Examples of HtmlCleaner

com.qkyrie.markdown2pdf.internal.converting.HtmlCleaner
User: Quinten Date: 31-3-2014 Time: 09:44 @author Quinten De Swaef
info.bliki.htmlcleaner.HtmlCleaner
of few constructors cleaner.setXXX(...) // optionally, set cleaner's behaviour clener.clean(); // calls cleaning process cleaner.writeXmlXXX(...) // writes resulting XML to string, file or any output stream Created by: Vladimir Nikic
Date: November, 2006
no.priv.garshol.duke.cleaners.HTMLCleaner
A cleaner that removes HTML-style entity references, such as Þ and —. @since 1.3
org.apache.wookie.util.html.HtmlCleaner
A HTML processor implemented using 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);
org.outerj.daisy.diff.HtmlCleaner
org.outerj.daisy.htmlcleaner.HtmlCleaner

Examples of org.htmlcleaner.HtmlCleaner

  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

Examples of org.htmlcleaner.HtmlCleaner

  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

Examples of org.htmlcleaner.HtmlCleaner

    {
        // 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

Examples of org.htmlcleaner.HtmlCleaner

    {
        // 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

Examples of org.htmlcleaner.HtmlCleaner

    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

Examples of org.htmlcleaner.HtmlCleaner

    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

Examples of org.htmlcleaner.HtmlCleaner

    props.setTranslateSpecialEntities(true);
    props.setTransResCharsToNCR(true);
    props.setTransSpecialEntitiesToNCR(true);
    props.setOmitComments(true);
      
    HtmlCleaner cleaner = new HtmlCleaner(props);


    TagNode node = cleaner.clean(new URL(lien));
    
    for (Object o : node.evaluateXPath("//div[@id='retour_accueil']/a/img")) 
    {
      //System.out.println(((TagNode)(o)).getAllChildren());
      lien_logo = ((TagNode)(o)).getAttributeByName("src");

View Full Code Here

Examples of org.htmlcleaner.HtmlCleaner

    props.setTranslateSpecialEntities(true);
    props.setTransResCharsToNCR(true);
    props.setTransSpecialEntitiesToNCR(true);
    props.setOmitComments(true);
      
    HtmlCleaner cleaner = new HtmlCleaner(props);
      
    int i=0;
    TagNode node = cleaner.clean(new URL(lien));
    
    for (Object o : node.evaluateXPath("//div[@class='encadre_fiche firstencadre']/div/div/a")) 
    {
      lien_site_spe = ((TagNode)(o)).getAttributeByName("href");
      //System.out.println("lien spe "+lien_site_spe);

View Full Code Here

Examples of org.htmlcleaner.HtmlCleaner

  }
  
  
  public boolean recherche(String mot, String lien) throws MalformedURLException, IOException, XPatherException 
  {
    HtmlCleaner cleaner = new HtmlCleaner();
    TagNode node = cleaner.clean(new URL(lien));
    boolean bool = false;


    String[] decoupage = mot.split(" ");
    if(decoupage.length == 1)
    {

View Full Code Here

Examples of org.htmlcleaner.HtmlCleaner

    }
    return new Template(mapping);
  }
  
  private static HtmlCleaner getCleaner() {
    HtmlCleaner cleaner = new HtmlCleaner();
    cleaner.getProperties().setTranslateSpecialEntities(false);
    cleaner.getProperties().setRecognizeUnicodeChars(false);
    cleaner.getProperties().setUseEmptyElementTags(false);
    return cleaner;
  }

View Full Code Here

0 1 2 3 4 5

TOP

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.