喜马拉雅app 爬取音频文件

============== 2019-10-28更新 =================
因为喜马拉雅的源码格式改了，所以爬虫代码也更新了一波

# -*- coding: utf-8 -*-

# website: http://30daydo.com

# @Time : 2019/6/30 12:03

# @File : main.py



import requests

import re

import os



url = 'http://180.153.255.6/mobile/v1/album/track/ts-1571294887744?albumId=23057324&device=android&isAsc=true&isQueryInvitationBrand=true&pageId={}&pageSize=20&pre_page=0'

headers = {'User-Agent': 'Xiaomi'}



def download():

    for i in range(1, 3):

        r = requests.get(url=url.format(i), headers=headers)

        js_data = r.json()

        data_list = js_data.get('data', {}).get('list', [])

        for item in data_list:

            trackName = item.get('title')

            trackName = re.sub('[\/\\\:\*\?\"\<\>\|]', '_', trackName)

            # trackName=re.sub(':','',trackName)

            src_url = item.get('playUrl64')

            filename = '{}.mp3'.format(trackName)

            if not os.path.exists(filename):



                try:

                    r0 = requests.get(src_url, headers=headers)

                except Exception as e:

                    print(e)

                    print(trackName)

                    r0 = requests.get(src_url, headers=headers)





                else:

                    with open(filename, 'wb') as f:

                        f.write(r0.content)



                    print('{} downloaded'.format(trackName))



            else:

                print(f'{filename}已经下载过了')



import shutil



def rename_():

    for i in range(1, 3):

        r = requests.get(url=url.format(i), headers=headers)

        js_data = r.json()

        data_list = js_data.get('data', {}).get('list', [])

        for item in data_list:

            trackName = item.get('title')

            trackName = re.sub('[\/\\\:\*\?\"\<\>\|]', '_', trackName)

            src_url = item.get('playUrl64')



            orderNo=item.get('orderNo')



            filename = '{}.mp3'.format(trackName)

            try:



                if os.path.exists(filename):

                    new_file='{}_{}.mp3'.format(orderNo,trackName)

                    shutil.move(filename,new_file)

            except Exception as e:

                print(e)











if __name__=='__main__':

    rename_()

 
音频文件也更新了，详情见百度网盘。
 
 
======== 2018-10=============
 爬取喜马拉雅app上 杨继东的投资之道 的音频文件
运行环境：python3

# -*- coding: utf-8 -*-

# website: http://30daydo.com

# @Time : 2019/6/30 12:03

# @File : main.py



import requests

import re

url = 'https://www.ximalaya.com/revision/play/album?albumId=23057324&pageNum=1&sort=1&pageSize=60'

headers={'User-Agent':'Xiaomi'}



r = requests.get(url=url,headers=headers)

js_data = r.json()

data_list = js_data.get('data',{}).get('tracksAudioPlay',)

for item in data_list:

    trackName=item.get('trackName')

    trackName=re.sub(':','',trackName)

    src_url = item.get('src')

    try:

        r0=requests.get(src_url,headers=headers)

    except Exception as e:

        print(e)

        print(trackName)

    else:

        with open('{}.m4a'.format(trackName),'wb') as f:

            f.write(r0.content)

        print('{} downloaded'.format(trackName))

保存为main.py
然后运行 python main.py
稍微等几分钟就自动下载好了。




附下载好的音频文件：
链接：https://pan.baidu.com/s/1t_vJhTvSJSeFdI1IaDS6fA 
提取码：e3zb 
 

原创文章
转载请注明出处
http://30daydo.com/article/503