通过urllib库爬取百度翻译，实现中文翻译为英文，英文翻译为中文

# -*- conding: utf-8 -*-
"""
使用post请求，调用百度翻译
使用的是:
urllib.request.Request
urllib.request.urlopen()
urllib.request.urlencode()
urlopen()方法中的url参数可以是字符串，也可以是一个Request对象

文中需要js加密，来自下面大佬链接
https://www.cnblogs.com/share-record/p/10724408.html
"""
import urllib
from urllib.request import Request, urlopen
from urllib.parse import urlencode
import json
import ssl
import execjs



"""
当出现报错：<urlopen error [SSL: BAD_SIGNATURE] bad signature (_ssl.c:1056)>
可多尝试几次，或者将下面的这行代再复制一行
"""
ssl._create_default_https_context = ssl._create_unverified_context    # 这是加密，不加会提示SSL类型的错误
query = input("请输入要翻译的英文: ")

# 定义请求头，里面必需要有user-agent和cookie，这个是不会改变的
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36',
    'cookie': 'BIDUPSID=D2B8972B8BB529C1B149B966F9B10202; PSTM=1587293381; BAIDUID=D2B8972B8BB529C11EEF8BCDFF44331C:FG=1; REALTIME_TRANS_SWITCH=1; FANYI_WORD_SWITCH=1; SOUND_SPD_SWITCH=1; HISTORY_SWITCH=1; SOUND_PREFER_SWITCH=1; MCITY=-194%3A; BDUSS=WJHbEdIflh1aVJENDBCcXRNMmM1STA2TnQtcDQxdkI3flhPSloyZ1FKNFhBckpmSVFBQUFBJCQAAAAAAAAAAAEAAABGOVyv0MTW0LXExMe49rXItP0AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABd1il8XdYpfQ; BDUSS_BFESS=WJHbEdIflh1aVJENDBCcXRNMmM1STA2TnQtcDQxdkI3flhPSloyZ1FKNFhBckpmSVFBQUFBJCQAAAAAAAAAAAEAAABGOVyv0MTW0LXExMe49rXItP0AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABd1il8XdYpfQ; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1603121480,1603721041,1604501323,1604501345; H_PS_PSSID=32819_1462_33038_32951_33061_31254_32723_32962_32957; BDRCVFR[feWj1Vr5u3D]=I67x6TjHwwYf0; delPer=0; PSINO=6; Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1605285352; __yjsv5_shitong=1.0_7_9f5a013d775e541fd4462b27e1c97346b19e_300_1605285353200_183.37.158.56_c7ed83fa; yjs_js_security_passport=7a93f32a61e5ab0509acdf625c875bb417862a4a_1605285354_js'
}
def create_sign(query):
    # 这里为js加密，暂时没有看懂
    jsCode = """
        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
        }
        var i = null;
        function e(r) {
            var t = r.length;
            t > 30 && (r = "" + r.substr(0, 10) + r.substr(Math.floor(t / 2) - 5, 10) + r.substr(-10, 10))
    
            var u = void 0, l = "" + String.fromCharCode(103) + String.fromCharCode(116) + String.fromCharCode(107);
    
            u = null !== i ? i : (i = '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)
        }
        """
    sign = execjs.compile(jsCode).call('e', query)
    return sign


def is_Chinese():
    """
    这里时判断输入的是否为中文，为中文返回True，否则返回Flase
    """

    for ch in query:
        if '\u4e00' <= ch <= '\u9fff':
            return True
    return False

# 定义执行函数
def fanyi():
    """
    data参数是一个字节（byte）类型
    query:  为要翻译的英文，这里为英译中，输入中文不能翻译为英文
    params： 参数必须要添加,这是传参  From和To指的是从什么语言翻译到什么语言，zh：表示中文；en：表示英文
    data：   是将params转换为字节类型，传参只支持字节(byte)类型
    res：    为调用urllib中的request中的Request方法，使用的是POST请求方式，返回的是是一个<urllib.request.Request object at 0x0000028FAE4E5BE0>
    resp:    通过urllib中的request中的urlopen方式去打开返回的一个Request对象,返回的是一个<http.client.HTTPResponse object at 0x000002256D154E48>
    respones: 读取urlopen返回的一个HTTPResponse对象，将其转化为可阅读的一个json格式,但是存在一个编码的问题，我们再通过json的loads方法
    将编码转化为utf-8格式的，便于阅读


    """
    if is_Chinese():
        From  = 'zh'
        To = 'en'
    else:
        From = 'en'
        To = 'zh'
    url = 'https://fanyi.baidu.com/v2transapi?from={}&to={}'.format(From, To)  # 这是百度翻译的url
    sign = create_sign(query)
    params = {
        'from': From,
        'query': query,
        'to': To,
        'token': '186f535b2be9fd3f2abbc75dc3fa63e4',
        'sign': sign
    }
    try:
        data = bytes(urlencode(params), encoding='utf-8')
        res = Request(url, data=data, headers=headers, method='POST')
        resp = urlopen(res)
        respones = resp.read()
        respones = json.loads(respones.decode('utf-8'))
    except Exception as Error:
        print('请求时错误！！！您的请求返回\n %s' %(Error))
        exit()
    try:
        translation = respones['trans_result']['data'][0]['dst']
        print('您想要翻译的 %s 的译文是 %s' %(query, translation))
        print(respones)
    except Exception as Error:
        print('请求错误！！！您请求获取到的值为：\n%s' %(respones))


if __name__ == '__main__':
    fanyi()