execjs使用体验

把前端代码抠出来,进行本地运行解析参数,这也就是知云翻译所用的方法吧~
转载链接地址

import requests
import re
import execjs


class BaiduTranslateSpider(object):
    def __init__(self):
        self.token_url = 'https://fanyi.baidu.com/?aldtype=16047'
        self.post_url = 'https://fanyi.baidu.com/v2transapi'
        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': 'no-cache',
            'cookie': 'BAIDUID=52920E829C1F64EE98183B703F4E37A9:FG=1; BIDUPSID=52920E829C1F64EE98183B703F4E37A9; PSTM=1562657403; 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; delPer=0; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; BCLID=6890774803653935935; BDSFRCVID=4XAsJeCCxG3DLCbwbJrKDGwjNA0UN_I3KhXZ3J; H_BDCLCKID_SF=tRk8oIDaJCvSe6r1MtQ_M4F_qxby26nUQ5neaJ5n0-nnhnL4W46bqJKFLtozKMoI3C7fotJJ5nololIRy6CKjjb-jaDqJ5n3bTnjstcS2RREHJrg-trSMDCShGRGWlO9WDTm_D_KfxnkOnc6qJj0-jjXqqo8K5Ljaa5n-pPKKRAaqD04bPbZL4DdMa7HLtAO3mkjbnczfn02OP5P5lJ_e-4syPRG2xRnWIvrKfA-b4ncjRcTehoM3xI8LNj405OTt2LEoDPMJKIbMI_rMbbfhKC3hqJfaI62aKDs_RCMBhcqEIL4eJOIb6_w5gcq0T_HttjtXR0atn7ZSMbSj4Qo5pK95p38bxnDK2rQLb5zah5nhMJS3j7JDMP0-4rJhxby523i5J6vQpnJ8hQ3DRoWXPIqbN7P-p5Z5mAqKl0MLIOkbC_6j5DWDTvLeU7J-n8XbI60XRj85-ohHJrFMtQ_q4tehHRMBUo9WDTm_DoTttt5fUj6qJj855jXqqo8KMtHJaFf-pPKKRAashnzWjrkqqOQ5pj-WnQr3mkjbn5yfn02OpjPX6joht4syPRG2xRnWIvrKfA-b4ncjRcTehoM3xI8LNj405OTt2LEoC0XtIDhMDvPMCTSMt_HMxrKetJyaR0JhpjbWJ5TEPnjDUOdLPDW-46HBM3xbKQw5CJGBf7zhpvdWhC5y6ISKx-_J68Dtf5; ZD_ENTRY=baidu; PSINO=2; H_PS_PSSID=26525_1444_21095_29578_29521_28518_29098_29568_28830_29221_26350_29459; locale=zh; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1563426293,1563996067; 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; Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1563999768; yjs_js_security_passport=2706b5b03983b8fa12fe756b8e4a08b98fb43022_1563999769_js',
            'pragma': 'no-cache',
            'upgrade-insecure-requests': '1',
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36',}

    # 获取token和gtk
    def get_token(self):
        # 定义请求头
        r = requests.get(self.token_url, headers=self.headers)
        token = re.findall(r"token: '(.*?)'", r.text)
        window_gtk = re.findall(r"window.*?gtk = '(.*?)';</script>", r.text)
        if token:
            return token[0], window_gtk[0]

    # 获取sign
    def get_sign(self, word, gtk):
        with open('translate.js', 'r',encoding='utf-8') as f:
            js_data = f.read()

        exec_object = execjs.compile(js_data)
        sign = exec_object.eval('e("{}","{}")'.format(word, gtk))

        return sign

    # 主函数
    def main(self, word, fro, to):
        token, gtk = self.get_token()
        sign = self.get_sign(word, gtk)
        # 找到form表单数据如下,sign和token需要想办法获取
        form_data = {
            'from': fro,
            'to': to,
            'query': word,
            'transtype': 'realtime',
            'simple_means_flag': '3',
            'sign': sign,
            'token': token
        }
        r = requests.post(self.post_url, data=form_data, headers=self.headers)
        print(r.json()['trans_result']['data'][0]['dst'])


if __name__ == '__main__':
    spider = BaiduTranslateSpider()
    choice = input('1. 英译汉 2. 汉译英 : ')
    word = input('请输入要翻译的单词:')
    if choice == '1':
        fro, to = 'en', 'zh'
    elif choice == '2':
        fro, to = 'zh', 'en'

    spider.main(word, fro, to)
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] || "") || "";
 //    String.fromCharCode(103)="g"
 //    String.fromCharCode(103)="t"
 //    String.fromCharCode(103)="k"
 //    window.gtk也就是从网页源码中取值
 //    进入函数断点调试
    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)
}
  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
PyExecJS是一个Python库,用于在本地运行JavaScript代码。它可以通过使用不同的JavaScript环境(如Node.js、PyV8、PhantomJS等)来执行代码。对于需要理解和处理经过混淆的前端JS代码,PyExecJS是一个很好的选择。你可以按照以下步骤在PyCharm中配置和使用PyExecJS: 1. 首先,安装Node.js作为JS环境。你可以从Node.js官方网站下载并安装最新版本。 2. 确保将Node.js添加到系统环境变量中。你可以在cmd中输入`node -v`来检查是否配置成功。 3. 在PyCharm中安装Node.js插件。打开“Settings | Plugins”,搜索并下载NodeJS插件。 4. 在“Settings | Languages & Frameworks| Node.js and NPM”中查看当前安装的Node.js路径。 5. 使用pip安装PyExecJS库:`pip install PyExecJS`。 6. 创建一个JS文件,例如`show.js`,其中包含你想要执行的JavaScript代码。 7. 在Python代码中导入`execjs`模块,并使用`execjs.compile()`方法加载和编译JS文件。 8. 使用`loader.call()`方法调用JS文件中的函数,并将结果返回。 以下是一个示例代码: ```python import execjs def my(sentence): # 读取js文件 with open('show.js', 'r', encoding='utf-8') as f: reader = f.read() # 加载编译读取内容 loader = execjs.compile(reader) # 调用js文件中的方法 result = loader.call('say', sentence) # 返回结果 return result if __name__ == '__main__': # 调用方法 print(my('What can you do any Kung Fu, John?')) ``` 请确保在运行代码之前,已经创建了一个名为`show.js`的JS文件,并在其中定义了一个名为`say`的函数。

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值