Examples of org.htmlcleaner.HtmlCleaner

org.htmlcleaner.HtmlCleaner
te an instance of HtmlCleaner HtmlCleaner cleaner = new HtmlCleaner(); // take default cleaner properties CleanerProperties props = cleaner.getProperties(); // customize cleaner's behaviour with property setters props.setXXX(...); // Clean HTML taken from simple string, file, URL, input stream, // input source or reader. Result is root node of created // tree-like structure. Single cleaner instance may be safely used // multiple times. TagNode node = cleaner.clean(...); // optionally find parts of the DOM or modify some nodes TagNode[] myNodes = node.getElementsByXXX(...); // and/or Object[] myNodes = node.evaluateXPath(xPathExpression); // and/or aNode.removeFromTree(); // and/or aNode.addAttribute(attName, attValue); // and/or aNode.removeAttribute(attName, attValue); // and/or cleaner.setInnerHtml(aNode, htmlContent); // and/or do some other tree manipulation/traversal // serialize a node to a file, output stream, DOM, JDom... new XXXSerializer(props).writeXmlXXX(aNode, ...); myJDom = new JDomSerializer(props, true).createJDom(aNode); myDom = new DomSerializer(props, true).createDOM(aNode);

  public static void main(String[] args) throws Exception 
  {
      Translator.load( "es");
      
      // create an instance of HtmlCleaner
    HtmlCleaner cleaner = new HtmlCleaner();


    // take default cleaner properties
    CleanerProperties props = cleaner.getProperties();


    // customize cleaner's behaviour with property setters
//    props.setXXX(...);


    // Clean HTML taken from simple string, file, URL, input stream, 
    // input source or reader. Result is root node of created 
    // tree-like structure. Single cleaner instance may be safely used
    // multiple times.
//    TagNode node = cleaner.clean( new File("tests/accept.html"));


    TagNode node = cleaner.clean( new File("tests/materias.html"));


    Village village = new Village();
        IOVillage.updateVillageOverview( village);
        System.out.println( village);

View Full Code Here

    public static void updatePlayers( Ally ally) throws Exception
    {
        // 1. get ally
      String page = HttpServer.getHttpServer().httpGetPage( "http://s3.travian.net/allianz.php?aid=" + ally.getId());
        
        HtmlCleaner cleaner = new HtmlCleaner();
        CleanerProperties props = cleaner.getProperties();
        props.setRecognizeUnicodeChars( true);
//        TagNode node = cleaner.clean( new File("tests/ally.html"));
        TagNode node = cleaner.clean( page);


        updatePlayers( ally, node);
       
    }

View Full Code Here


public class IOVillage 
{
  public static void updateVillageOverview( Village village) throws Exception
  {
    HtmlCleaner cleaner = new HtmlCleaner();
//    CleanerProperties props = cleaner.getProperties();
//    props.setRecognizeUnicodeChars( true);
    TagNode node = cleaner.clean( new File("tests/overview3.html"));


    updateTerrains(village, node);
    updateStorage( village, node);
    updateProductionRate( village, node);
    updateServerTimestamp( village, node);

View Full Code Here

    {
        // 1. get overview/innerview pantalla actual
      String page = HttpServer.getHttpServer().httpGetPage( "http://s3.travian.net/spieler.php?uid=" + player.getId());
      Thread.sleep( (long) (1000 + 3000*Math.random()));


        HtmlCleaner cleaner = new HtmlCleaner();
        CleanerProperties props = cleaner.getProperties();
        props.setRecognizeUnicodeChars( true);
//        TagNode node = cleaner.clean( new File("tests/perfil.html"));
        TagNode node = cleaner.clean( page);


        updateMapVillages2( player, node);


    }

View Full Code Here

  public static void updateVillages( Villages villages) throws Exception 
  {
    // 1. get overview/innerview pantalla actual
//    String page = HttpServer.getHttpServer().httpGetPage( "http://s3.travian.net/dorf1.php");
      
