python调用百度翻译、谷歌翻译

谷歌翻译不提供接口，想要使用谷歌的翻译结果，需要借用爬虫技术，将待翻译的文本传入，抓取页面，解析出翻译结果，经测试，这种方法的翻译效果较差，不建议使用。
百度翻译提供接口，可在百度翻译注册开发者后获取appid与secretKey直接在python中进行调用，这种方法翻译效果较好，但仍存在一些问题，对于那些翻译不太好的文本，只能手动复制到谷歌翻译或必应翻译中进行翻译。

#-*-coding:utf-8-*-
# date: 2018-11-07
import requests
import json
import execjs
import hashlib
import urllib
import random
#需要先用pip install pyexecjs 安装，用来执行js脚本

class Py4Js():
    def __init__(self):
        self.ctx = execjs.compile(""" 
            function TL(a) { 
            var k = ""; 
            var b = 406644; 
            var b1 = 3293161072;       
            var jd = "."; 
            var $b = "+-a^+6"; 
            var Zb = "+-3^+b+-f";    
            for (var e = [], f = 0, g = 0; g < a.length; g++) { 
                var m = a.charCodeAt(g); 
                128 > m ? e[f++] = m : (2048 > m ? e[f++] = m >> 6 | 192 : (55296 == (m & 64512) && g + 1 < a.length && 56320 == (a.charCodeAt(g + 1) & 64512) ? (m = 65536 + ((m & 1023) << 10) + (a.charCodeAt(++g) & 1023), 
                e[f++] = m >> 18 | 240, 
                e[f++] = m >> 12 & 63 | 128) : e[f++] = m >> 12 | 224, 
                e[f++] = m >> 6 & 63 | 128), 
                e[f++] = m & 63 | 128) 
            } 
            a = b; 
            for (f = 0; f < e.length; f++) a += e[f], 
            a = RL(a, $b); 
            a = RL(a, Zb); 
            a ^= b1 || 0; 
            0 > a && (a = (a & 2147483647) + 2147483648); 
            a %= 1E6; 
            return a.toString() + jd + (a ^ b) 
          };      
          function RL(a, b) { 
            var t = "a"; 
            var Yb = "+"; 
            for (var c = 0; c < b.length - 2; c += 3) { 
                var d = b.charAt(c + 2), 
                d = d >= t ? d.charCodeAt(0) - 87 : Number(d), 
                d = b.charAt(c + 1) == Yb ? a >>> d: a << d; 
                a = b.charAt(c) == Yb ? a + d & 4294967295 : a ^ d 
            } 
            return a 
          } 
        """)
    def getTk(self, text):
        '''google translate请求参数中tk值是根据内容实时变化的，是由js动态生成，因此此函数调用js代码执行后返回text对应的tk值'''
        return self.ctx.call("TL", text)

def buildUrl(text, tk):
    baseUrl = 'https://translate.google.cn/translate_a/single'
    baseUrl += '?client=t&'
    baseUrl += 's1=auto&'
    baseUrl += 't1=zh-CN&'
    baseUrl += 'h1=zh-CN&'
    baseUrl += 'dt=at&'
    baseUrl += 'dt=bd&'
    baseUrl += 'dt=ex&'
    baseUrl += 'dt=ld&'
    baseUrl += 'dt=md&'
    baseUrl += 'dt=qca&'
    baseUrl += 'dt=rw&'
    baseUrl += 'dt=rm&'
    baseUrl += 'dt=ss&'
    baseUrl += 'dt=t&'
    baseUrl += 'ie=UTF-8&'
    baseUrl += 'oe=UTF-8&'
    baseUrl += 'otf=1&'
    baseUrl += 'pc=1&'
    baseUrl += 'ssel=0&'
    baseUrl += 'tsel=0&'
    baseUrl += 'kc=2&'
    baseUrl += 'tk=' + str(tk) + '&'
    baseUrl += 'q=' + text
    return baseUrl

def google_translate(text):
    js = Py4Js()
    header = {
        'authority':'translate.google.cn',
        'method':'GET',
        'path':'',
        'scheme':'https',
        'accept':'*/*',
        'accept-encoding':'gzip, deflate, br',
        'accept-language':'zh-CN,zh;q=0.9',
        'cookie':'',
        'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64)  AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36',
        'x-client-data':'CIa2yQEIpbbJAQjBtskBCPqcygEIqZ3KAQioo8oBGJGjygE='
    }
    url = buildUrl(text, js.getTk(text))
    res = ''
    try:
        r = requests.get(url)
        result = json.loads(r.text)
        if result[7] != None:
            # 如果我们文本输错，提示你是不是要找xxx的话，那么重新把xxx正确的翻译之后返回
            # 谷歌返回的结果是一个json格式的数据，我们将其变成一个嵌套的list，可以发现该list长度为9，第零个元素就是翻译结果,第七个结果是一些提示信息。
            try:
                correctText=result[7][0].replace('<b><i>', ' ').replace('</i></b>', '')
                print(correctText)
                correctUrl=buildUrl(correctText,js.getTk(correctText))
                correctR=requests.get(correctUrl)
                newResult=json.loads(correctR.text)
                res=newResult[0][0][0]
            except Exception as e:
                print(e)
                res = result[0][0][0]
        else:
            res = result[0][0][0]
    except Exception as e:
        res = ''
        print(url)
        print("翻译"+text+"失败")
        print("错误信息:")
        print(e)
    finally:
        return res

def baidu_translate(text, from_lang='auto', to_lang='zh', appid = 'your appid', secretKey = 'your secretKey'):
    url = 'https://api.fanyi.baidu.com/api/trans/vip/translate'
    salt = random.randint(32768, 65536)
    sign = appid + text + str(salt) + secretKey
    m = hashlib.md5()
    m.update(sign.encode("utf8"))
    sign = m.hexdigest()
    url = url + '?appid=' + appid + '&q=' + urllib.parse.quote(text) + '&from=' + from_lang + '&to=' + to_lang + '&salt=' + str(salt) + '&sign=' + sign
    try:
        result = eval(requests.get(url).text)
        result = result['trans_result'][0]['dst']
    except Exception as e:
        result = ''
        print (e)
    finally:
        return result

if __name__ == '__main__':
    res = google_translate('oh shit')
    print(res)

参考：

1. https://www.imooc.com/article/35255