百度翻译爬虫

# 百度翻译爬虫

**今日目标**

百度翻译能够随意输入内容并进行翻译

思路：在JS文件里面找到sign对应的m(a)函数，再用pyexecjs模块在Python中是实现
```python
import requests
import re
import execjs

class BaiduTranslateSpider(object):
    def __init__(self):
        self.get_url = 'https://fanyi.baidu.com/?aldtype=16047'
        self.headers = {
            "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3",
            "accept-encoding": "gzip, deflate, br",
            "accept-language": "zh-CN,zh;q=0.9",
            "cache-control": "max-age=0",
            "cookie": "BAIDUID=2619E4B40580C3B077FF47135A00E390:FG=1; PSTM=1561529240; BIDUPSID=6E51187F13540BD223A2CC75D5DAD043; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; locale=zh; to_lang_often=%5B%7B%22value%22%3A%22en%22%2C%22text%22%3A%22%u82F1%u8BED%22%7D%2C%7B%22value%22%3A%22zh%22%2C%22text%22%3A%22%u4E2D%u6587%22%7D%5D; REALTIME_TRANS_SWITCH=1; FANYI_WORD_SWITCH=1; HISTORY_SWITCH=1; SOUND_SPD_SWITCH=1; SOUND_PREFER_SWITCH=1; from_lang_often=%5B%7B%22value%22%3A%22zh%22%2C%22text%22%3A%22%u4E2D%u6587%22%7D%2C%7B%22value%22%3A%22en%22%2C%22text%22%3A%22%u82F1%u8BED%22%7D%5D; delPer=0; PSINO=1; td_cookie=18446744071276835184; H_PS_PSSID=1456_21115_29578_29518_28519_29098_29568_28837_29220_29588; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1563954537,1564019919,1564022523,1564024494; Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1564026816; yjs_js_security_passport=76d517a36b6cea24775539304d39f1d5b4a11c3d_1564026815_js",
            "upgrade-insecure-requests": "1",
            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36",
        }

    # 获取token
    def get_token(self):
        html = requests.get(
            url = self.get_url,
            headers = self.headers
        ).text
        # 正则解析
        pattern = re.compile("token: '(.*?)'",re.S)
        token = pattern.findall(html)[0]

        return token

    # 获取sign
    def get_sign(self,word):
        with open('node.js','r') as f:
            js_data = f.read()
        execjs_obj = execjs.compile(js_data)
        sign = execjs_obj.eval('e("{}")'.format(word))

        return sign

    # 获取翻译结果
    def get_result(self,word,fro,to):
        token = self.get_token()
        sign = self.get_sign(word)
        # 把formdata定义成字典
        formdata = {
            'from': fro,
            'to': to,
            'query': word,
            'transtype': 'realtime',
            'simple_means_flag': '3',
            'sign': sign,
            'token': token,
        }
        html_json = requests.post(
            url = 'https://fanyi.baidu.com/v2transapi',
            data = formdata,
            headers = self.headers
        ).json()

        result = html_json['trans_result']['data'][0]['dst']

        return result



if __name__ == '__main__':
    spider = BaiduTranslateSpider()
    choice = input('1.翻译英语　2.翻译汉语 请选择(1/2):')
    if choice == '1':
        fro = 'en'
        to = 'zh'
    else:
        fro = 'zh'
        to = 'en'

    word = input('请输入要翻译的单词:')
    result = spider.get_result(word,fro,to)
    print(result)



```
node.js代码
```
function a(r) {
    if (Array.isArray(r)) {
        for (var o = 0, t = Array(r.length); o < r.length; o++)
            t[o] = r[o];
        return t
    }
    return Array.from(r)
}
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 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] || "") || "";

    var u = '320305.131321201'

    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)
}
var i = null;
//t.exports = e
```