喜马拉雅爬取

https://www.ximalaya.com/revision/play/album?albumId=11219907&pageNum=1&sort=-1&pageSize=30这个url找了好久，fo了。。。

点击全部播放按钮后出现右边箭头指的url，发现是个json格式的字符串，直接解析就ok了。

code：

import re
import requests
from bs4 import BeautifulSoup
import json

headers_1 = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.6824.400 QQBrowser/10.3.3127.400'
}

urls = []
for i in range(1,4):
    urls.append('https://www.ximalaya.com/revision/play/album?albumId=11219907&pageNum='+str(i)+'&sort=-1&pageSize=30')
x = 1
for u in urls:
    response = requests.get(u,headers = headers_1)
    html = response.text
    dic = json.loads(html)
    #print(type(dic['data']['tracksAudioPlay']))  list
    for content in dic['data']['tracksAudioPlay']:
        print(x,content['trackName'],'正在下载',content['src'])
        with open('E:\岳云鹏相声\%d%s.m4a' %(x,content['trackName']),'wb') as f:
            f.write(requests.get(content['src'],headers = headers_1).content)
        x += 1