C#實現谷歌翻譯API


  由於谷歌翻譯官方API是付費版本,本着免費和開源的精神,分享一下用C#實現谷歌翻譯API的代碼。這個代碼非常簡單,主要分兩塊:通過WebRequest的方式請求內容;獲取Get方式的請求參數(難點在於tk的獲取)。注意該項目需要添加以下幾個引用:

System.Web

Newtonsoft.Json

MSScriptControl(com組件中的Microsoft Script Control 1.0)

一、WebRequest代碼

var webRequest = WebRequest.Create(url) as HttpWebRequest;

webRequest.Method = "GET";

webRequest.CookieContainer = cookie;

webRequest.Referer = referer;

webRequest.Timeout = 20000;

webRequest.Headers.Add("X-Requested-With:XMLHttpRequest");

webRequest.Accept = "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8";

webRequest.UserAgent = useragent;

  using (var webResponse = (HttpWebResponse)webRequest.GetResponse())
  {
   using (var reader = new StreamReader(webResponse.GetResponseStream(), Encoding.UTF8))
   {

    html = reader.ReadToEnd();
    reader.Close();
    webResponse.Close();
   }
  }

  

二、谷歌翻譯接口的實現

  1、抓包查看翻譯網絡請求,這里是用谷歌瀏覽器查看的網絡請求,如下圖:

 

 

   可以看到,請求方式是“Get”方式,后面跟的請求參數很多,如下圖:

  其中,最重要的參數有:sl--來源語言,一般設置為auto即自動檢測,tl--目標語言,你想翻譯成的語言,tk--ticket即使發車車票,谷歌就靠這個來防止我們免費調用的,這是本API最難的地方。

  2、tk的獲取

  在打開https://translate.google.com/頁面是,獲取到的HTML代碼中有如下一個TKK的值:

 

  直接在獲取的源代碼中用正則匹配出這個值:Regex re = new Regex(@"(?<=TKK=')(.*?)(?=')"),可以得到一個字符串:428502.368022592

 

  從監控的網絡中可以發現其中一個JS調用了這個TKK值,這個JS加了密進行混淆的,要破解這個JS需要扎實的基本功,以及足夠的耐心,我也是網上找的別人破解的JS代碼,親測可用,需將此代碼保存在gettk.js文檔中,方便調用:

var b = function (a, b) {
    for (var d = 0; d < b.length - 2; d += 3) {
        var c = b.charAt(d + 2),
            c = "a" <= c ? c.charCodeAt(0) - 87 : Number(c),
            c = "+" == b.charAt(d + 1) ? a >>> c : a << c;
        a = "+" == b.charAt(d) ? a + c & 4294967295 : a ^ c
    }
    return a
}

var tk =  function (a,TKK) {
    for (var e = TKK.split("."), h = Number(e[0]) || 0, g = [], d = 0, f = 0; f < a.length; f++) {
        var c = a.charCodeAt(f);
        128 > c ? g[d++] = c : (2048 > c ? g[d++] = c >> 6 | 192 : (55296 == (c & 64512) && f + 1 < a.length && 56320 == (a.charCodeAt(f + 1) & 64512) ? (c = 65536 + ((c & 1023) << 10) + (a.charCodeAt(++f) & 1023), g[d++] = c >> 18 | 240, g[d++] = c >> 12 & 63 | 128) : g[d++] = c >> 12 | 224, g[d++] = c >> 6 & 63 | 128), g[d++] = c & 63 | 128)
    }
    a = h;
    for (d = 0; d < g.length; d++) a += g[d], a = b(a, "+-a^+6");
    a = b(a, "+-3^+b+-f");
    a ^= Number(e[1]) || 0;
    0 > a && (a = (a & 2147483647) + 2147483648);
    a %= 1E6;
    return a.toString() + "." + (a ^ h)
}

  

  要得到tk只需要,運行tk這個函數,它有兩個輸入值:a為翻譯文本內容,TKK是上文正則匹配得到的JS字符串執行的結果值。為方便在C#中執行JS,封裝了一個能執行JS的函數,如下:

