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);

    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

    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

  }
  
  
  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

    }
    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

    return getError(response);
  }
  
  private static String getError(String response) throws IOException{
    String error = null;
    HtmlCleaner cleaner = new HtmlCleaner();
    TagNode html = cleaner.clean(response);
    TagNode errortag = html.findElementByAttValue("id", "error", true, true);
    if (errortag != null){
      error = errortag.getAttributeByName("title");
    }
    return error;

View Full Code Here

    private CleanerProperties parserProps;
    private DomSerializer2 domCreator;




    public HtmlParser() {
        this.htmlToXmlParser = new HtmlCleaner();
        this.parserProps = this.htmlToXmlParser.getProperties();
        this.parserProps.setRecognizeUnicodeChars(true);
        this.parserProps.setUseEmptyElementTags(true);
        this.parserProps.setAdvancedXmlEscape(true);
        this.parserProps.setTranslateSpecialEntities(true);

View Full Code Here

      String charset = get.getRequestCharSet();


      //
      // Check for charset overrides in the HTML start page
      //
      HtmlCleaner cleaner = new HtmlCleaner();
 
      TagNode httpEquivNode = cleaner.clean(get.getResponseBodyAsStream()).findElementByAttValue("http-equiv", "content-type", true, false);
      if (httpEquivNode != null && httpEquivNode.hasAttribute("content")){
        String value = httpEquivNode.getAttributeByName("content");
        int offset = value.indexOf("charset=");
        if (offset >= -1){
            charset = value.substring(offset+8).toUpperCase();

View Full Code Here

    }


    @Override
    public String select(String text) {
        try {
            HtmlCleaner htmlCleaner = new HtmlCleaner();
            TagNode tagNode = htmlCleaner.clean(text);
            Document document = new DomSerializer(new CleanerProperties()).createDOM(tagNode);
            Object result;
            try {
                result = xPathExpression.evaluate(document, XPathConstants.NODESET);
            } catch (XPathExpressionException e) {

View Full Code Here


    @Override
    public List<String> selectList(String text) {
        List<String> results = new ArrayList<String>();
        try {
            HtmlCleaner htmlCleaner = new HtmlCleaner();
            TagNode tagNode = htmlCleaner.clean(text);
            Document document = new DomSerializer(new CleanerProperties()).createDOM(tagNode);
            Object result;
            try {
                result = xPathExpression.evaluate(document, XPathConstants.NODESET);
            } catch (XPathExpressionException e) {

View Full Code Here

    @Ignore("take long time")
    @Test
    public void parserPerformanceTest() throws XPatherException {
        System.out.println(html.length());


        HtmlCleaner htmlCleaner = new HtmlCleaner();
        TagNode tagNode = htmlCleaner.clean(html);
        Document document = Jsoup.parse(html);


        long time =System.currentTimeMillis();
        for (int i = 0; i < 2000; i++) {
            htmlCleaner.clean(html);
        }
        System.out.println(System.currentTimeMillis()-time);


        time =System.currentTimeMillis();
        for (int i = 0; i < 2000; i++) {
            tagNode.evaluateXPath("//a");
        }
        System.out.println(System.currentTimeMillis()-time);


        System.out.println("=============");


        time =System.currentTimeMillis();
        for (int i = 0; i < 2000; i++) {
            Jsoup.parse(html);
        }
        System.out.println(System.currentTimeMillis()-time);


        time =System.currentTimeMillis();
        for (int i = 0; i < 2000; i++) {
            document.select("a");
        }
        System.out.println(System.currentTimeMillis()-time);


        System.out.println("=============");


        time =System.currentTimeMillis();
        for (int i = 0; i < 2000; i++) {
            htmlCleaner.clean(html);
        }
        System.out.println(System.currentTimeMillis()-time);


        time =System.currentTimeMillis();
        for (int i = 0; i < 2000; i++) {

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.