Python爬取酷狗MP3音频的步骤


Posted in Python onFebruary 26, 2021

分析问题

音频url

点入某个音乐的播放界面,通过F12-Network,分析数据,可以看到有一个index.php?..返回数据中有一个play_url,打开后正是我们需要的音频。

查看该url的headers,其params参数如下,通过反复不同的几次尝试,得知r、callback、dfid、mid、platid这几项不变,而通过初步的requests尝试,发现最后一项'_'可有可无,改变的只有hash和album_id两项。

r: play/getdata
callback: jQuery1910861615852090795_1612578519454
hash: EF0DA656831F08B1FD2CB855BC38ED2C
dfid: 0Q0Clh1IcZaG3ey1J70RaTiL
mid: b6cf66837b18642cc269390b066649dc
platid: 4
album_id: 41669581
_: 1612578519455

搜索url

得知改变的只有两项后,那就容易多了,在搜索歌曲界面Network,发现song?...该url返回值中有hash和album_id存在,我们之后只用搜索结果第一项(一般要搜的歌曲排名第一)。

同样分析其params参数,改变的只有keyword、signature、clienttime、mid、uuid。后三者可以比较容易看出其为毫秒级时间戳(13位),keyword也挺容易明白,signature哪里找呢?通过全局搜索signature,发现有一个js文件中含有该关键词。

callback: callback123
keyword: 花海
page: 1
pagesize: 30
bitrate: 0
isfuzzy: 0
tag: em
inputtype: 0
platform: WebFilter
userid: -1
clientver: 2000
iscorrection: 1
privilege_filter: 0
srcappid: 2919
clienttime: 1612579100435
mid: 1612579100435
uuid: 1612579100435
dfid: -
signature: 472F60133C23184CAFC5005350C90229

