Python爬虫-音乐下载器

仅供参考学习，禁止用于非法用途

目录

1.第三方库准备

安装库
requests selenium webdriver
以及 PhantomJS

2.创建目录

创建主目录Music_Downloader
创建文件 Music_Downloader.py
在同目录下创建包Downloader
在包中创建文件
kugou.py
kuwo.py
wangyiyun.py
QQMusic.py
qianqian.py
类似这样

然后就可以快乐的书写我们的代码了

kugou.py

from urllib.parse import *
import requests
import os
import json

headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36',
    'referer': 'https://www.kugou.com/yy/html/search.html',
    'cookie': 'kg_mid=54466227d384411d3637dfa321b337d6; kg_dfid=1Hvl060iZWHn0cXnq12YuJP5; kg_dfid_collect=d41d8cd98f00b204e9800998ecf8427e; Hm_lvt_aedee6983d4cfc62f509129360d6bb3d=1585209276,1585279988,1585380359; Hm_lpvt_aedee6983d4cfc62f509129360d6bb3d=1585380377',
}


def get_id(url):
    r = requests.get(url, headers=headers).text
    dict = json.loads(r[43:-2])
    data = dict['data']['lists']
    names = []
    hashes = []
    ids = []
    for item in data:
        names.append(item['FileName'].replace('<em>', '').replace('</em>', ''))
        hashes.append(item['FileHash'])
        ids.append(item['AlbumID'])
    return names, hashes, ids


def download_music(name, hash, id):
    url = f'https://wwwapi.kugou.com/yy/index.php?r=play/getdata&callback=jQuery19108859518011228213_1585286241467&hash={hash}&album_id={id}&dfid=1Hvl060iZWHn0cXnq12YuJP5&mid=54466227d384411d3637dfa321b337d6&platid=4&_=1585286241469'
    r = requests.get(url, headers=headers).text
    dict = json.loads(r[41:-2])
    play_url = dict['data']['play_url']
    try:
        with open('%s.mp3' % name, 'wb') as f:
            f.write(requests.get(play_url).content)
        print("%s 下载完成" % name)
    except:
        pass


def Kugou_Downloader():
    music_name = input("输入你要下载的歌名或歌手>>>")
    url = f'https://songsearch.kugou.com/song_search_v2?callback=jQuery1124001117916144825526_1585380377159&keyword={quote(music_name)}&page=1&pagesize=10&userid=-1&clientver=&platform=WebFilter&tag=em&filter=2&iscorrection=1&privilege_filter=0&_=1585380377161'
    if not os.path.exists('。/music'):
        os.mkdir('./music')
    os.chdir('./music')
    print("下载位置:%s" % os.getcwd())
    names = get_id(url)[0]
    hashes = get_id(url)[1]
    ids = get_id(url)[2]
    for i in range(len(names)):
        name = names[i]
        hash = hashes[i]
        id = ids[i]
        download_music(name, hash, id)
    os.chdir('..')

kuwo.py

import requests
from urllib.parse import quote
import json
import os


def get_song_id(url, headers):
    r = json.loads(requests.get(url, headers=headers).text)
    data = r['data']['list']
    singers = []
    names = []
    ids = []
    for item in data:
        singers.append(item['artist'])
        names.append(item['name'])
        ids.append(item['rid'])
    return singers, names, ids


def download_song(singer, name, rid, headers):
    url = f'http://www.kuwo.cn/url?format=mp3&rid={rid}&response=url&type=convert_url3&br=128kmp3&from=web&t=1585283715475&reqId={rid}'
    r = json.loads(requests.get(url, headers=headers).text)
    video_url = r['url']
    file = open('%s %s.mp3' % (name, singer), 'wb')
    file.write(requests.get(video_url).content)
    file.close()
    print("%s %s 下载完成" % (name, singer))


def Kuwo_Downloader():
    music_name = input("输入你要下载的歌名或歌手>>>")
    url = f'http://www.kuwo.cn/api/www/search/searchMusicBykeyWord?key={quote(music_name)}&pn=1&rn=10&reqId=23529c50-6fe2-11ea-99be-470e4c105e4c'
    headers = {
        'Cookie': '_ga=GA1.2.531172689.1585271847; _gid=GA1.2.1879378667.1585271847; gtoken=P4vBP1VaNQmV; gid=b29e452c-a559-42d9-8b94-f0ec588c2f7c; Hm_lvt_cdb524f42f0ce19b169a8071123a4797=1585271847,1585272586,1585272601,1585282753; Hm_lpvt_cdb524f42f0ce19b169a8071123a4797=1585282753; _gat=1; kw_token=MGLE4XIH6LK',
        'csrf': 'MGLE4XIH6LK',
        'Host': 'www.kuwo.cn',
        'Referer': f'http://www.kuwo.cn/search/list?key={quote(music_name)}',
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36',
    }
    if not os.path.exists('./music'):
        os.mkdir('./music')
    os.chdir('./music')
    print("下载位置:%s" % os.getcwd())
    singers = get_song_id(url, headers)[0]
    names = get_song_id(url, headers)[1]
    ids = get_song_id(url, headers)[2]
    for i in range(len(singers)):
        singer = singers[i]
        name = names[i]
        id = ids[i]
        download_song(singer, name, id, headers)
    os.chdir('..')

wangyiyun.py

from selenium import webdriver
from urllib.parse import quote
import os
import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36',
    'Referer': 'https://music.163.com/',
}


class Wangyiyun_Music:
    idlist = []
    namelist = []
    singerlist = []

    def __init__(self):
        self.music_name = input("输入你要下载的歌名或作者>>>")
        self.url = f'https://music.163.com/#/search/m/?s={quote(self.music_name)}&type=1'

    def get_song_id(self):
        self.browser = webdriver.PhantomJS()
        self.browser.get(self.url)
        self.browser.switch_to.frame('g_iframe')
        self.req = self.browser.find_element_by_class_name('srchsongst')
        self.song_id = self.req.find_elements_by_xpath('.//div[@class="item f-cb h-flag  "]/div[2]//a')
        for item in self.song_id:
            Wangyiyun_Music.idlist.append(item.get_attribute('href').split('=')[1])
        self.song_name = self.req.find_elements_by_xpath('.//div[@class="item f-cb h-flag  "]/div[2]//b')
        for item in self.song_name:
            Wangyiyun_Music.namelist.append(item.get_attribute('title'))
        self.song_singer = self.req.find_elements_by_xpath('.//div[@class="item f-cb h-flag  "]/div[4]//a')
        for item in self.song_singer:
            Wangyiyun_Music.singerlist.append(item.text)

    def download_song(self):
        Wangyiyun_Music.get_song_id(self)
        self.base_url = 'http://music.163.com/song/media/outer/url?id={}.mp3'
        self.video_url = []
        for item in Wangyiyun_Music.idlist:
            self.video_url.append(self.base_url.format(item))
        if not os.path.exists('./music'):
            os.mkdir('./music')
        os.chdir('./music')
        print("下载位置:%s" % os.getcwd())
        for i in range(len(self.video_url)):
            try:
                self.name = Wangyiyun_Music.namelist[i]
                self.singer = Wangyiyun_Music.singerlist[i]
                self.video = self.video_url[i]
                file = open('%s %s.mp3' % (self.name, self.singer), 'wb')
                file.write(requests.get(self.video, headers=headers).content)
                file.close()
                print("%s %s  下载成功" % (self.name, self.singer))
            except:
                pass

QQMusic.py

import requests
import os
from urllib.parse import urlencode


def download_QQMusic():
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36',
        'referer': 'https://y.qq.com/portal/search.html',
    }
    music_name = input("输入要下载的歌名或歌手>>>")
    data = {
        'ct': '24',
        'qqmusic_ver': '1298',
        'new_json': '1',
        'remoteplace': 'txt.yqq.song',
        'searchid': '72054918315855694',
        't': '0',
        'aggr': '1',
        'cr': '1',
        'catZhida': '1',
        'lossless': '0',
        'flag_qc': '0',
        'p': '1',
        'n': '10',
        'w': music_name,
        'g_tk_new_20200303': '2057904734',
        'g_tk': '2057904734',
        'loginUin': '1571120423',
        'hostUin': '0',
        'format': 'json',
        'inCharset': 'utf8',
        'outCharset': 'utf - 8',
        'notice': '0',
        'platform': 'yqq.json',
        'needNewCode': '0',
    }
    base_url = 'https://c.y.qq.com/soso/fcgi-bin/client_search_cp?' + urlencode(data)
    r = requests.get(base_url, headers=headers).json()
    song_list = r['data']['song']['list']
    names = []
    singers = []
    midlist = []
    for item in song_list:
        names.append(item['title'])
        midlist.append(item['mid'])
        singers.append(item['singer'][0]['name'])
    # ------------------------------------------------------------------------------------------------------
    purl_list = []
    for mid in midlist:
        url = f'https://u.y.qq.com/cgi-bin/musicu.fcg?-=getplaysongvkey6455258874010792&g_tk=2057904734&loginUin=1571120423&hostUin=0&format=json&inCharset=utf8&outCharset=utf-8&notice=0&platform=yqq.json&needNewCode=0&data=%7B%22req%22%3A%7B%22module%22%3A%22CDN.SrfCdnDispatchServer%22%2C%22method%22%3A%22GetCdnDispatch%22%2C%22param%22%3A%7B%22guid%22%3A%225916370708%22%2C%22calltype%22%3A0%2C%22userip%22%3A%22%22%7D%7D%2C%22req_0%22%3A%7B%22module%22%3A%22vkey.GetVkeyServer%22%2C%22method%22%3A%22CgiGetVkey%22%2C%22param%22%3A%7B%22guid%22%3A%225916370708%22%2C%22songmid%22%3A%5B%22{mid}%22%5D%2C%22songtype%22%3A%5B0%5D%2C%22uin%22%3A%221571120423%22%2C%22loginflag%22%3A1%2C%22platform%22%3A%2220%22%7D%7D%2C%22comm%22%3A%7B%22uin%22%3A1571120423%2C%22format%22%3A%22json%22%2C%22ct%22%3A24%2C%22cv%22%3A0%7D%7D'
        response = requests.get(url, headers=headers).json()
        s = response['req_0']['data']['midurlinfo'][0]['purl']
        purl_list.append(s)
    play_url = ['https://isure.stream.qqmusic.qq.com/' + x for x in purl_list]
    if not os.path.exists('./music'):
        os.mkdir('./music')
    os.chdir('./music')
    print("下载位置:%s" % os.getcwd())
    for i in range(len(names)):
        try:
            name = names[i]
            singer = singers[i]
            url = play_url[i]
            file = open('%s %s.mp3' % (name, singer), 'wb')
            file.write(requests.get(url, headers=headers).content)
            file.close()
            print("%s %s  保存成功" % (name, singer))
        except:
            pass
    os.chdir('..')

