某网站音频下载

msmvc

原帖 https://www.52pojie.cn/thread-1963688-1-1.html
是要下载2楼说的网站里的1800+音频
http://www.yuetingba.cn/book/detail/3a0a4394-004b-58cc-bee6-fd01e7787da4/0


我试着分析了一下
页面是

onclick=

testFn('3a0a487b-f73b-aae9-f268-d501098118b9')

只能通过浏览器的开发者工具直接得到真实的mp3地址
1800我多个文件，总不能一个一个下载吧
哪位大神帮分析一下，通过

testFn('3a0a487b-f73b-aae9-f268-d501098118b9')如何得到真实的地址

我好写个工具把音频下载下来

爱飞的猫

抓包 http://www.yuetingba.cn/api/app/docs-listen/3a0a487b-f73b-aae9-f268-d501098118b9/ting-with-ef 请求：

{
    "id": "3a0a487b-f73b-aae9-f268-d501098118b9",
    "bookId": "3a0a4394-004b-58cc-bee6-fd01e7787da4",
    "tingNo": 1,
    "title": "",
    "ef": "Ob1B4vtdV6FAXBD3sD3PlI02ie5zefztNrbsg7VpNwRxvQfcxrTgKcUDnTF/weOy8Ut7cNwUVGLgfsY6RQuAfegb3ogVjwIwzwG5Qxaplve/S5JTVFlupQ99g2eRi8E2D5SBAhY3EIbFxVyvIEHH2Q=="
}

剩下的就很简单了，交给你自己琢磨：

let wo = new class {
    constructor() {
        this.key = mo.enc.Base64.parse("le95G3hnFDJsBE+1/v9eYw=="),
        this.iv = mo.enc.Base64.parse("IvswQFEUdKYf+d1wKpYLTg==")
    }
    encrypt(e) {
        const t = mo.enc.Utf8.parse(e);
        return mo.AES.encrypt(t, this.key, {
            iv: this.iv,
            mode: mo.mode.CBC,
            padding: mo.pad.Pkcs7
        }).ciphertext.toString(mo.enc.Base64)
    }
    decrypt(e) {
        e = (e + "").replace(/\n*$/g, "").replace(/\n/g, "");
        const t = mo.enc.Base64.parse(e)
          , n = mo.enc.Base64.stringify(t);
        return mo.AES.decrypt(n, this.key, {
            iv: this.iv,
            mode: mo.mode.CBC,
            padding: mo.pad.Pkcs7
        }).toString(mo.enc.Utf8).toString()
    }
}

hebeijianke

[Python] 纯文本查看 复制代码

import requests
from Crypto.Cipher import AES
from Crypto.Util.Padding import pad, unpad
import base64
from bs4 import BeautifulSoup
from concurrent.futures import ThreadPoolExecutor
import os
import time
from tqdm import tqdm


# 定义加密解密类
class Crypter:
    def __init__(self):
        self.key = base64.b64decode('le95G3hnFDJsBE+1/v9eYw==')
        self.iv = base64.b64decode('IvswQFEUdKYf+d1wKpYLTg==')

    def encrypt(self, data):
        data = data.encode('utf-8')
        cipher = AES.new(self.key, AES.MODE_CBC, self.iv)
        ciphertext = cipher.encrypt(pad(data, AES.block_size))
        return base64.b64encode(ciphertext).decode('utf-8')

    def decrypt(self, ciphertext):
        ciphertext = base64.b64decode(ciphertext)
        cipher = AES.new(self.key, AES.MODE_CBC, self.iv)
        data = unpad(cipher.decrypt(ciphertext), AES.block_size)
        return data.decode('utf-8')


# 获取mp3链接
def get_mp3_url(url):
    response = requests.get(url, headers=headers)
    soup = BeautifulSoup(response.text, 'html.parser')
    mp3_url_list = []
    for a in soup.find_all('a', title=True, onclick=True):
        title = a['title']
        if title:
            id = a['onclick'].split("'")[1]
            url = f'http://www.yuetingba.cn/api/app/docs-listen/{id}/ting-with-ef'
            mp3_url = 'http://117.65.51.119:50010' + Crypter().decrypt(requests.get(url, headers=headers).json()['ef'])
            mp3_url_list.append((title, mp3_url))
    return mp3_url_list