JS

找到的js代码如下

"undefined" == typeof faultylabs && (faultylabs = {}),
faultylabs.MD5 = function(a) {
 function b(a) {
  var b = (a >>> 0).toString(16);
  return "00000000".substr(0, 8 - b.length) + b
 }
 function c(a) {
  for (var b = [], c = 0; c < a.length; c++)
   b = b.concat(k(a[c]));
  return b
 }
 function d(a) {
  for (var b = [], c = 0; 8 > c; c++)
   b.push(255 & a),
   a >>>= 8;
  return b
 }
 function e(a, b) {
  return a << b & 4294967295 | a >>> 32 - b
 }
 function f(a, b, c) {
  return a & b | ~a & c
 }
 function g(a, b, c) {
  return c & a | ~c & b
 }
 function h(a, b, c) {
  return a ^ b ^ c
 }
 function i(a, b, c) {
  return b ^ (a | ~c)
 }
 function j(a, b) {
  return a[b + 3] << 24 | a[b + 2] << 16 | a[b + 1] << 8 | a[b]
 }
 function k(a) {
  for (var b = [], c = 0; c < a.length; c++)
   if (a.charCodeAt(c) <= 127)
    b.push(a.charCodeAt(c));
   else
    for (var d = encodeURIComponent(a.charAt(c)).substr(1).split("%"), e = 0; e < d.length; e++)
     b.push(parseInt(d[e], 16));
  return b
 }
 function l() {
  for (var a = "", c = 0, d = 0, e = 3; e >= 0; e--)
   d = arguments[e],
   c = 255 & d,
   d >>>= 8,
   c <<= 8,
   c |= 255 & d,
   d >>>= 8,
   c <<= 8,
   c |= 255 & d,
   d >>>= 8,
   c <<= 8,
   c |= d,
   a += b(c);
  return a
 }
 function m(a) {
  for (var b = new Array(a.length), c = 0; c < a.length; c++)
   b[c] = a[c];
  return b
 }
 function n(a, b) {
  return 4294967295 & a + b
 }
 function o() {
  function a(a, b, c, d) {
   var f = v;
   v = u,
   u = t,
   t = n(t, e(n(s, n(a, n(b, c))), d)),
   s = f
  }
  var b = p.length;
  p.push(128);
  var c = p.length % 64;
  if (c > 56) {
   for (var k = 0; 64 - c > k; k++)
    p.push(0);
   c = p.length % 64
  }
  for (k = 0; 56 - c > k; k++)
   p.push(0);
  p = p.concat(d(8 * b));
  var m = 1732584193
   , o = 4023233417
   , q = 2562383102
   , r = 271733878
   , s = 0
   , t = 0
   , u = 0
   , v = 0;
  for (k = 0; k < p.length / 64; k++) {
   s = m,
   t = o,
   u = q,
   v = r;
   var w = 64 * k;
   a(f(t, u, v), 3614090360, j(p, w), 7),
   a(f(t, u, v), 3905402710, j(p, w + 4), 12),
   a(f(t, u, v), 606105819, j(p, w + 8), 17),
   a(f(t, u, v), 3250441966, j(p, w + 12), 22),
   a(f(t, u, v), 4118548399, j(p, w + 16), 7),
   a(f(t, u, v), 1200080426, j(p, w + 20), 12),
   a(f(t, u, v), 2821735955, j(p, w + 24), 17),
   a(f(t, u, v), 4249261313, j(p, w + 28), 22),
   a(f(t, u, v), 1770035416, j(p, w + 32), 7),
   a(f(t, u, v), 2336552879, j(p, w + 36), 12),
   a(f(t, u, v), 4294925233, j(p, w + 40), 17),
   a(f(t, u, v), 2304563134, j(p, w + 44), 22),
   a(f(t, u, v), 1804603682, j(p, w + 48), 7),
   a(f(t, u, v), 4254626195, j(p, w + 52), 12),
   a(f(t, u, v), 2792965006, j(p, w + 56), 17),
   a(f(t, u, v), 1236535329, j(p, w + 60), 22),
   a(g(t, u, v), 4129170786, j(p, w + 4), 5),
   a(g(t, u, v), 3225465664, j(p, w + 24), 9),
   a(g(t, u, v), 643717713, j(p, w + 44), 14),
   a(g(t, u, v), 3921069994, j(p, w), 20),
   a(g(t, u, v), 3593408605, j(p, w + 20), 5),
   a(g(t, u, v), 38016083, j(p, w + 40), 9),
   a(g(t, u, v), 3634488961, j(p, w + 60), 14),
   a(g(t, u, v), 3889429448, j(p, w + 16), 20),
   a(g(t, u, v), 568446438, j(p, w + 36), 5),
   a(g(t, u, v), 3275163606, j(p, w + 56), 9),
   a(g(t, u, v), 4107603335, j(p, w + 12), 14),
   a(g(t, u, v), 1163531501, j(p, w + 32), 20),
   a(g(t, u, v), 2850285829, j(p, w + 52), 5),
   a(g(t, u, v), 4243563512, j(p, w + 8), 9),
   a(g(t, u, v), 1735328473, j(p, w + 28), 14),
   a(g(t, u, v), 2368359562, j(p, w + 48), 20),
   a(h(t, u, v), 4294588738, j(p, w + 20), 4),
   a(h(t, u, v), 2272392833, j(p, w + 32), 11),
   a(h(t, u, v), 1839030562, j(p, w + 44), 16),
   a(h(t, u, v), 4259657740, j(p, w + 56), 23),
   a(h(t, u, v), 2763975236, j(p, w + 4), 4),
   a(h(t, u, v), 1272893353, j(p, w + 16), 11),
   a(h(t, u, v), 4139469664, j(p, w + 28), 16),
   a(h(t, u, v), 3200236656, j(p, w + 40), 23),
   a(h(t, u, v), 681279174, j(p, w + 52), 4),
   a(h(t, u, v), 3936430074, j(p, w), 11),
   a(h(t, u, v), 3572445317, j(p, w + 12), 16),
   a(h(t, u, v), 76029189, j(p, w + 24), 23),
   a(h(t, u, v), 3654602809, j(p, w + 36), 4),
   a(h(t, u, v), 3873151461, j(p, w + 48), 11),
   a(h(t, u, v), 530742520, j(p, w + 60), 16),
   a(h(t, u, v), 3299628645, j(p, w + 8), 23),
   a(i(t, u, v), 4096336452, j(p, w), 6),
   a(i(t, u, v), 1126891415, j(p, w + 28), 10),
   a(i(t, u, v), 2878612391, j(p, w + 56), 15),
