以 jsoup 來解析Yahoo奇摩字典查詢結果

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class ParseDictionary
{
    //seletor 的變數
    public Document doc;
   
    //被 seletor 蒐集到的 html 元素集合
    public Elements results;

   //主要程式執行區域
public static void main(String[] args)
{
    try
    {
       ParseDictionary obj = new ParseDictionary();
       obj.showResult("good");
    }
    catch(Exception e)
    {
       e.printStackTrace();
    }
}

//設定查詢文字
public void setParserConnect(String vocabulary)
{
    try
    {
       doc = Jsoup.connect("http://tw.dictionary.search.yahoo.com/search?p=" + vocabulary + "&fr2=dict").get();
       results = doc.select("ol li[class=result_cluster_first res]");
    }
    catch(Exception e)
    {
       e.printStackTrace();
    }
}

    //顯示測試結果
    public void showResult(String vocabulary)
    {
       try
       {
           //ParseDictionary parse = new ParseDictionary();
           this.setParserConnect( vocabulary );
          
           //抓取單字的詞性、解釋、例句
           Elements main_result = this.results.select("ul[class=explanation_wrapper] > li[class=explanation_pos_wrapper]");
           for(Element result : main_result )
           {
              System.out.println("詞性（英文）： " + result.select("h5[class=explanation_group_hd] > span[class=pos_abbr]").text() );
              System.out.println( "詞性（中文）" + result.select("h5[class=explanation_group_hd] > span[class=pos_desc]").text() );
             
              for(Element r : result.select("ol[class=explanation_ol] > li") )
              {
                  System.out.println( "解釋： " + r.select("p[class=explanation]").text() );
                  System.out.println( "例句： " + r.select("p[class=sample]").text() );
              }
             
              System.out.println();
              System.out.println();
           }
          
           //單字形態變化
           Elements diversity_result = this.results.select("ul[class=extra_wrapper] li").eq(0);
           System.out.println("動詞變化： " + diversity_result.select("div[class=extra_wordlist] > p:nth-child(1) span").eq(1).text() );
           System.out.println("複詞： " + diversity_result.select("div[class=extra_wordlist] > p:nth-child(2) span").eq(1).text() );
           System.out.println();
           System.out.println();
          
           //同義字
           System.out.println("同義字:";);
           Elements synonym_result = this.results.select("ul[class=extra_wrapper] li";).eq(1);
           for(Element synonym_r : synonym_result.select("div[class=extra_wordlist]") )
           {
               System.out.println( synonym_r.select("p").text() );
              for(Element synonym_rr : synonym_r.select("samp a") )
              {
                  System.out.println( synonym_rr.text() );
              }
           }
           System.out.println();
           System.out.println();
          
           //反義字
           System.out.println("反義字:");
           Elements antonym_result = this.results.select("ul[class=extra_wrapper] li").eq(2);
           for(Element antonym_r : antonym_result.select("div[class=extra_wordlist]") )
           {
               System.out.println( antonym_r.select("p").text() );
              for(Element antonym_rr : antonym_r.select("samp a") )
              {
                  System.out.println( antonym_rr.text() );
              }
           }
           System.out.println();
           System.out.println();      
       }
       catch(Exception e)
       {
           e.printStackTrace();
       }
    }
}