python 喜马拉雅_【Python爬虫】喜马拉雅FM听书，陶冶情操，走向成功！-音频爬取，仅提供思路。...

[Python] 纯文本查看 复制代码# -*- coding : 'UTF-8' -*-

# 喜马拉雅FM听书下载

# Author ：XSX

# https://www.ximalaya.com/jiaoyu/29391994/p1/

# Python 3.8 PyCharm Community Edition 2019.3.3

import requests

from lxml import etree

import os

import time

import json

def Get_ID_Name(url, headers):

Contents_IDS = []

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

r.encoding = r.apparent_encoding

html = etree.HTML(r.text)

Titles = html.xpath('//div[@class="sound-list _Qp"]/ul/li/div[2]/a/@title')

Contents_lists = html.xpath('//div[@class="sound-list _Qp"]/ul/li/div[2]/a/@href')

for Contents_list in Contents_lists:

links_Cache = str(Contents_list).split('/')[-1]

JsonURL = 'https://www.ximalaya.com/revision/play/v1/audio?id={}&ptype=1'.format(links_Cache)

Contents_IDS.append(JsonURL)

return Titles, Contents_IDS

def Json_Get_links(Contents_IDS, headers):

Itemlists = []

n = 0

for Contents_ID in Contents_IDS:

contents = {}

time.sleep(1.5)

r1 = requests.get(Contents_ID, headers=headers)

r1.encoding = r1.apparent_encoding

results = json.loads(r1.text)

id = results['data']['trackId']

m4alinks = results['data']['src']

contents['ID'] = id

contents['M4aLinks'] = m4alinks

Itemlists.append(contents)

n += 1

print('已采集{}个链接！'.format(n))

# print(Itemlists)

return Itemlists

def DownLoadM4A(Itemlists, filename):

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36',

'If-None-Match': '"llN9ISnSdOkEmb835lC9NQ_j47Kl"',

'Host': 'fdfs.xmcdn.com',

}

if not os.path.exists('./XMLYFM'):

os.mkdir('./XMLYFM')

count = 0

for filename1, Itemlist in zip(filename, Itemlists):

srclinks = Itemlist['M4aLinks']

print(srclinks)

r2 = requests.get(srclinks, headers=headers)

print(r2.raise_for_status())

with open('./XMLYFM/' + str(filename1) + '.m4a', 'wb')as f:

f.write(r2.content)

count += 1

print('已下载{}个音频文件！'.format(count))

print("{}个音频文件已全部下载完成！".format(count))

if __name__ == '__main__':

print('正在加载...')

url = 'https://www.ximalaya.com/jiaoyu/29391994/p1/'

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',

'Cookie': '请换上自己的',

'Referer': 'https://www.ximalaya.com/jiaoyu/29391994/p1/',

'Host': 'www.ximalaya.com'

}

data1 = Get_ID_Name(url, headers)

IDlinks = data1[1]

fileName = data1[0]

DownLoadM4A(Json_Get_links(IDlinks, headers), fileName)