   a(i(t, u, v), 4237533241, j(p, w + 20), 21),
   a(i(t, u, v), 1700485571, j(p, w + 48), 6),
   a(i(t, u, v), 2399980690, j(p, w + 12), 10),
   a(i(t, u, v), 4293915773, j(p, w + 40), 15),
   a(i(t, u, v), 2240044497, j(p, w + 4), 21),
   a(i(t, u, v), 1873313359, j(p, w + 32), 6),
   a(i(t, u, v), 4264355552, j(p, w + 60), 10),
   a(i(t, u, v), 2734768916, j(p, w + 24), 15),
   a(i(t, u, v), 1309151649, j(p, w + 52), 21),
   a(i(t, u, v), 4149444226, j(p, w + 16), 6),
   a(i(t, u, v), 3174756917, j(p, w + 44), 10),
   a(i(t, u, v), 718787259, j(p, w + 8), 15),
   a(i(t, u, v), 3951481745, j(p, w + 36), 21),
   m = n(m, s),
   o = n(o, t),
   q = n(q, u),
   r = n(r, v)
  }
  return l(r, q, o, m).toUpperCase()
 }
 var p = null
  , q = null;
 return "string" == typeof a ? p = k(a) : a.constructor == Array ? 0 === a.length ? p = a : "string" == typeof a[0] ? p = c(a) : "number" == typeof a[0] ? p = a : q = typeof a[0] : "undefined" != typeof ArrayBuffer ? a instanceof ArrayBuffer ? p = m(new Uint8Array(a)) : a instanceof Uint8Array || a instanceof Int8Array ? p = m(a) : a instanceof Uint32Array || a instanceof Int32Array || a instanceof Uint16Array || a instanceof Int16Array || a instanceof Float32Array || a instanceof Float64Array ? p = m(new Uint8Array(a.buffer)) : q = typeof a : q = typeof a,
 q && alert("MD5 type mismatch, cannot process " + q),
 o()
}
,
function() {
 function a(a) {
  if (window.KgMobileCall)
   a && a();
  else {
   var b = document.createElement("script");
   b.src = "https://m3ws.kugou.com/static/js/common/mobilecall_3.0.js",
   b.onload = function() {
    this.readyState && "loaded" != this.readyState && "complete" != this.readyState || a && a()
   }
   ,
   document.body.appendChild(b)
  }
 }
 function b(b, c, d) {
  b = b || {},
  c = c || "",
  d = d || {};
  var e, f = !1, g = "json";
  "function" == typeof d ? e = d : (e = d.callback,
  f = d.useH5 || !1,
  g = d.postType || "json");
  var h = {};
  for (var i in b)
   !h[i] && (h[i] = b[i]);
  var j = function() {
   var a = navigator.userAgent.match(/KGBrowser/gi) ? !0 : !1
    , b = navigator.userAgent.match(/kugouandroid/gi) ? !0 : !1
    , c = "undefined" == typeof external ? !1 : "undefined" == typeof external.superCall ? !1 : !0;
   return c || b || a ? !0 : !1
  }()
   , k = (new Date).getTime()
   , l = []
   , m = {}
   , n = []
   , o = []
   , p = "NVPh5oo715z5DIWAeQlhMDsWXXQV4hwt"
   , q = {
   appid: function(a) {
    return a()
   },
   srcappid: function(a) {
    return a("2919")
   },
   clientver: function(a) {
    return a("20000")
   },
   "clienttime,mid,uuid,dfid": function(a) {
    return a({
     clienttime: k,
     mid: k,
     uuid: k,
     dfid: "-"
    })
   }
  }
   , r = function() {
   for (var a in q)
    l.push(a);
   !function(a) {
    function b(a) {
     if (a < l.length)
      q[l[a]](function(c) {
       if (c)
        if ("[object Object]" == Object.prototype.toString.call(c))
         for (var d in c)
          m[d] = c[d];
        else
         m[l[a]] = c;
       b(a + 1)
      });
     else {
      for (var d in m)
       !h[d] && (h[d] = m[d]);
      for (var d in h)
       n.push(d);
      if (n.sort(),
      n.forEach(function(a) {
       o.push(a + "=" + h[a])
      }),
      c)
       if ("[object Object]" == Object.prototype.toString.call(c))
        if ("json" == g)
         o.push(JSON.stringify(c));
        else {
         var f = [];
         for (var d in c)
          f.push(d + "=" + c[d]);
         o.push(f.join("&"))
        }
       else
        o.push(c);
      o.unshift(p),
      o.push(p),
      h.signature = faultylabs.MD5(o.join("")),
      e && e(h)
     }
    }
    b(a)
   }(0)
  };
  if (c && ("[object Object]" != Object.prototype.toString.call(c) ? j = !1 : "urlencoded" == g && (j = !1)),
  j && !f) {
   var s = !1;
   a(function() {
    KgMobileCall.callCmd({
     cmd: 764,
     jsonStr: JSON.stringify({
      get: h,
      post: c
     }),
     callback: function(a) {
      if (s)
       return !1;
      if (s = !0,
      a && a.status) {
       delete a.status;
       for (var b in a)
        !h[b] && (h[b] = a[b]);
       return e && e(h)
      }
      j = !1,
      r()
     }
    })
   })
  } else
   j = !1,
   r()
 }
 "undefined" != typeof module && module.exports ? module.exports = b : "function" == typeof define && define.amd ? define(function() {
  return b
 }) : window.getInterFacePublic = b
}();

