Python3调谷歌翻译

公司最近有翻译的需求（本人适用的是在第三方服务器上使用，不在本地也不在谷歌控制台），发现Google的Translate API只能FQ调，但是国内也有翻译需求，经多方查找汇集众家之长，找到一个感觉最好用的，稍稍改进了一下，

一。国内爬虫版（主要参考https://blog.csdn.net/andeyeluguo/article/details/78581590）：

很多博客有提到tk值要js处理，不多说，直接上干货

首先，是要pip处理js的模块  

pip install PyExecJS

创建HandleJs.py

import execjs  
  
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):  
        return self.ctx.call("TL",text)

创建main.py

import json
import urllib.request
import urllib.parse
from HandleJs import Py4Js


def open_url(url):
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
    req = urllib.request.Request(url=url, headers=headers)
    response = urllib.request.urlopen(req)
    data = response.read().decode('utf-8')
    return data


def buildUrl(content, tk, tl):
    baseUrl = 'http://translate.google.cn/translate_a/single'
    baseUrl += '?client=t&'
    baseUrl += 'sl=auto&'
    baseUrl += 'tl=' + str(tl) + '&'
    baseUrl += 'hl=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 += 'clearbtn=1&'
    baseUrl += 'otf=1&'
    baseUrl += 'pc=1&'
    baseUrl += 'srcrom=0&'
    baseUrl += 'ssel=0&'
    baseUrl += 'tsel=0&'
    baseUrl += 'kc=2&'
    baseUrl += 'tk=' + str(tk) + '&'
    baseUrl += 'q=' + content
    return baseUrl


def translate(content, tk, tl):
    content = urllib.parse.quote(content)
    url = buildUrl(content, tk, tl)

    result = open_url(url)
    res_json = json.loads(result)
    trans_text = res_json[0][0][0]
    # sl是要翻译的源语种
    sl = res_json[8][0][0]
    print(trans_text)
    print(sl)


def main():
    js = Py4Js()
    #content是要翻译的内容
    #tl是要翻译的目标语种，值参照ISO 639-1标准，如果翻译成中文"zh/zh-CN简体中文"
    content = "test"
    tl = "ja"
    tk = js.getTk(content)
    translate(content, tk, tl)


if __name__ == "__main__":
    main()

 二。谷歌API调用

谷歌控制台创建项目，绑定信用卡（翻译API收费），绑定项目和账号，启用Translation API，创建service account（这部分可以参考 https://blog.csdn.net/nicolelili1/article/details/76973097 的一-五），然后

首先还是pip Google translation SDK

pip install --upgrade google-cloud-translate

翻译的代码（指定credentials）

from google.cloud import translate
    from google.oauth2 import service_account
    credentials = service_account.Credentials.from_service_account_file('Key.json')

    translate_client = translate.Client(credentials=credentials)
    translation = translate_client.translate(
        text,
        target_language=target_lang)
    print(translation)

ok啦

 三。谷歌API调用

转了一大圈，发现自己走了很多弯路，此方法最为便捷，但是也有安全隐患（有明文的Key）

代码

import urllib.request
import urllib.parse
key = "**********" #你的API Key
content = urllib.parse.quote(text)
url = "https://translation.googleapis.com/language/translate/v2?key=%s&target=%s&q=%s" % (key, target_lang, content)
response = urllib.request.urlopen(url)
data = json.loads(response.read().decode('utf-8'))
res = data['data']['translations'][0]
print(res)

 附AWS的翻译(不过目前只有3个region有这个功能)：

import boto3
client = boto3.client('translate', region_name='us-east-1')
result = client.translate_text(
    Text=text,
    SourceLanguageCode=source_lang if source_lang else 'auto',
    TargetLanguageCode=target_lang
)

 

参考链接：

https://blog.csdn.net/andeyeluguo/article/details/78581590

https://blog.csdn.net/nicolelili1/article/details/76973097

https://cloud.google.com/translate/docs/quickstart-client-libraries

https://googleapis.github.io/google-cloud-python/latest/translate/usage.html

http://iamct.iteye.com/blog/952558