唱鸭作品音频下载

原创文｜Space9

K歌自嗨让我们嗨得更自由

需求场景

1. 我们自唱的音频想保留音频文件，分发给朋友或者保存到别的地方
2. 我们想将自唱的音频作为视频背景音乐或者二次编辑音频文件
3. 我们注销账号时，主流平台没有提供打包下载的功能或者下载自己的K歌有某些限制

实现方式（仅以唱鸭为例）

1. 获取分享页面数据
   我们可以搜索发现id名为“NEXT_DATA”的script标签
2. 解析json数据，获取我们需要的下载链接及音频名称
3. 通过调用aria2c.exe来完成我们的下载

源码

Amusic.py

import base64
import json
import random
import re
import time
from urllib import parse

import requests


# 解析jsonp数据格式为json
def loads_jsonp(_jsonp):
    try:
        return json.loads(re.match(".*?({.*}).*", _jsonp, re.S).group(1))
    except:
        raise ValueError('Invalid Input')


def get_xima_music_parm(music_url):
    print("开始获取喜马拉雅的参数")
    # 将%xx转义符替换为它们的单字符等效项
    url_data = parse.unquote(music_url)

    # url结果
    result = parse.urlparse(url_data)
    print(result)

    song_id = result.path.rsplit('/', 1)[1]
    print(song_id)

    url = "https://m.ximalaya.com/tracks/" + song_id + ".json"

    headers = {
   
        'Host': "m.ximalaya.com",
        'Accept-Encoding': "gzip, deflate",
        'Connection': "keep-alive",
        'cache-control': "no-cache"
    }

    response = requests.request("GET", url, headers=headers)
    print(response.text)

    music_data = json.loads(response.text)
    # 文件名不能包含下列任何字符：\/:*?"<>|       英文字符
    music_name = re.sub(r'[\\/:*?"<>|\r\n]+', "", music_data["title"])
    print(music_name)
    play_path_64 = music_data["play_path_64"]

    music_parm = [music_name, play_path_64]
    return music_parm


def get_changba_music_parm(music_url):
    print("开始获取唱吧的参数")
    html = requests.get(music_url).text

    is_video_res = re.search(r'&isvideo=(?P<is_video>[\s\S]*?)\'', html)
    is_video = is_video_res.groupdict()['is_video']

    if is_video == "0":
        title_res = re.search(r'<div class="title">(?P<title>[\s\S]*?)</div>', html)
        origin_name = title_res.groupdict()['title']
        if origin_name == " ":
            music_name = "changba" + str(int(round(time.time() * 1000)))
            print(music_name)
        else:
            # 文件名不能包含下列任何字符：\/:*?"<>|       英文字符
            music_name = re.sub(r'[\\/:*?"<>|\r\n]+', "", origin_name)
            print(music_name)
        sub_url_res = re.search(r'var a="http(?P<sub_url>[\s\S]*?)",', html)
        sub_url = sub_url_res.groupdict()['sub_url']
        mp3_url = "http" + sub_url
    else:
        sub_url_res = re.search(r'video_url: \'(?P<sub_url>[\s\S]*?)\',', html)
        sub_url = sub_url_res.groupdict()['sub_url']
        str_url = base64.b64decode(sub_url).decode("utf-8")
        mp3_url = "http:" + str_url

        music_name = "changba" + str(int(round(time.time() * 1000)))
        print(music_name)

    music_parm = [music_name, mp3_url]
    return music_parm


# （已发现缺陷）打印日志不全，文件头过长，不过文件转换没有问题
def get_lizhi_music_parm(music_url):
    print("开始获取荔枝的参数")
    # 将%xx转义符替换为它们的单字符等效项
    url_data = parse.unquote(music_url)

    # url结果
    result = parse.urlparse(url_data)
    print(result)

    song_id = result.path.rsplit('/', 1)[1]
    print(song_id)

    url = "https://m.lizhi.fm/vodapi/voice/info/" + song_id

    headers = {
   
        'Host': "m.lizhi.fm",
        'Accept-Encoding': "gzip, deflate",
        'Connection': "keep-alive",
        'cache-control': "no-cache"
    }

    response = requests.request("GET", url, headers=headers)
    print(response.text)

    music_data = json.loads(response.text)["data"]
    # 文件名不能包含下列任何字符：\/:*?"<>|       英文字符
    music_name = re.sub(r'[\\/:*?"<>|\r\n]+', "", music_data["userVoice"]["voiceInfo"]["name"])
    print(music_name)
    track_url = music_data["userVoice"]["voicePlayProperty"]["trackUrl"]

    music_parm = [music_name, track_url]
    return music_parm


def get_changya_music_parm(music_url):
    print("开始获取唱鸭的参数")
    headers = {
   
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36'
    }
    html = requests.request("GET", music_url, headers=headers).text

    song_json_res = re.search(
        r'<script id="__NEXT_DATA__" type="application/json" crossorigin="anonymous">(?P<song_json>[\s\S]*?)</script>',
        html)
    song_data = song_json_res.groupdict()['song_json'].strip()
    music_data = json.loads(song_data)["props"]["pageProps"]["clip"]

    # 文件名不能包含下列任何字符：\/:*?"<>|       英文字符
    music_name = re.sub(r'[\\/:*?"<>|\r\n]+', "", music_data["songName"])
    print(music_name)
    mp3_url = music_data["audioSrc"]

    music_parm = [music_name, mp3_url]
    return music_parm


def get_changya2_music_parm(music_url):
    print("开始获取唱鸭2的参数")
    headers = {
   
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36'
    }
    html = requests.request("GET", music_url, headers=headers).text

    song_json_res = re.search(
        r'<script id="__NEXT_DATA__" type="application/json" crossorigin="anonymous">(?P<song_json>[\s\S]*?)</script>',
        html)
    song_data = song_json_res.groupdict()['song_json'].strip()
    mp4_url = json.loads(song_data)["props"]["pageProps"]["url"]

    music_name = "changya" + str(int(round(time.time() * 1000)))
    print(music_name)

    music_parm = [music_name, mp4_url]
    return music_parm


def get_kugouchang_music_parm(music_url):
    print("开始获取酷狗唱唱和斗歌和酷狗K歌的参数")
    headers = {
   
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36'
    }
    res = requests.request("GET", music_url