在274行发现h.signature = faultylabs.MD5(o.join("")),初步理解为signature是o内部元素拼接成字符串,对其加上断点并将o加入watch。

0: "NVPh5oo715z5DIWAeQlhMDsWXXQV4hwt"
1: "bitrate=0"
2: "callback=callback123"
3: "clienttime=1612580098162"
4: "clientver=2000"
5: "dfid=-"
6: "inputtype=0"
7: "iscorrection=1"
8: "isfuzzy=0"
9: "keyword=花海"
10: "mid=1612580098162"
11: "page=1"
12: "pagesize=30"
13: "platform=WebFilter"
14: "privilege_filter=0"
15: "srcappid=2919"
16: "tag=em"
17: "userid=-1"
18: "uuid=1612580098162"
19: "NVPh5oo715z5DIWAeQlhMDsWXXQV4hwt"
length: 20

在watch里不难发现o为一个长度为20的数组,之后我们按之前理解将字符串拼接。

NVPh5oo715z5DIWAeQlhMDsWXXQV4hwtbitrate=0callback=callback123clienttime=1612580098162clientver=2000dfid=-inputtype=0iscorrection=1isfuzzy=0keyword=花海mid=1612580098162page=1pagesize=30platform=WebFilterprivilege_filter=0srcappid=2919tag=emuserid=-1uuid=1612580098162NVPh5oo715z5DIWAeQlhMDsWXXQV4hwt

之后要js解密,这谁会?反正我不会 0.0,那也有办法,用python调用js文件。在274行分析为md5加密,往前找看看有没有相关函数,果真有一个,将其保存为kugou.js

