Python爬虫之JS逆向破解百度翻译

2019-08-17

一、分析百度翻译

这跟有道翻译不同，有着另一种反爬机制，因此仍然使用pc端网站接口会报997错误
所以这次爬虫使用手机端地址进行爬取：

1	self.url='https://fanyi.baidu.com/basetrans'

注意的是其他headers及data明细也要使用手机网页端的。

二、使用mitmproxy进行抓包

暂时关闭我的arch的iptables 之后在同一局域网内将手机的代理设置为电脑端的ip 端口使用默认的8080
其次安装证书是必不可少的。
至此就可以实现mitmproxy监听手机端了
token需要使用手机端的
sign的产生和电脑网页端的生成方式是一样的，都是需要执行js代码生成。

附上JS代码：baidu_translate.js

 function n(r, o) {
        for (var t = 0; t < o.length - 2; t += 3) {
            var a = o.charAt(t + 2);
            a = a >= "a" ? a.charCodeAt(0) - 87 : Number(a),
            a = "+" === o.charAt(t + 1) ? r >>> a : r << a,
            r = "+" === o.charAt(t) ? r + a & 4294967295 : r ^ a
        }
        return r
    }
function e(r) {
        var i='320305.131321201'
        var o = r.match(/[\uD800-\uDBFF][\uDC00-\uDFFF]/g);
        if (null === o) {
            var t = r.length;
            t > 30 && (r = "" + r.substr(0, 10) + r.substr(Math.floor(t / 2) - 5, 10) + r.substr(-10, 10))
        } else {
            for (var e = r.split(/[\uD800-\uDBFF][\uDC00-\uDFFF]/), C = 0, h = e.length, f = []; h > C; C++)
                "" !== e[C] && f.push.apply(f, a(e[C].split(""))),
                C !== h - 1 && f.push(o[C]);
            var g = f.length;
            g > 30 && (r = f.slice(0, 10).join("") + f.slice(Math.floor(g / 2) - 5, Math.floor(g / 2) + 5).join("") + f.slice(-10).join(""))
        }
        var u = void 0
          , l = "" + String.fromCharCode(103) + String.fromCharCode(116) + String.fromCharCode(107);
        u = null !== i ? i : (i = window[l] || "") || "";
        for (var d = u.split("."), m = Number(d[0]) || 0, s = Number(d[1]) || 0, S = [], c = 0, v = 0; v < r.length; v++) {
            var A = r.charCodeAt(v);
            128 > A ? S[c++] = A : (2048 > A ? S[c++] = A >> 6 | 192 : (55296 === (64512 & A) && v + 1 < r.length && 56320 === (64512 & r.charCodeAt(v + 1)) ? (A = 65536 + ((1023 & A) << 10) + (1023 & r.charCodeAt(++v)),
            S[c++] = A >> 18 | 240,
            S[c++] = A >> 12 & 63 | 128) : S[c++] = A >> 12 | 224,
            S[c++] = A >> 6 & 63 | 128),
            S[c++] = 63 & A | 128)
        }
        for (var p = m, F = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(97) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(54)), D = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(51) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(98)) + ("" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(102)), b = 0; b < S.length; b++)
            p += S[b],
            p = n(p, F);
        return p = n(p, D),
        p ^= s,
        0 > p && (p = (2147483647 & p) + 2147483648),
        p %= 1e6,
        p.toString() + "." + (p ^ m)
}

Python代码：

import execjs
import requests
# python爬取百度翻译返回：{'error': 997, 'from': 'zh', 'to': 'en', 'query 问题
# 修改url为手机版的地址：http://fanyi.baidu.com/basetrans
# User-Agent及token等也用手机版的
class baiduTranslateJs(object):
    def __init__(self,query):
        self.query=query
        self.url='https://fanyi.baidu.com/basetrans'
        self.headers={
            'x-requested-with': 'XMLHttpRequest',
            'content-type':'application/x-www-form-urlencoded',
            'referer':'https://fanyi.baidu.com/?aldtype=38319&tpltype=sigma',
            'accept-encoding':'gzip, deflate, br',
            'accept-language':'zh-CN,zh;q=0.9',
            'cookie': 'BIDUPSID=B672909954F5126364A994D3D59115E1; BAIDUID=98D32FCD46AF8B942922DDA6B2980992:FG=1; rsv_i=1fa0LaBzzVsbkiCumF7bn0XUoEF9g89aI6Q4H%2FRe0dYzGkDRF8Y7BFQhi4nLKbg2ubD%2F%2BYYX6gEIExHQ3qICdYeKn28ASUE; FEED_SIDS=536472_0816_22; BDORZ=AE84CDB3A529C0F8A2B9DCDD1D18B695; SE_LAUNCH=5%3A26099434_0%3A26099434_15%3A26099434; H_WISE_SIDS=125703_132919_135072_128065_120179_132910_133041_131247_132439_130762_132378_131517_118883_118869_118850_118818_118791_107311_132781_122034_133352_134795_132553_129651_132250_124637_128968_133473_133838_133847_132551_132336_134462_134319_134047_134214_129646_131423_134818_133191_110085_134153_127969_131298_127318_127417_134151_134231; delPer=0; PSINO=6; locale=zh; Hm_lvt_afd111fa62852d1f37001d1f980b6800=1565966061,1565966204; Hm_lpvt_afd111fa62852d1f37001d1f980b6800=1565966204; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1565966061,1565966204; Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1565966204',
            'user-agent': 'Mozilla/5.0 (Linux; Android 9; TA-1041) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.101 Mobile Safari/537.36'
        }
        self.data={
            'query': self.query,
            'from': 'auto', #将这里的en改成auto就可以自动识别语言了
            'to': 'auto', #将这里的zh改成auto就可以自动识别语言了
            'sign': '',
            'token': 'e32d652ac93e4d95b6b9eb9768fbadb1'
        }
    def structure_form(self):
        """
                读取js文件
                执行js代码得到sign值
                构造新的表单
                :return:
        """
        with open('/home/lsp/py/lsls/js_spider/baidu_translate.js', 'r', encoding='utf-8') as f:
            ctx = execjs.compile(f.read())
        sign = ctx.call('e', self.query)  # 54706.276099
        print(sign)
        self.data['sign']=sign

    def get_response(self):
        """
        通过构造的新的表单数据，访问api，获取翻译内容
        :return: 翻译结果
        """
        self.structure_form()
        # print(self.headers)
        print(self.data)
        response = requests.post(self.url, headers=self.headers, data=self.data).json()
        # print(response.status_code)
        # print(json.loads(response))
        print(response)
        r = response['trans'][0]['dst']
        return r

if __name__ == '__main__':

    trjs=baiduTranslateJs('hello world!')
    r=trjs.get_response()
    print(r)