python爬虫笔记七： 酷狗查询js分析

分析网址：酷狗音乐 - 就是歌多

        F12网络分析查询，难点为下面图中的红色框，特别是 signature 的获取，调试了一下，原先MD5的方式已改

播放

 前面查询页面查询关键字：

 调试js代码

 断点运行，获取参数

参数  o的详细内容

 再次跟踪断点之前参数获取代码，发现只有一个时间戳，其它都是固定

 

源代码

import hashlib #md5, sha1, sha224, sha256, sha384, and sha512
import requests
import re
import time
import json
import pandas as pd

class Public_kugo():
    def __init__(self):
        #这个地方替换成自已的Cooike，其中的kg_mid与kg_dfid在后面Head中要用到，单独拿出来
        self.kg_mid = '92f43c1ca98aeef7f805654bc16b687e'
        self.kg_dfid = '10GOa11RqXIo2jvJbD3jt3BN'
        self.url = "https://complexsearch.kugou.com/v2/search/song"  #目标URL
        self.url2 = "https://wwwapi.kugou.com/yy/index.php"
        self.head = {
            'accept': '*/*',
            'accept-encoding': 'gzip, deflate, br',
            'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8',
            'cookie': 'kg_mid='+self.kg_mid+'; kg_dfid='+self.kg_dfid+'; kg_dfid_collect=d41d8cd98f00b204e9800998ecf8427e; Hm_lvt_aedee6983d4cfc62f509129360d6bb3d=1629682120; Hm_lpvt_aedee6983d4cfc62f509129360d6bb3d=1629683486',
            'referer': 'https://www.kugou.com/',
            'sec-ch-ua': '" Not;A Brand";v="99", "Google Chrome";v="91", "Chromium";v="91"',
            'sec-ch-ua-mobile': '?0',
            'sec-fetch-dest': 'script',
            'sec-fetch-mode': 'no-cors',
            'sec-fetch-site': 'same-site',
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.106 Safari/537.36',
        }
        self.data = ["NVPh5oo715z5DIWAeQlhMDsWXXQV4hwt", "bitrate=0", "callback=callback123", "clienttime=1629688889293"
            , "clientver=2000", "dfid=-", "inputtype=0", "iscorrection=1" , "isfuzzy=0"
            , "keyword=学猫叫", "mid=1629688889293", "page=1", "pagesize=30"
            , "platform=WebFilter", "privilege_filter=0", "srcappid=2919", "tag=em", "userid=0"
            , "uuid=1629688889293", "NVPh5oo715z5DIWAeQlhMDsWXXQV4hwt"]

        self.params={
            'callback': 'callback123',
            'keyword': '学猫叫',
            'page': '1',
            'pagesize': '30',
            'bitrate': '0',
            'isfuzzy': '0',
            'tag': 'em',
            'inputtype': '0',
            'platform': 'WebFilter',
            'userid': '0',
            'clientver': '2000',
            'iscorrection': '1',
            'privilege_filter': '0',
            'srcappid': '2919',
            'clienttime': '1629688889293',
            'mid': '1629688889293',
            'uuid': '1629688889293',
            'dfid': '-',
            'signature': 'A819E0B497883BF0435D2D26667B5B5F'
        }
        self.params2 = {
            'r': 'play/getdata',
            'callback': 'jQuery191017104544130952526_1629693532392',
            'hash': '2BE99967C762BC56E2DF23682C755FE8',
            'dfid': self.kg_dfid,
            'mid': self.kg_mid,
            'platid': '4',
            'album_id': '',
            '_': '1629693532394',
        }
    def gen_md5(self,row):
        byte_row = row.encode("utf8", "ignore")
        md5 = hashlib.md5()
        md5.update(byte_row)
        return md5.hexdigest().upper()


    def gettime(self):
        return '%d' % (time.time() * 1000)


    def Get_html(self,val):
        time=self.gettime()
        self.data[3] = 'clienttime=' + time
        self.data[9]='keyword='+val
        self.data[10] = 'mid=' + time
        self.data[18] = 'uuid=' + time
        self.params['keyword']=val
        self.params['clienttime']=time
        self.params['mid']=time
        self.params['uuid']=time
        self.params['signature']=self.gen_md5(''.join(self.data))

        response= requests.get(self.url, params=self.params, headers=self.head).content.decode('utf-8')
        # 获取json内容
        response = re.sub(r'callback123\((.*)\)$', r'\1', response)
        return json.loads(response)['data']['lists']


    def Get_html2(self,id,hs):
        time = self.gettime()
        self.params2['callback']='jQuery191017104544130952526_'+time
        self.params2['hash'] = hs
        self.params2['album_id'] = id
        self.params2['_'] = time
        response= requests.get(self.url2, params=self.params2, headers=self.head).content.decode('utf-8')
        # 获取json内容
        response = re.sub(r'jQuery.*_'+time+'\((.*)\);$', r'\1', response)
        song=json.loads(response)['data']
        if(isinstance(song,dict)):
            if('play_url' in 'play_url' in song.keys() and 'audio_name' in song.keys()):
                if (song['play_url']!=''):
                    return (song['audio_name'],song['play_url'])


    def Search(self,val):
        songs= self.Get_html(val)
        i=0
        for o in songs:
            name = re.sub(r'<em>(.*?)</em>',r'\1', o['FileName'])#OriSongName
            id=o['AlbumID']
            #hs=o['FileHash']
            hs=o['HQFileHash']
            # hs=o['MvHash']
            # hs=o['SQFileHash']
            retsong=self.Get_html2(id,hs)
            if(pd.isnull(retsong)==False):
                i = i + 1
                print(i,retsong[0],retsong[1])
            #print(i,name,id,hs)


if __name__ == '__main__':
    cx=Public_kugo()
    cx.Search('好人一生平安')

结果