python爬蟲之爬取音頻

抓取“xmly”鬼故事音頻

import json    # 在這個url，音頻鏈接為JSON動態生成，所以用到了json模塊
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"
}


# 請求網頁
def open_url(url):
    r = requests.get(url, headers=headers)
    r.encoding = 'utf-8'
    html = r.text
    # 將JSON轉化成字符串
    html = json.loads(html)
    return html


# 得到所有音頻的鏈接
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)
    # 遍歷得到每個音頻的鏈接和對應的名稱
    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()