Examples of org.htmlcleaner.TagNode

org.htmlcleaner.TagNode

XML node tag - basic node of the cleaned HTML tree. At the same time, it represents start tag token after HTML parsing phase and before cleaning phase. After cleaning process, tree structure remains containing tag nodes (TagNode class), content (text nodes - ContentNode), comments (CommentNode) and optionally doctype node (DoctypeToken).

  }
  
  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")) 
    {
      if(count > 2  && count < 4){
        info = info + ((TagNode)(o)).getText() + "\n";
      }
      count++;

View Full Code Here

    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()));
      //System.out.println("href: "+dUrl);
      ajout = "LI: " + org.apache.commons.lang3.StringEscapeUtils.unescapeHtml4(((TagNode)(o)).getText().toString())+"\n";

View Full Code Here

    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");
      //System.out.println("lien_logo "+lien_logo);
    }
    
    String temp2[] = new String[10];
    for (Object o : node.evaluateXPath("//style")) 
    {
      //System.out.println(((TagNode)(o)).getAllChildren());
      for(Object temp: ((TagNode)(o)).getAllChildren())
      {
        if(temp.toString().contains("}"))

View Full Code Here

    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);
    }
    
    for (Object o : node.evaluateXPath("//div[@id='infos_generales']/table/tbody/tr")) 
    {
      for(Object temp: ((TagNode)(o)).getAllChildren())
      {
        if(temp.toString().contains("th"))
        {
          for(Object temp2: ((TagNode)(temp)).getAllChildren())
          {
            info_principal[i][0] = org.apache.commons.lang3.StringEscapeUtils.unescapeHtml4(temp2.toString()); 
          }
        }
        if(temp.toString().contains("td"))
        {
          for(Object temp2: ((TagNode)(temp)).getAllChildren())
          {
            info_principal[i][1] = org.apache.commons.lang3.StringEscapeUtils.unescapeHtml4(temp2.toString()); 
            i++;
          }
        }
      }
    }
    
    i=0;
    for (Object o : node.evaluateXPath("//div[@class='element_deco'][2]")) 
    {
      //System.out.println("description "+((TagNode)(o)).getAllChildren());
      for(Object temp: ((TagNode)(o)).getAllChildren())
      {
        if(temp.toString().contains("strong"))
        {
          for(Object temp2: ((TagNode)(temp)).getAllChildren())
          {
            description[i][0] =org.apache.commons.lang3.StringEscapeUtils.unescapeHtml4(temp2.toString());
          }
        }
        else if(temp.toString().equals("div"))
        {
          for(Object temp2: ((TagNode)(temp)).getAllChildren())
          {
            if(temp2.toString().equals("font"))
            {
              for(Object temp3: ((TagNode)(temp2)).getAllChildren())
              {
                if(temp3.toString().equals("strong"))
                {
                  for(Object temp4: ((TagNode)(temp3)).getAllChildren())
                  {
                    //System.out.println("description strong "+temp4.toString());
                    description[i][0] =org.apache.commons.lang3.StringEscapeUtils.unescapeHtml4(temp2.toString());
                    i++;
                  }
                }
                else if(temp3.toString().length()>=5)
                {
                  //System.out.println("description font "+temp3.toString());
                  description[i][0] =org.apache.commons.lang3.StringEscapeUtils.unescapeHtml4(temp2.toString());
                  i++;
                }
              }
            }
            else if(temp2.toString().length()>=5)
            {
              //System.out.println("description div "+temp2.toString());
              description[i][0] =org.apache.commons.lang3.StringEscapeUtils.unescapeHtml4(temp2.toString());
              i++;
            }
          }
        }
        else if(temp.toString().equals("p"))
        {
          for(Object temp2: ((TagNode)(temp)).getAllChildren())
          {
            if(temp2.toString().equals("strong"))
            {
              for(Object temp3: ((TagNode)(temp2)).getAllChildren())
              {
                //System.out.println("description 3 "+temp3.toString());
                break;
              }
            }
            else if(temp2.toString().length()>=5)
            {
              //System.out.println("description i "+i+" "+temp2.toString());
              description[i][0] =org.apache.commons.lang3.StringEscapeUtils.unescapeHtml4(temp2.toString());
              i++;
              break;
            }
          }
        }
        else if(temp.toString().length()>=5)
        {
          description[i][1] = org.apache.commons.lang3.StringEscapeUtils.unescapeHtml4(temp.toString());
          break;
        }
      }
    }
    