    HtmlCleaner cleaner = new HtmlCleaner();
    CleanerProperties props = cleaner.getProperties();
    props.setRecognizeUnicodeChars( true);
        TagNode node = cleaner.clean( new File("tests/overview8.html"));
//        TagNode node = cleaner.clean( page);


        updateVillages2( villages, node);


  }

View Full Code Here

  public static Troops getTroops( Village village) throws Exception 
  {
    // 1. goto village
    // 2. goto inner village
    // 3. goto rally point
    HtmlCleaner cleaner = new HtmlCleaner();
    TagNode node = cleaner.clean( new File("tests/materias.html"));


    int  numNode = 0;
        Object[] domTroops = node.evaluateXPath( "//div[@id='content']//table");
        for( Object t : domTroops) {
          if( t instanceof TagNode) {

View Full Code Here

    {
        // 1. get standard map
        // 2. goto (x,y)
//        String page = HttpServer.getHttpServer().getMapPage( coordX, coordY);
        
        HtmlCleaner cleaner = new HtmlCleaner();
        CleanerProperties props = cleaner.getProperties();
        props.setRecognizeUnicodeChars( true);
        TagNode node = cleaner.clean( new File("tests/karte.htm"));
//        TagNode node = cleaner.clean( page);


        return getSquareUrl2( node);
    }

View Full Code Here

    {
        // 1. get overview/innerview pantalla actual
//        String page =  HttpServer.getHttpServer().httpGetPage( url.toString().replace( "&amp;", "&"));
        Thread.sleep( (long) (1000 + 2000*Math.random()));
        
        HtmlCleaner cleaner = new HtmlCleaner();
        CleanerProperties props = cleaner.getProperties();
        props.setRecognizeUnicodeChars( true);
        TagNode node = cleaner.clean( new File("tests/karte_village.htm"));
//        TagNode node = cleaner.clean( page);


        return getSquareType2( node);


    }

View Full Code Here

    recherche(source);
  }
  
  public void recherche(String lien) throws MalformedURLException, IOException, XPatherException 
  {
    HtmlCleaner cleaner = new HtmlCleaner();
    TagNode node = cleaner.clean(new URL(lien));
    info = new String();
    int count = 0;
    
    for (Object o : node.evaluateXPath("//body//p")) 
    {

View Full Code Here

    props.setAdvancedXmlEscape(true);
    props.setTransResCharsToNCR(true);
    props.setTranslateSpecialEntities(true);
    props.setTransSpecialEntitiesToNCR(true);
    
    HtmlCleaner cleaner = new HtmlCleaner(props);
      
    TagNode node = cleaner.clean(new URL(lien));
    //System.out.println("Title: " + ((TagNode)(node.evaluateXPath("//title")[0])).getText());
    for (Object o : node.evaluateXPath("//ul[@id='acces_1']//li/a")) 
    {
      String dUrl = ((TagNode)(o)).getAttributeByName("href");
      //System.out.println("LI: " + org.apache.commons.lang3.StringEscapeUtils.unescapeHtml4(((TagNode)(o)).getText().toString()));

View Full Code Here

0 1 2 3 4 5

TOP

Related Classes of org.htmlcleaner.HtmlCleaner

at.newmedialab.ldpath.model.functions.CleanHtmlFunction

ch.entwine.weblounge.preview.xhtmlrenderer.XhtmlRendererPagePreviewGenerator

com.atlantbh.nutch.filter.xpath.XPathHtmlParserFilter

com.cubusmail.mail.text.MessageTextUtil

com.cubusmail.mail.text.test.HtmlParserTest

com.cubusmail.server.mail.text.MessageTextUtil

com.ikanow.infinit.e.harvest.enrichment.custom.UnstructuredAnalysisHarvester

com.jeck.microblogging.utils.HtmlUtils

com.netfever.site.dynovisz.tools.utils.XmlUtils

com.skrul.greasefire.DownloadScripts

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.