tracksAudioPlay‘]
    return us


def main():
    num = 1
    url = ‘https://www.ximalaya.com/revision/play/album?albumId=4256765&pageNum=1&sort=-1&pageSize=30‘
    html = open_url(url)
    urls = get_urls(html)
    # 遍历得到每个音频的链接和对应的名称
    for ul in urls:
        uls = ul[‘src‘]
        filename = ul[‘trackName‘]
        reponse = requests.get(uls).content
        with open(filename + ‘.m4a‘, ‘wb‘) as file:
            file.write(reponse)
        print(str(num) + ‘. ‘ + filename)
        num += 1

if __name__ == ‘__main__‘:
    main()