AudioApp/biliAudio/getAudio/download.py

from random import choice
import json
from lxml import etree
import requests
import re
import os
import time
from pathlib import Path
import subprocess

# from pydub import AudioSegment

def get_user_agent():
    user_agents = [
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
        "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
        "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
        "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
        "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
        "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
        "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
        "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
        "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
        "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
        "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
        "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
        "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
        "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
        "MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "Mozilla/5.0 (iPhone; CPU iPhone OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1",
        "Mozilla/5.0 (Linux; Android 5.1.1; Nexus 6 Build/LYZ28E) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.23 Mobile Safari/537.36",
        "Mozilla/5.0 (iPod; U; CPU iPhone OS 2_1 like Mac OS X; ja-jp) AppleWebKit/525.18.1 (KHTML, like Gecko) Version/3.1.1 Mobile/5F137 Safari/525.20",
        "Mozilla/5.0 (Linux;u;Android 4.2.2;zh-cn;) AppleWebKit/534.46 (KHTML,like Gecko) Version/5.1 Mobile Safari/10600.6.3 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
        "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html）"

    ]
    return choice(user_agents)

def audio_download(aid):
    BASE_DIR = Path(__file__).resolve().parent
    headers = {
        'user-agent':get_user_agent(),
        'referer':'https://www.bilibili.com/'
    }
    file_list = os.listdir(os.path.join(BASE_DIR,'download'))
    os.chdir(os.path.join(BASE_DIR,'download'))
    if len(file_list) > 5:
        latest = [0,file_list[0]]
        for f in file_list:
            create_time = os.stat(f).st_ctime
            if create_time < latest[0]:
                latest[0] = create_time
                latest[1] = f
        os.system('rm \"{}\"'.format(f))
    for i in range(5):
        try:
            response = requests.get('https://www.bilibili.com/video/'+aid,headers=headers)
            if response.status_code == 200:
                html = etree.HTML(response.text)
                # print('获取成功!')
                title_lst = html.xpath('//title[@data-vue-meta="true"]/text()')
                title = title_lst[0]
                str = title
                title = re.sub('/', '|', str)
                title = re.sub('\"','\'',title)
                title = re.sub('#','No.',title)

                print(title)
                pattern = '<script>window.__playinfo__=(.*?)</script>'
                info_text = json.loads(re.findall(string=response.text, pattern=pattern)[0])

                audio_url_list = []
                audio_url_list.append(info_text['data']['dash']['audio'][0]['baseUrl'])
                audio_url_list.append(info_text['data']['dash']['audio'][0]['base_url'])
                audio_url_list.extend(info_text['data']['dash']['audio'][0]['backupUrl'])
                # print('url获取成功')
                break
        except Exception as e:
            print(e)
        time.sleep(0.5)
    else:
        return "FAIL"

    if os.path.exists(os.path.join(BASE_DIR,('download/' + title + '.mp3'))):
        print('已存在')
        return (title + '.mp3')

    for audio_url in audio_url_list:
        audio_content = requests.get(audio_url, headers=headers)
        if audio_content.status_code == 200:
            print('开始下载，下载中...')
            download_path = os.path.join(BASE_DIR,'download')
            temp_path = os.path.join(BASE_DIR,'temp')
            os.chdir(temp_path)
            with open('{}.m4s'.format(title), 'wb') as f:
                f.write(audio_content.content)
                f.flush()
            mp3file = title + '.mp3'
            m4sfile = title + '.m4s'
            # subprocess.run(['ffmpeg', '-i', m4sfile, '-vn', '-ar', '44100', '-ac', '2', '-ab', '192k', '-f', 'mp3', download_path+'/'+mp3file],stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
            os.system('ffmpeg -i \"{}\" -vn -ar 44100 -ac 2 -ab 192k -f mp3 \"{}\"'.format(m4sfile,download_path+'/'+mp3file))
            # sound = AudioSegment.from_file(title + '.m4s', format="m4s")
            # sound.export(title + '.mp3', format="mp3")
            # os.rename(mp3file,download_path + '/' + mp3file)
            os.chdir(temp_path)
            os.system('rm \"{}\"'.format(m4sfile))
            os.chdir(download_path)
            print(title, '下载完成！')
            return (mp3file)
        else:
            print("FAIL!!!")

def get_urls(bv):
    headers = {
        'user-agent':get_user_agent(),
        'referer':'https://www.bilibili.com/'
    }
    url = 'https://www.bilibili.com/video/' + bv + '/?p=1'
    for count in range(3):
        try:
            response = requests.get(url=url,headers=headers)
            j = re.findall('window\.__INITIAL_STATE__=\{(.*?)\};\(function\(\)',response.text)[0]
            j = "{" + j + "}"
            j = json.loads(j)
            # print(j)
            # print(j['videoData'])
            # print(j['videoData']['pages'])
            namelist = []
            pagelist = []
            urllist = []
            url_list = j['videoData']['pages']
            for i in url_list:
                pagelist.append(i['page'])
                namelist.append(i['part'])
                urllist.append('https://www.bilibili.com/video/{}/?p={}'.format(bv,i['page']))
            ziplist = zip(pagelist,namelist,urllist)
            return ziplist
        except Exception as e:
            print(e)
            time.sleep(0.5)
    else:
        return "FAIL"