2019-下载喜马拉雅音频

#coding=utf-8
'''
author : berrycam
time : 2019.8.1
'''

import os
import requests
from lxml import etree


class DownloadMedia(object):
    '''
    下载喜马拉雅的音频文件
    '''
    def __init__(self, target):
        self.__target_url = target
        self.__headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                          'Chrome/73.0.3683.75 Safari/537.36'}

    def get_url_list(self):
        '''
        :return:把所有需要下载音频json数据进行汇集
        '''
        resp_home_page = requests.get(self.__target_url, headers=self.__headers)
        html = resp_home_page.text
        elements = etree.HTML(html)
        # 创建下载文件夹
        folder_path = elements.xpath('//*[@id="root"]/main/section/div/div[2]/div[1]/div[1]/div[2]/div[2]/h1')[0].text.strip()
        if not os.path.exists(folder_path):
            os.mkdir(folder_path)
        # 获取总的页数
        page_navigation = elements.xpath('//*[@id="anchor_sound_list"]/div[2]/div/nav/ul/li')[-2]
        page_num = page_navigation.xpath('./a/span')[0].text
        # 获取要进行访问音频列表的URL列表
        page_url = ['{}p{}'.format(self.__target_url, num) for num in range(1, int(page_num)+1)]
        media_url_list = list()
        for url in page_url:
            response = requests.get(url, headers=self.__headers).text
            elements = etree.HTML(response)
            sound_list = elements.xpath('//*[@id="anchor_sound_list"]/div[2]/ul/li')
            for li in sound_list:
                media_href = li.xpath('./div[2]/a/@href')[0].strip()
                trackID = media_href.split('/')
                track_json = 'http://www.ximalaya.com/tracks/{}.json'.format(trackID[-1])
                media_url_list.append(track_json)
        return media_url_list,folder_path

    def down_media_m4a(self, media_url_list, folder_path):
        '''下载音频文件
        '''
        for url in media_url_list:
            resp = requests.get(url, headers=self.__headers)
            json_dict = resp.json()
            play_path = json_dict.get('play_path_64')
            title = json_dict.get('title')
            file_path = os.path.join(folder_path, title+'.m4a')
            resp_data = requests.get(play_path, headers=self.__headers)
            if resp_data.status_code == 200:
                with open(file_path, 'wb') as f:
                    f.write(resp_data.content)
                    print(' %s  finish'% file_path)
            else:
                print('error ：%d' % resp_data.status_code)


if __name__ == '__main__':
    # target_url = str(input("请输入喜马拉雅下载地址：\n"))
    target_url = 'https://www.ximalaya.com/yinyue/16162468/'
    d = DownloadMedia(target=target_url)
    url_list, forder_path = d.get_url_list()
    d.down_media_m4a(url_list, forder_path)