 # 下载mp3文件
 def download_mp3(mp3_url_list):
     with ThreadPoolExecutor(max_workers=None) as executor:
         futures = []
         for title, mp3_url in mp3_url_list:
             # print(title,mp3_url)
             filename = f'资治通鉴(白话文)/{title}.mp3'
             if os.path.exists(filename):
                 print(f'{title}.mp3 已存在')
                 continue
             future = executor.submit(download_file, mp3_url, filename)
             futures.append(future)

         # 使用tqdm显示进度条
         for future in tqdm(futures):
             try:
                 future.result()
             except Exception as e:
                 print(f'下载失败: {e}')


# 下载文件的辅助函数
def download_file(url, filename):
    response = requests.get(url, headers=headers)
    with open(filename, 'wb') as f:
        f.write(response.content)
    print(f'{filename} 下载完成')


# 主程序
if __name__ == '__main__':
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:130.0) Gecko/20100101 Firefox/130.0',
    }
    base_url = 'http://www.yuetingba.cn/book/detail/3a0a4394-004b-58cc-bee6-fd01e7787da4/0'
    response = requests.get(base_url, headers=headers)
    soup = BeautifulSoup(response.text, 'html.parser')
    nav_tabs = soup.find('ul', class_='nav nav-tabs').find_all('a')

    #使用多线程下载
    with ThreadPoolExecutor() as executor:
         for a in nav_tabs:
             url = 'http://www.yuetingba.cn' + a['href']
             # print(url)
             mp3_url_list = get_mp3_url(url)
             executor.submit(download_mp3, mp3_url_list)

多线程下载的也很慢

netsome

http://117.65.51.119:50010/myfiles/host/listen/%E5%90%AC%E4%B9%A6%E7%9B%AE%E5%BD%95/%E8%B5%84%E6%B2%BB%E9%80%9A%E9%89%B4(%E7%99%BD%E8%AF%9D%E6%96%87)~%E5%8F%B8%E9%A9%AC%E5%85%89~%E5%B3%BB%E5%AE%87/c36ca68eab2245fc9c42c7519d4612b0.mp3，用猫抓能嗅探到，但是一个个的点和编号有点痛苦。

msmvc

netsome 发表于 2024-9-14 09:12
http://117.65.51.119:50010/myfiles/host/listen/%E5%90%AC%E4%B9%A6%E7%9B%AE%E5%BD%95/%E8%B5%84%E6%B2% ...

是啊，通过浏览器自带的开发者工具也能得到这个IP
一个一个的下载，太麻烦

msmvc

爱飞的猫 发表于 2024-9-14 04:08
[md]
抓包 `http://www.yuetingba.cn/api/app/docs-listen/3a0a487b-f73b-aae9-f268-d501098118b9/ting-wi ...

版主出手就是厉害

anorith

静待楼主写好工具

msmvc

爱飞的猫 发表于 2024-9-14 04:08
[md]
抓包 `http://www.yuetingba.cn/api/app/docs-listen/3a0a487b-f73b-aae9-f268-d501098118b9/ting-wi ...

感谢版主
ef=Ob1B4vtdV6FAXBD3sD3PlI02ie5zefztNrbsg7VpNwRxvQfcxrTgKcUDnTF/weOy8Ut7cNwUVGLgfsY6RQuAfQGnaVEteiPSdZoyBC8E8B5kIPLJnXSxzZZu1LnfRVtcgykcXcuN5J8ZgCwCv1OyQQ==
de=/myfiles/host/listen/听书目录/资治通鉴(白话文)~司马光~峻宇/de3306fd640f42d4ad3feb25b0a36dd2.mp3

就差 如何取得这个ef的值了

msmvc

anorith 发表于 2024-9-14 10:03
静待楼主写好工具

等我啊，晚上回家后写一下

llyaomo

利用猫爪嗅探的话，还要外挂下载器，期待楼主搞个一步到位

msmvc

llyaomo 发表于 2024-9-14 10:22
利用猫爪嗅探的话，还要外挂下载器，期待楼主搞个一步到位

必须整一个，等我