python爬虫 拼多多_拼多多爬虫之anti_content分析

首先来看抓包:

查找相关的代码:

this.request = function() {

var e, t = (e = c.a.mark(function e(t) {

var n, o, a, i, s, l;

return c.a.wrap(function(e) {

for (; ; )

switch (e.prev = e.next) {

case 0:

return n = t.requestContext,

o = void 0 === n ? {} : n,

e.next = 4,

Ot.a.getAntiContent();

case 4:

(a = e.sent) && (r.antiContent = a);

case 6:

return r.formatRequestParams(),

e.prev = 7,

e.next = 10,

Object(wt.a)({

req: o.__req,

path: "search",

params: r.requestModelParams

}).get();

case 10:

if (e.t0 = e.sent,

e.t0) {

e.next = 13;

break

}

e.t0 = {};

case 13:

return i = e.t0,

s = kt(i, {

sort: r.sortType,

page: r.searchPageIndex

}) || {},

l = r.successLoggerParams(i),

r.trackingSearchEvent(l),

s.loadSearchResultTracking = l,

s.firstFilter = r.requestModelParams.filter || "",

r.flip = i.flip,

r.updateFlip(i.flip),

r.searchPageIndex++,

Ot.a.clearCache(),

e.abrupt("return", s);

case 26:

return e.prev = 26,

e.t1 = e.catch(7),

e.abrupt("return", Object(St.a)(e.t1));

case 29:

case "end":

return e.stop()

}

}, e, null, [[7, 26]])

})

过程:

通过 Ot.a.getAntiContent()得到的这个值,(a = e.sent)&&(r.antiContent = a)执行这段的时候就已经获得了这个anticontent了.但是跟这这个追进去得到的是一个Promise对象,单步就会一直进入到漫长的pengding状态中…

生无可恋!

思路:

先看看这个:

{

key: "initRiskController",

value: function() {

this.riskControlCrawler || (this.riskControlCrawler = new n.a({

serverTime: this.serverTime,

_2827c887a48a351a: !1

}),

this.riskControlCrawler.init())

}

}

爬虫控制风险,看名字就知道不简单,这里先做了一次初始化,初始化的时候记录了一个serverTime的时间戳,而且以后的每一次下拉页面都有拿时间作比较.等等…

看一下是js头部:

(window.webpackJsonp = window.webpackJsonp || []).push([[11], {

100: function(e, t, r) {

e.exports = {

container: "_1y-VhIOC",

title: "rvmJzAGI",

list: "_8KUXGnrb",

item: "_2oaWTr_0",

mallItem: "_1cIPk2r5"

}

},

又是webpack打包!!!

生无可恋!

不过还是得硬上啊!

然后就打算把所有的包都打开,放到一起运行,结果…电脑先破溃了!!

没有办法,我们还是要一个文件一个文件的看看:

研究了一下,发现是这样的代码:

187: function(e, t, r) {

(function(e) {

var r, n, o, a;

function i(e) {

return (i = "function" == typeof Symbol && "symbol" == typeof Symbol.iterator ? function(e) {

return typeof e

}

: function(e) {

return e && "function" == typeof Symbol && e.constructor === Symbol && e !== Symbol.prototype ? "symbol" : typeof e

}

)(e)

}

"undefined" != typeof self && self,

a = function() {

return function(e) {

var t = {};

function r(n) {

if (t[n])

return t[n].exports;

var o = t[n] = {

i: n,

l: !1,

exports: {}

};

return e[n].call(o.exports, o, o.exports, r),

o.l = !0,

o.exports

}

return r.m = e,

r.c = t,

r.d = function(e, t, n) {

r.o(e, t) || Object.defineProperty(e, t, {

enumerable: !0,

get: n

})

}

,

r.r = function(e) {

"undefined" != typeof Symbol && Symbol.toStringTag && Object.defineProperty(e, Symbol.toStringTag, {

value: "Module"

}),

Object.defineProperty(e, "__esModule", {

value: !0

})

}

,

r.t = function(e, t) {

if (1 & t && (e = r(e)),

8 & t)

return e;

if (4 & t && "object" == i(e) && e && e.__esModule)

return e;

var n = Object.create(null);

if (r.r(n),

Object.defineProperty(n, "default", {

enumerable: !0,

value: e

}),

2 & t && "string" != typeof e)

for (var o in e)

r.d(n, o, function(t) {

return e[t]

}

.bind(null, o));

return n

}

,

r.n = function(e) {

var t = e && e.__esModule ? function() {

return e.default

}

: function() {

return e

}

;

return r.d(t, "a", t),

t

}

,

r.o = function(e, t) {

return Object.prototype.hasOwnProperty.call(e, t)

}

,

r.p = "",

r(r.s = 5)

内层又进行一次打包!!!

感觉要吐血了!!! 都快要放弃了!

不要紧,慢慢看,那么容易就让你搞到数据,那还怎么玩!

分析:

this.riskControlCrawler || (this.riskControlCrawler = new n.a({

serverTime: this.serverTime,

_2827c887a48a351a: !1

}),

this.riskControlCrawler.init())

}

首先初始化了一个加密对象跟着这个对象进去,发现了一堆混淆了的代码,这个ee就是关键的加密代码了:

没有关系我们把它全部把下来,但是发现还是需要好多的依赖包比如这些:

看到这里完全是一团乱麻,有2个思路

1.每次把需要的代码就把对应的依赖包找到,改写成单独的文件,使用require()加载进来

2.一次运行到位,加载所有的包

我采用第二种办法,首先把整个代码call一遍,不管有多少依赖包,全部都加载到位,在关键的地方强制截断,强制弹出anticontent

aaa=new ee({

serverTime: 1556530561960,

_2827c887a48a351a: !1

})

aaa.init() //初始化

anticontent = aaa.messagePackSync({

touchEventData: !0,

clickEventData: !0,

focusblurEventData: !0,

changeEventData: !0,

locationInfo: !0,

referrer: !0,

browserSize: !0,

browserInfo: !0,

token: !0,

fingerprint: !0

})

console.log(anticontent)

舒服!!