        /// <summary>
        /// 執行JS
        /// </summary>
        /// <param name="sExpression">參數體</param>
        /// <param name="sCode">JavaScript代碼的字符串</param>
        /// <returns></returns>
        private string ExecuteScript(string sExpression, string sCode)
        {
            MSScriptControl.ScriptControl scriptControl = new MSScriptControl.ScriptControl();
            scriptControl.UseSafeSubset = true;
            scriptControl.Language = "JScript";
            scriptControl.AddCode(sCode);
            try
            {
                string str = scriptControl.Eval(sExpression).ToString();
                return str;
            }
            catch (Exception ex)
            {
                string str = ex.Message;
            }
            return null;
        }      

  

  3、實現翻譯的完整代碼

using System;
using System.IO;
using System.Net;
using System.Text;
using System.Text.RegularExpressions;
using MSScriptControl;
using System.Web;

namespace GoogleTranslate
{
    public class Translate
    {
        /// <summary>
        /// 谷歌翻譯
        /// </summary>
        /// <param name="text">待翻譯文本</param>
        /// <param name="fromLanguage">自動檢測:auto</param>
        /// <param name="toLanguage">中文:zh-CN,英文:en</param>
        /// <returns>翻譯后文本</returns>
        public string GoogleTranslate(string text, string fromLanguage, string toLanguage)
        {
            CookieContainer cc = new CookieContainer();

            string GoogleTransBaseUrl = "https://translate.google.com/";

            var BaseResultHtml = GetResultHtml(GoogleTransBaseUrl, cc, "");

            Regex re = new Regex(@"(?<=TKK=')(.*?)(?=')");

            var TKK = re.Match(BaseResultHtml).ToString();//在返回的HTML中正則匹配TKK的值

            var GetTkkJS = File.ReadAllText("./gettk.js");

            var tk = ExecuteScript("tk(\"" + text + "\",\"" + TKK + "\")", GetTkkJS);

            string googleTransUrl = "https://translate.google.com/translate_a/single?client=t&sl=" + fromLanguage + "&tl=" + toLanguage + "&hl=en&dt=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca&dt=rw&dt=rm&dt=ss&dt=t&ie=UTF-8&oe=UTF-8&otf=1&ssel=0&tsel=0&kc=1&tk=" + tk + "&q=" + HttpUtility.UrlEncode(text);

            var ResultHtml = GetResultHtml(googleTransUrl, cc, "https://translate.google.com/");

            dynamic TempResult = Newtonsoft.Json.JsonConvert.DeserializeObject(ResultHtml);

            string ResultText = Convert.ToString(TempResult[0][0][0]);

            return ResultText;
        }

        public string GetResultHtml(string url, CookieContainer cookie, string referer)
        {
            var html = "";

            var webRequest = WebRequest.Create(url) as HttpWebRequest;

            webRequest.Method = "GET";

            webRequest.CookieContainer = cookie;

            webRequest.Referer = referer;

            webRequest.Timeout = 20000;

            webRequest.Headers.Add("X-Requested-With:XMLHttpRequest");

            webRequest.Accept = "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8";

            webRequest.UserAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36";

            using (var webResponse = (HttpWebResponse)webRequest.GetResponse())
            {
                using (var reader = new StreamReader(webResponse.GetResponseStream(), Encoding.UTF8))
                {

                    html = reader.ReadToEnd();
                    reader.Close();
                    webResponse.Close();
                }
            }
            return html;
        }

        /// <summary>
        /// 執行JS
        /// </summary>
        /// <param name="sExpression">參數體</param>
        /// <param name="sCode">JavaScript代碼的字符串</param>
        /// <returns></returns>
        private string ExecuteScript(string sExpression, string sCode)
        {
            MSScriptControl.ScriptControl scriptControl = new MSScriptControl.ScriptControl();
            scriptControl.UseSafeSubset = true;
            scriptControl.Language = "JScript";
            scriptControl.AddCode(sCode);
            try
            {
                string str = scriptControl.Eval(sExpression).ToString();
                return str;
            }
            catch (Exception ex)
            {
                string str = ex.Message;
            }
            return null;
        }
    }
}

  

 


免責聲明!

本站轉載的文章為個人學習借鑒使用,本站對版權不負任何法律責任。如果侵犯了您的隱私權益,請聯系本站郵箱yoyou2525@163.com刪除。



 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM