爬取酷狗音乐全分析

代码实现从搜索到爬取酷狗音乐，付费音乐暂时只能爬取试听部分。

---

一、分析问题

1. 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

2. 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

3. 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