"undefined" == typeof faultylabs && (faultylabs = {}),
faultylabs.MD5 = function(a) {
 function b(a) {
  var b = (a >>> 0).toString(16);
  return "00000000".substr(0, 8 - b.length) + b
 }
 function c(a) {
  for (var b = [], c = 0; c < a.length; c++)
   b = b.concat(k(a[c]));
  return b
 }
 function d(a) {
  for (var b = [], c = 0; 8 > c; c++)
   b.push(255 & a),
   a >>>= 8;
  return b
 }
 function e(a, b) {
  return a << b & 4294967295 | a >>> 32 - b
 }
 function f(a, b, c) {
  return a & b | ~a & c
 }
 function g(a, b, c) {
  return c & a | ~c & b
 }
 function h(a, b, c) {
  return a ^ b ^ c
 }
 function i(a, b, c) {
  return b ^ (a | ~c)
 }
 function j(a, b) {
  return a[b + 3] << 24 | a[b + 2] << 16 | a[b + 1] << 8 | a[b]
 }
 function k(a) {
  for (var b = [], c = 0; c < a.length; c++)
   if (a.charCodeAt(c) <= 127)
    b.push(a.charCodeAt(c));
   else
    for (var d = encodeURIComponent(a.charAt(c)).substr(1).split("%"), e = 0; e < d.length; e++)
     b.push(parseInt(d[e], 16));
  return b
 }
 function l() {
  for (var a = "", c = 0, d = 0, e = 3; e >= 0; e--)
   d = arguments[e],
   c = 255 & d,
   d >>>= 8,
   c <<= 8,
   c |= 255 & d,
   d >>>= 8,
   c <<= 8,
   c |= 255 & d,
   d >>>= 8,
   c <<= 8,
   c |= d,
   a += b(c);
  return a
 }
 function m(a) {
  for (var b = new Array(a.length), c = 0; c < a.length; c++)
   b[c] = a[c];
  return b
 }
 function n(a, b) {
  return 4294967295 & a + b
 }
 function o() {
  function a(a, b, c, d) {
   var f = v;
   v = u,
   u = t,
   t = n(t, e(n(s, n(a, n(b, c))), d)),
   s = f
  }
  var b = p.length;
  p.push(128);
  var c = p.length % 64;
  if (c > 56) {
   for (var k = 0; 64 - c > k; k++)
    p.push(0);
   c = p.length % 64
  }
  for (k = 0; 56 - c > k; k++)
   p.push(0);
  p = p.concat(d(8 * b));
  var m = 1732584193
   , o = 4023233417
   , q = 2562383102
   , r = 271733878
   , s = 0
   , t = 0
   , u = 0
   , v = 0;
  for (k = 0; k < p.length / 64; k++) {
   s = m,
   t = o,
   u = q,
   v = r;
   var w = 64 * k;
   a(f(t, u, v), 3614090360, j(p, w), 7),
   a(f(t, u, v), 3905402710, j(p, w + 4), 12),
   a(f(t, u, v), 606105819, j(p, w + 8), 17),
   a(f(t, u, v), 3250441966, j(p, w + 12), 22),
   a(f(t, u, v), 4118548399, j(p, w + 16), 7),
   a(f(t, u, v), 1200080426, j(p, w + 20), 12),
   a(f(t, u, v), 2821735955, j(p, w + 24), 17),
   a(f(t, u, v), 4249261313, j(p, w + 28), 22),
   a(f(t, u, v), 1770035416, j(p, w + 32), 7),
   a(f(t, u, v), 2336552879, j(p, w + 36), 12),
   a(f(t, u, v), 4294925233, j(p, w + 40), 17),
   a(f(t, u, v), 2304563134, j(p, w + 44), 22),
   a(f(t, u, v), 1804603682, j(p, w + 48), 7),
   a(f(t, u, v), 4254626195, j(p, w + 52), 12),
   a(f(t, u, v), 2792965006, j(p, w + 56), 17),
   a(f(t, u, v), 1236535329, j(p, w + 60), 22),
   a(g(t, u, v), 4129170786, j(p, w + 4), 5),
   a(g(t, u, v), 3225465664, j(p, w + 24), 9),
   a(g(t, u, v), 643717713, j(p, w + 44), 14),
