用新版的Yahoo宝贝鱼(Babel Fish)做自己的翻译器(防乱码)

本文链接：https://blog.youkuaiyun.com/superlw/article/details/1733620

本文介绍了如何利用新版Yahoo Babel Fish构建自己的翻译器。由于Google Translate的限制，作者转向了Yahoo Babel Fish，并发现需要在Java中设置特定的User-Agent才能正确处理中文。代码示例展示了如何进行URL编码、设置请求头以及获取翻译内容，从而避免中文乱码问题。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

很多系统中需要做自己的翻译器,所以大家都想到把现成的网站扒下来用,Google Translate和Yahoo Babel Fish就成了大家的首选.Google好说,直接用HttpURLConnection做post请求即可,但是Google防盗措施非常好,用个几次就出现一个防盗链的页面,就无法玩了,所以Yahoo Babel Fish就成了大家的选择.但是发现最新版本的宝贝鱼用HttpURLConnection怎么请求,怎么设置编码方式得到的中文都是乱码.后来发现,在java中必须设置connection.setRequestProperty( "User-agent" , "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; .NET CLR 1.1.4322; .NET CLR 2.0.50215; fqSpider)" );才能得到正确的中文显示,c#中同样.还需要注意的是,在输入的link中是中文的话,除了用java.net.URLEncoder.encode编码外还需要在link中加入&ei=gb2312.下面是全部编码.

import java.io.*;
import java.net.*;

public class Yahoo {

static final String yahooUrl ="http://babelfish.yahoo.com.cn/translate_txt";

public String yahootranslate(String query,String lang) throws MalformedURLException,IOException,UnsupportedEncodingException
    {
     String urlstr = yahooUrl;
     String content=null;
     try{
      content=getHtmlContent(urlstr,"trtext=" + encodeText(query) + "&lp=" + lang+"&ei=gb2312","UTF-8");
     }catch(Exception e){}
     return getyahooContent(content).trim();
    }


    private String getyahooContent(String htmltext) {

          String ss = "<div id=/"pd/" class=/"pd/">" ;
          String se = "</div>" ;
           int ssidx = htmltext.indexOf(ss);
           int seidx = htmltext.indexOf(se,ssidx);

          if(ssidx<0)return null;
          String restr = htmltext.substring(ssidx + ss.length(),seidx);
           return restr;
      }

    private String getHtmlContent(String _url,String _post,String _charset) throws Exception
    {
    String post=null;
    URLConnection connection=null;
    Proxy proxy=null;

        URL url =   new URL(_url);

  if(proxy!=null)connection = (HttpURLConnection)url.openConnection(proxy);
  else connection = (HttpURLConnection)url.openConnection();
     connection.setRequestProperty( "User-agent" , "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; .NET CLR 1.1.4322; .NET CLR 2.0.50215; fqSpider)" );
     connection.setDoInput(true);
     connection.setDoOutput(true);

     connection.connect();
     OutputStreamWriter out = new
     OutputStreamWriter(connection.getOutputStream(),"UTF-8");
     out.write(_post);
     //     remember to clean up
     out.flush();
     out.close();

     String charset = _charset;
     BufferedReader in = new BufferedReader( new
     InputStreamReader(connection.getInputStream(),charset)); // 使用指定编码接收数据

     String line = null ;
     StringBuilder sb = new StringBuilder();
     while ((line = in.readLine()) != null ) {
        sb.append(line);
     }
     in.close();

     return sb.toString();
    }

public static String encodeText(String text) {
   String str = java.net.URLEncoder.encode(text);
    return str;
}

public static void main(String[] args) throws Exception{
  Yahoo yahoo=new Yahoo();

//中->英
System.out.println(yahoo.yahootranslate("你好吗?","zh_en"));

//英->中

System.out.println(yahoo.yahootranslate("hello China","en_ch"));

}