python3 爬去QQ音樂

import requests
import re
import json
import os



def get_name(singer):
    url = 'https://c.y.qq.com/soso/fcgi-bin/client_search_cp'
    params = {
        'catZhida': '1',
        'w': singer,
    }
    headers = {
        'referer': 'https://y.qq.com/portal/search.html',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36'
    }
    html = requests.get(url,headers=headers,params=params).text
    content = re.compile('callback\((.*)\)').findall(html)[0]
    content = json.loads(content)
    data = content.get('data')
    song = data.get('song')
    lists = song.get('list')
    name = []
    for list in lists:
        singer = list.get('singer')[0].get('mid')
        name.append(singer)
    name = name[0]
    return name

def get_html(name,singer):
    url = 'https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg'
    params = {
        'singermid': name,
        'order': 'listen',
        'begin': '0',
        'num': '30',
    }
    headers = {
        'referer': 'https://y.qq.com/n/yqq/singer/003aQYLo2x8izP.html',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36'
    }
    html = requests.get(url,headers=headers,params=params).text
    return html


def get_music(vkey,songname,filename,singer):
    if vkey and songname:
        url3 = 'http://dl.stream.qqmusic.qq.com/' + filename + '?vkey=' + vkey + '&guid=7133372870&uin=0&fromtag=66'

        headers = {
            'referer': 'https://y.qq.com/n/yqq/singer/003aQYLo2x8izP.html',
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36'
        }
        music = requests.get(url3,headers=headers).content
        dir = singer
        if  not os.path.exists(dir):
            os.mkdir(dir)
        with open(dir+'/'+songname+'.m4a','wb') as f:
            f.write(music)
        print(songname,'__',singer)

def get_vkey(strMediaMid,songmid,songname,singer):
    if strMediaMid and songmid and songname :
        url2 = 'https://c.y.qq.com/base/fcgi-bin/fcg_music_express_mobile3.fcg'
        params = {
            'g_tk': '5381',
            'jsonpCallback': 'MusicJsonCallback8571665793949388',
            'loginUin': '0',
            'hostUin': '0',
            'format': 'json',
            'inCharset': 'utf8',
            'outCharset': 'utf-8',
            'notice': '0',
            'platform': 'yqq',
            'needNewCode': '0',
            'cid': '205361747',
            'callback': 'MusicJsonCallback8571665793949388',
            'uin': '0',
            'songmid': songmid,
            'filename': 'C400'+ strMediaMid + '.m4a',
            'guid': '7133372870'
        }
        headers = {
            'referer': 'https://y.qq.com/portal/player.html',
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36'
        }
        detail_html = requests.get(url2,headers=headers,params=params).text
        vkey_disc = re.compile('MusicJsonCallback8571665793949388\((.*?)\)').findall(detail_html)[0]
        vkey_disc = json.loads(vkey_disc)

        data = vkey_disc['data']
        items = data.get('items')[0]
        vkey = items.get('vkey')
        get_music(vkey,songname,'C400'+ strMediaMid + '.m4a',singer)


def get_list(detail_html,singer):
    if detail_html:
        lists = re.compile('data\":{\"list\":(.*?),\"singer_id',re.S).findall(detail_html)[0]
        datas = json.loads(lists)
        for data in datas:
            musicData = data.get('musicData')
            strMediaMid = musicData.get('strMediaMid')
            songmid = musicData.get('songmid')
            songname = musicData.get('songname')
            get_vkey(strMediaMid,songmid,songname,singer)



def main():
    singer = input('請輸入您想要下載的歌手：')
    name = get_name(singer)
    detail_html = get_html(name,singer)
    get_list(detail_html,singer)

if __name__ == '__main__':
    main()

有些地方代碼有些冗余，還可以再改進  但是費了些功夫終於爬出的效果 確實想要快點編輯出來  按耐不住小激動  這應該就是敲代碼的樂趣

 

 

當播放一個音樂的時候  在Elements中 可以看到音樂的鏈接  當然是通過js 和 css 加載過的   但是 可以用逆向思維進行參數的找尋  

http://dl.stream.qqmusic.qq.com/C4000032qfIn1Tzdbq.m4a？vkey=80525033DD719DAB87C0CEC7B4F9F40D8755982D3A495E3BA0810E50A89668A2AFD61C4C19876FD0FB68932DED89B340AE9F4F464D82DC15&guid=7133372870&uin=0&fromtag=66

發現  vkey 是一個很重要的參數  所以就先去翻一翻網頁查一下vkey在哪   

 

 經發現 在同播放頁面的JS中   但是如果想獲得vkey 就需要訪問這個對應的URL  也要找到相應的參數

 

 

標紅箭頭的是一直在變化而且沒有不行的參數  

 

 所以將繼續往里使勁挖！

 

 

 

 目前處於列表頁  發現參數已經浮現

但發現第一個紅箭頭是歌手的意思  被不知道用了什么樣的格式換了一種形式  因為后續還想通過段小亂碼找到每個歌手所對應的歌曲 所以 還是找到每個歌手所對應的小亂碼比較好 

 

 

 

 

 找到了！！！

但是 寫代碼的話 要用正向思維來寫  Year!