   a(g(t, u, v), 3921069994, j(p, w), 20),
   a(g(t, u, v), 3593408605, j(p, w + 20), 5),
   a(g(t, u, v), 38016083, j(p, w + 40), 9),
   a(g(t, u, v), 3634488961, j(p, w + 60), 14),
   a(g(t, u, v), 3889429448, j(p, w + 16), 20),
   a(g(t, u, v), 568446438, j(p, w + 36), 5),
   a(g(t, u, v), 3275163606, j(p, w + 56), 9),
   a(g(t, u, v), 4107603335, j(p, w + 12), 14),
   a(g(t, u, v), 1163531501, j(p, w + 32), 20),
   a(g(t, u, v), 2850285829, j(p, w + 52), 5),
   a(g(t, u, v), 4243563512, j(p, w + 8), 9),
   a(g(t, u, v), 1735328473, j(p, w + 28), 14),
   a(g(t, u, v), 2368359562, j(p, w + 48), 20),
   a(h(t, u, v), 4294588738, j(p, w + 20), 4),
   a(h(t, u, v), 2272392833, j(p, w + 32), 11),
   a(h(t, u, v), 1839030562, j(p, w + 44), 16),
   a(h(t, u, v), 4259657740, j(p, w + 56), 23),
   a(h(t, u, v), 2763975236, j(p, w + 4), 4),
   a(h(t, u, v), 1272893353, j(p, w + 16), 11),
   a(h(t, u, v), 4139469664, j(p, w + 28), 16),
   a(h(t, u, v), 3200236656, j(p, w + 40), 23),
   a(h(t, u, v), 681279174, j(p, w + 52), 4),
   a(h(t, u, v), 3936430074, j(p, w), 11),
   a(h(t, u, v), 3572445317, j(p, w + 12), 16),
   a(h(t, u, v), 76029189, j(p, w + 24), 23),
   a(h(t, u, v), 3654602809, j(p, w + 36), 4),
   a(h(t, u, v), 3873151461, j(p, w + 48), 11),
   a(h(t, u, v), 530742520, j(p, w + 60), 16),
   a(h(t, u, v), 3299628645, j(p, w + 8), 23),
   a(i(t, u, v), 4096336452, j(p, w), 6),
   a(i(t, u, v), 1126891415, j(p, w + 28), 10),
   a(i(t, u, v), 2878612391, j(p, w + 56), 15),
   a(i(t, u, v), 4237533241, j(p, w + 20), 21),
   a(i(t, u, v), 1700485571, j(p, w + 48), 6),
   a(i(t, u, v), 2399980690, j(p, w + 12), 10),
   a(i(t, u, v), 4293915773, j(p, w + 40), 15),
   a(i(t, u, v), 2240044497, j(p, w + 4), 21),
   a(i(t, u, v), 1873313359, j(p, w + 32), 6),
   a(i(t, u, v), 4264355552, j(p, w + 60), 10),
   a(i(t, u, v), 2734768916, j(p, w + 24), 15),
   a(i(t, u, v), 1309151649, j(p, w + 52), 21),
   a(i(t, u, v), 4149444226, j(p, w + 16), 6),
   a(i(t, u, v), 3174756917, j(p, w + 44), 10),
   a(i(t, u, v), 718787259, j(p, w + 8), 15),
   a(i(t, u, v), 3951481745, j(p, w + 36), 21),
   m = n(m, s),
   o = n(o, t),
   q = n(q, u),
   r = n(r, v)
  }
  return l(r, q, o, m).toUpperCase()
 }
 var p = null
  , q = null;
 return "string" == typeof a ? p = k(a) : a.constructor == Array ? 0 === a.length ? p = a : "string" == typeof a[0] ? p = c(a) : "number" == typeof a[0] ? p = a : q = typeof a[0] : "undefined" != typeof ArrayBuffer ? a instanceof ArrayBuffer ? p = m(new Uint8Array(a)) : a instanceof Uint8Array || a instanceof Int8Array ? p = m(a) : a instanceof Uint32Array || a instanceof Int32Array || a instanceof Uint16Array || a instanceof Int16Array || a instanceof Float32Array || a instanceof Float64Array ? p = m(new Uint8Array(a.buffer)) : q = typeof a : q = typeof a,
 q && alert("MD5 type mismatch, cannot process " + q),
 o()
}

