模拟百度翻译

fanyi.py

# ！user/bin/env python3
# -*-coding: utf-8 -*-
__author__ = '闻名'

import execjs
import re
import requests


def get_sign(word, gtk):
    with open('index.js') as f:
        js_data = f.read()

    ctx = execjs.compile(js_data)

    sign = ctx.call('e', word, gtk)

    return sign


def get_token_gtk(response):
    '''
    获取token和gtk的值
    :param response:
    :return:
    '''

    token = re.findall(r"token: '(.*?)',", response)
    gtk = re.findall(r"window.gtk = '(.*?)';", response)
    if token and gtk:
        return token[0], gtk[0]


if __name__ == '__main__':
    session = requests.session()

    start_url = 'https://fanyi.baidu.com/'

    response = session.post(start_url)
    response = session.post(start_url)

    # 获取token和gtk的值
    token, gtk = get_token_gtk(response.text)

    # print(token, gtk)

    headers = {
        'Referer': 'https://fanyi.baidu.com/',
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.87 Safari/537.36'
    }
    word = '大笨蛋，我最最最讨厌你了'
    sign = get_sign(word, gtk)
    # print(sign)

    data = {
        'from': 'zh',
        'to': 'en',
        'query': word,
        'transtype': 'realtime',
        'simple_means_flag': '3',
        'sign': sign,
        'token': token,
    }

    session.post(url='https://fanyi.baidu.com/langdetect', data={'query': word})
    # print(res.text)
    res = session.post(url='https://fanyi.baidu.com/v2transapi?from=en&to=jp', data=data, headers=headers)
    print(word, res.json()['trans_result']['data'][0]['dst'])

index.js

var i = null;

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, gtk) {
    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 = gtk || "") || "";
    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)
}