qianqian.py

import requests
import re
import json
from urllib.parse import *
import os


def get_id(music_name):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36',
        'Host': 'music.taihe.com',
        'Referer': 'http://music.taihe.com/',
        'Cookie': 'BAIDUID=E23486F8F8E78C1989B3691059C374AA:FG=1; u_lo=0; u_id=; u_t=; log_sid=1585711800186E23486F8F8E78C1989B3691059C374AA; Hm_lvt_d0ad46e4afeacf34cd12de4c9b553aa6=1585278402,1585278908,1585711802; tracesrc=-1%7C%7C-1; __qianqian_pop_tt=4; Hm_lpvt_d0ad46e4afeacf34cd12de4c9b553aa6=1585712626',
    }
    url = f'http://music.taihe.com/search?key={quote(music_name)}'
    html = requests.get(url, headers=headers).text
    return re.findall(re.compile(r'\{ "id": "(.*?)" }'), html)


def download(id):
    url = f'http://musicapi.taihe.com/v1/restserver/ting?method=baidu.ting.song.playAAC&format=jsonp&callback=jQuery172036047943074942945_1585711904941&songid={id}&from=web&_=1585711907963'
    r = requests.get(url).text
    data=r[r.index('{'):-2]
    try:
        data=json.loads(data)
        name = data['songinfo']['title']
        singer = data['songinfo']['compose']
        play_url = data['bitrate']['file_link']
        with open("%s %s.mp3"%(name,singer),'wb') as f:
            f.write(requests.get(play_url).content)
        print("%s %s 保存完成"%(name,singer))
    except:
        pass


def qianqian_download():
    if not os.path.exists('./music'):
        os.mkdir('./music')
    os.chdir('./music')
    music_name = input("输入你要下载的歌名或歌手>>>")
    print("下载地址 %s"%os.getcwd())
    for item in get_id(music_name):
        download(item)
    os.chdir('..')

Music_Dpwnloader.py

import Downloader.kugou
import Downloader.kuwo
import Downloader.wangyiyun
import Downloader.QQMusic
import Downloader.qianqian

def main():
    while True:
        print('''\n请选择下载方式
1:酷狗音乐;
2:酷我音乐;
3:网易云音乐;
4:QQ音乐;
5:千千音乐
(输入q退出程序)''')
        guess = input("\n请输入下载器(填序号)>>>")
        if guess == '1':
            Downloader.kugou.Kugou_Downloader()
            go = input("继续下载(y/n)").upper()
            if go == 'Y' or go == 'YES':
                continue
            else:
                exit("退出")
        elif guess == '2':
            Downloader.kuwo.Kuwo_Downloader()
            go = input("继续下载(y/n)").upper()
            if go == 'Y' or go == 'YES':
                continue
            else:
                exit("退出")
        elif guess == '3':
            wangyiyunmusic = Downloader.wangyiyun.Wangyiyun_Music()
            wangyiyunmusic.download_song()
            go = input("继续下载(y/n)").upper()
            if go == 'Y' or go == 'YES':
                continue
            else:
                exit("退出")
        elif guess == '4':
            Downloader.QQMusic.download_QQMusic()
            go = input("继续下载(y/n)").upper()
            if go == 'Y' or go == 'YES':
                continue
            else:
                exit("退出")
        elif guess == '5':
            Downloader.qianqian.qianqian_download()
            go = input("继续下载(y/n)").upper()
            if go == 'Y' or go == 'YES':
                continue
            else:
                exit("退出")
        else:
            exit()


if __name__ == '__main__':
    print("*" * 21 + "音乐下载器" + "*" * 21)
    main()

本人小白，写的不好请见谅