之后用python的pyexecjs库调用, 但是注意调用的时候的名字是execjs。

代码实现

"""
data: 2021/02/05

通过搜索爬取酷狗音乐,付费音乐暂时只能爬取试听部分。
"""

import requests
import re
import json
import time
import execjs


def get_signature(text):
 """
 获取signature值
 :param text: 格式化之后的字符串
 :return: 返回酷狗网站上加密后的signature
 """
 # 读取js文件内容
 with open("kugou.js", "r", encoding='utf-8') as f:
  js_str = f.read()

 # 通过js文件中逻辑数据,对文件进行加密
 if js_str:
  js_obj = execjs.compile(js_str)
  return js_obj.call('faultylabs.MD5', text)


def get_url(keyword):
 """
 获取搜索之后的url
 :param keyword: 搜索词,如晴天
 :return: 返回完整的url地址
 """
 search = "https://complexsearch.kugou.com/v2/search/song?callback=callback123&keyword={keyword}&page=1&pagesize=30&bitrate=0&isfuzzy=0&tag=em&inputtype=0&platform=WebFilter&userid=-1&clientver=2000&iscorrection=1&privilege_filter=0&srcappid=2919&clienttime={time}&mid={time}&uuid={time}&dfid=-&signature={signature}"
 key_code = "NVPh5oo715z5DIWAeQlhMDsWXXQV4hwtbitrate=0callback=callback123clienttime={time}clientver=2000dfid=-inputtype=0iscorrection=1isfuzzy=0keyword={keyword}mid={time}page=1pagesize=30platform=WebFilterprivilege_filter=0srcappid=2919tag=emuserid=-1uuid={time}NVPh5oo715z5DIWAeQlhMDsWXXQV4hwt"

 # 获得13位时间戳
 millis = str(round(time.time() * 1000))
 p = key_code.format(time=millis, keyword=keyword)
 signature = get_signature(p)
 # print(signature)

 search_url = search.format(keyword=keyword, time=millis, signature=signature)
 return search_url


def get_data(url):
 headers = {
  'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.146 Safari/537.36',
  'referer': 'https://www.kugou.com/',
  'authority': 'complexsearch.kugou.com',
 }

 res = requests.get(url=url, headers=headers)

 # 将获取的数据转为json格式
 data = re.findall('callback123\((.*)\)', res.text, re.S)[0]
 json_data = json.loads(data)['data']

 hash_value = json_data['lists'][0]['FileHash'].lower()
 album_id = json_data['lists'][0]['AlbumID']
 return hash_value, album_id


def get_mp3(hash_value, album_id):
 """
 获取MP3音频文件
 :param hash_value: 传入哈希值
 :param album_id: 传入album id
 :return: none
 """
 url = 'https://wwwapi.kugou.com/yy/index.php'

 params = {
  'r': 'play/getdata',
  'callback': 'jQuery191019800824574510756_1612519333214',
  'hash': str(hash_value),
  'dfid': '0Q0Clh1IcZaG3ey1J70RaTiL',
  'mid': 'b6cf66837b18642cc269390b066649dc',
  'platid': '4',
  'album_id': str(album_id),
 }

 headers = {
  'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.146 Safari/537.36',
  'referer': 'https://www.kugou.com/',
  'authority': 'wwwapi.kugou.com',
 }
 res = requests.post(url=url, params=params, headers=headers)

 data = re.findall('jQuery191019800824574510756_1612519333214\((.*?)\);', res.text, re.S)[0]
 json_data = json.loads(data)

 audio_name = json_data['data']['audio_name']
 play_url = json_data['data']['play_url']

 save_mp3(audio_name, play_url)


def save_mp3(audio_name, play_url):
 """
 保持MP3文件
 :param audio_name: 传入命名
 :param play_url: 传入音频url
 :return: none
 """
 content = requests.get(play_url).content
 with open(audio_name + '.mp3', mode='ab') as f:
  f.write(content)


if __name__ == '__main__':
 try:
  keyword = input('请输入要搜索的歌曲名称:')
  hash_value, album_id = get_data(get_url(keyword))

  get_mp3(hash_value, album_id)
 except Exception as e:
  print('请输入正确歌曲名称。')

以上就是Python爬取酷狗MP3音频的步骤的详细内容,更多关于Python爬取酷狗MP3音频的资料请关注三水点靠木其它相关文章!

