My_Code

Save meanings from www.urduenglishdictionary.ord

import java.net.*;

import java.io.*;

public class UrduEnglishDictionary

{

 static int i=0;

 public static void main(String[] args) throws Exception

 {// Run programm as JAVA UrduEnglishDictionary word page1 page2 outputfile.txt

  // A=English Alphabet; P1=Page1; P2=Page2

  // JAVA UrduEnglishDictionary B 1 5 b.txt

  // Output is saved in out.txt

  System.out.println(System.currentTimeMillis()/1000);

  for(i=Integer.parseInt(args[1]);i<=Integer.parseInt(args[2]) ;i++){

   new UrduEngDictThread("http://www.urduenglishdictionary.org/English-To-Urdu-Translation/"

       +args[0]+"/Page-"+i+".htm").savePageExtractToFile(args[3]);

  }

 }//main

}//test2

//----------------------------------------------------------------------

//void savePageExtractToFile(); By default saves in out.txt

//void savePageExtractToFile("out.txt");

//----------------------------------------------------------------------

class UrduEngDictThread extends Thread

{

 //public UrduEngDictThread(String URLString)

 //public void run()

 //public void savePageExtractToFile(String outFile)

 //public static String getMeaningsFromURL(String HTMLSourceURL)

 //public static String getMeanings(String HTMLSource)

 String URLString;

 //-----------------------------------------------------

 public UrduEngDictThread(String URLString)

 {

  super(URLString);

  this.URLString=URLString;

 }

 //-----------------------------------------------------

 public void run()

 {

  try

  {

   savePageExtractToFile("out.txt");

  }catch(Exception e){ }

 }

 //-----------------------------------------------------

 public void savePageExtractToFile(String outFile)

 //Uses getMeaningsFromURL(page URL): returns extracted meanings

 //Method over ridden for specifying out file name

 {

  try

  {

   Writer out2 = new BufferedWriter(new OutputStreamWriter( new FileOutputStream(outFile,true), "UTF8"));

   out2.write(getMeaningsFromURL(URLString));

   out2.close();

   System.out.println("Page:"+UrduEnglishDictionary.i+",Time:" +System.currentTimeMillis()/1000+" URL:"+URLString);

  }catch(Exception e){ }

 }

  //-----------------------------------------------------

  public static String getMeaningsFromURL(String HTMLSourceURL)

  {

   String inputLine="", outLine="";

   try

   {

     //System.out.println(System.currentTimeMillis()+"   Stream Opening");

     URL dictURL = new URL(HTMLSourceURL);

     BufferedReader dictURLIn = new BufferedReader(new InputStreamReader( dictURL.openStream() , "UTF-8"  ));

     //System.out.println(System.currentTimeMillis()+" Reading Started");

     while ((inputLine = dictURLIn.readLine()) != null)

     {

      outLine+=inputLine;

     }

     //System.out.println(System.currentTimeMillis()+"   Reading Complete");

     dictURLIn.close(); //internet stream closed

     //System.out.println(System.currentTimeMillis()+"  Stream closed: ");

   } catch(Exception e){}

   return getMeanings(outLine);

  }//getMeaningsFromURL

  //-----------------------------------------------------

  public static String getMeanings(String HTMLSource)

  {

   String outText="",tagStartText="",tagEndText="";

   int i, tagStartPos=0, tagEndPos=0;

   tagStartText="<td class='data-cell' align=left valign=top>";

   i=tagStartText.length();

   if (HTMLSource!=null)

   {

    while(HTMLSource.indexOf(tagStartText, tagEndPos)>0)

    {

    //Serial

    //outText+=getFieldFromHTML(HTMLSource,"<td class='data-cell' align=left valign=top>","</td>", tagEndPos)+ "|";

    tagStartText="<td class='data-cell' align=left valign=top>";

    tagEndText="</td>";

    i=tagStartText.length();

    tagStartPos = HTMLSource.indexOf(tagStartText, tagEndPos);

    tagEndPos = HTMLSource.indexOf(tagEndText,tagStartPos);

    outText+=HTMLSource.substring(tagStartPos+i, tagEndPos)+"|";

    //English Word

    //outText+=getFieldFromHTML(HTMLSource,"<td class='data-cell' align=left valign=top nowrap>","<sup>", tagEndPos)+ "|";

    tagStartText="<td class='data-cell' align=left valign=top nowrap>";

    tagEndText="<sup>";

    i=tagStartText.length();

    tagStartPos = HTMLSource.indexOf(tagStartText,tagEndPos);

    tagEndPos = HTMLSource.indexOf(tagEndText,tagStartPos);

    outText+=HTMLSource.substring(tagStartPos+i, tagEndPos)+ "|";

    //English Word Type

    //outText+=getFieldFromHTML(HTMLSource,"<span class='feature'>","<BR>", tagEndPos)+ "|";

    tagStartText="<span class='feature'>";

    tagEndText="<BR>";

    i=tagStartText.length();

    tagStartPos = HTMLSource.indexOf(tagStartText,tagEndPos);

    tagEndPos = HTMLSource.indexOf(tagEndText,tagStartPos);

    outText+=HTMLSource.substring(tagStartPos+i, tagEndPos)+ "|";

    //Urdu Word

    //outText+=getFieldFromHTML(HTMLSource,"<td class='urdu-cell' align=right valign=top>","</td>", tagEndPos)+ "\r\n";

    tagStartText="<td class='urdu-cell' align=right valign=top>";

    tagEndText="</td>";

    i=tagStartText.length();

    tagStartPos = HTMLSource.indexOf(tagStartText,tagEndPos);

    tagEndPos = HTMLSource.indexOf(tagEndText,tagStartPos);

    outText+=HTMLSource.substring(tagStartPos+i, tagEndPos)+ "\r\n";

    }//End for  while

   }//if HTMLSource=null

   //if(outText.length()>1000)return "xxxxx"; else return outText;

   return outText;

  }//getMeanings

  //-----------------------------------------------------

}//class