Python 相关文章推荐
python实现redis三种cas事务操作
Dec 19 Python
Python实现学校管理系统
Jan 11 Python
基于numpy.random.randn()与rand()的区别详解
Apr 17 Python
python 返回一个列表中第二大的数方法
Jul 09 Python
对python中url参数编码与解码的实例详解
Jul 25 Python
Django中自定义查询对象的具体使用
Oct 13 Python
Python 模拟动态产生字母验证码图片功能
Dec 24 Python
tensorflow 实现自定义layer并添加到计算图中
Feb 04 Python
python爬虫调度器用法及实例代码
Nov 30 Python
10个顶级Python实用库推荐
Mar 04 Python
Django一小时写出账号密码管理系统
Apr 29 Python
python实现MD5进行文件去重的示例代码
Jul 09 Python
python利用xpath爬取网上数据并存储到django模型中
Feb 26 #Python
用python 绘制茎叶图和复合饼图
Feb 26 #Python
python lambda的使用详解
Feb 26 #Python
python爬虫scrapy框架之增量式爬虫的示例代码
Feb 26 #Python
详解Python openpyxl库的基本应用
Feb 26 #Python
解决python的空格和tab混淆而报错的问题
Feb 26 #Python
Python Spyder 调出缩进对齐线的操作
Feb 26 #Python
You might like
PHP实现图片简单上传
2006/10/09 PHP
php header()函数使用说明
2008/07/10 PHP
php使用explode()函数将字符串拆分成数组的方法
2015/02/17 PHP
php实现统计目录文件大小的函数
2015/12/25 PHP
Laravel 实现密码重置功能
2018/02/23 PHP
php输出形式实例整理
2020/05/05 PHP
jquery实用代码片段集合
2010/08/12 Javascript
jquery使用ColorBox弹出图片组浏览层实例演示
2013/03/14 Javascript
js清除input中type等于file的值域(示例代码)
2013/12/24 Javascript
JavaScript调用ajax获取文本文件内容实现代码
2014/03/28 Javascript
JavaScript实现的一个计算数字步数的算法分享
2014/12/06 Javascript
JavaScript检测字符串中是否含有html标签实现方法
2015/07/01 Javascript
详解AngularJS实现表单验证
2015/12/10 Javascript
基于javascript实现右下角浮动广告效果
2016/01/08 Javascript
vue数据双向绑定的注意点
2017/06/23 Javascript
vue的事件绑定与方法详解
2017/08/16 Javascript
vue-cli 3.x 配置Axios(proxyTable)跨域代理方法
2018/09/19 Javascript
微信小程序判断页面是否从其他页面返回的实例代码
2019/07/03 Javascript
Nuxt 嵌套路由nuxt-child组件用法(父子页面组件的传值)
2020/11/05 Javascript
[01:21:07]EG vs Liquid 2018国际邀请赛淘汰赛BO3 第一场 8.25
2018/08/29 DOTA
[02:58]魔廷新尊——痛苦女王至宝语音台词节选
2020/06/14 DOTA
pyqt4教程之实现半透明的天气预报界面示例
2014/03/02 Python
Flask框架学习笔记(一)安装篇(windows安装与centos安装)
2014/06/25 Python
在centos7中分布式部署pyspider
2017/05/03 Python
python实现基于信息增益的决策树归纳
2018/12/18 Python
对python多线程中Lock()与RLock()锁详解
2019/01/11 Python
对python中GUI,Label和Button的实例详解
2019/06/27 Python
python GUI库图形界面开发之PyQt5信号与槽的高级使用技巧装饰器信号与槽详细使用方法与实例
2020/03/06 Python
CSS图片翻转动画技术详解(IE也实现了)
2014/04/03 HTML / CSS
HTML5 embed标签定义和用法详解
2014/05/09 HTML / CSS
教育局长自荐信范文
2013/12/22 职场文书
大学生自我鉴定范文模板
2014/01/21 职场文书
涉密人员保密承诺书
2014/05/28 职场文书
初中生考试作弊检讨书
2014/12/14 职场文书
律师催款函范文
2015/06/24 职场文书
OpenCV-Python实现轮廓的特征值
2021/06/09 Python