    i=0;
    int ok=0;
    for (Object o : node.evaluateXPath("//div[@class='encadre_fiche']")) 
    {
      for(Object temp: ((TagNode)(o)).getAllChildren())
      {
        if(ok == 1)
        {

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)
    {
      for (Object o : node.evaluateXPath("//table[@class='clFlatTable']//tr//td")) 
      {
        if(((((TagNode)(o)).getText()).toString()).toLowerCase().equals(mot.toLowerCase()))
        {
          bool = true;
          int i = 0;
          String [] tabl = new String[6];
          for(Object k : ((TagNode)(o)).getParent().evaluateXPath("td"))
          {
            String str = ((TagNode)(k)).getText().toString();
            tabl[i] = str;
            i++;
          }
          resultats.addElement(tabl);
        }  
      }
    }
    else
    {
      test = false;
      for (Object o : node.evaluateXPath("//table[@class='clFlatTable']//tr//td")) 
      {
        if(((((TagNode)(o)).getText()).toString()).toLowerCase().equals(decoupage[0].toLowerCase()))
        {
          int tag = -1;
          if(((((TagNode)(o)).getText()).toString()).toLowerCase().equals(decoupage[0].toLowerCase()))

View Full Code Here

  
  /* (non-Javadoc)
   * @see org.apache.wookie.util.html.IHtmlProcessor#injectScript(java.lang.String)
   */
  public void injectScript(String script) {
    TagNode js = new TagNode(SCRIPT_TAG);
    js.addAttribute(TYPE_ATTRIBUTE, TYPE_ATTRIBUTE_VALUE);
    js.addAttribute(SRC_ATTRIBUTE, script);
    headNode.addChild(js);
  }

View Full Code Here


  /* (non-Javadoc)
   * @see org.apache.wookie.util.html.IHtmlProcessor#injectStylesheet(java.lang.String)
   */
  public void injectStylesheet(String stylesheet) {
    TagNode js = new TagNode(LINK_TAG);
    js.addAttribute(TYPE_ATTRIBUTE, CSS_TYPE_ATTRIBUTE_VALUE);
    js.addAttribute(REL_ATTRIBUTE, CSS_REL_ATTRIBUTE_VALUE);
    js.addAttribute(HREF_ATTRIBUTE, stylesheet);
    headNode.addChild(js);
  }

View Full Code Here

    
    //
    // Check if the page already has a META http-equiv=content-type tag,
    // if it doesn't create one and add it to the head node
    //
    TagNode meta = headNode.findElementByAttValue("http-equiv", "content-type", true, false);
    if (meta == null) {
      meta = new TagNode(META_TAG);
      meta.addAttribute("http-equiv", "Content-Type");
      headNode.getChildren().add(0, meta);
    }
    //
    // Force UTF into lowercase
    //
    if (charset.equals("UTF-8")) charset = "utf-8";
    
    //
    // Override the charset and content-type values for the 
    // META http-equiv=content-type tag
    //
    meta.addAttribute("content", type + ";charset=" + charset);
  }

View Full Code Here

   * @param callback
   * @return
   */
  private static Node traverse(BaseToken root, int depth, Callback callback) {
    if (root instanceof TagNode) {
      TagNode tn = (TagNode) root;


      int height = -1;
      int hash = HashCodeUtil.SEED;


      hash = HashCodeUtil.hash(hash, tn.getName());
      hash = HashCodeUtil.hash(hash, tn.getAttributes().toString());


      for (Object n : tn.getChildren()) {
        if (isInteresting(n)) {
          Node c = traverse((BaseToken) n, depth + 1, callback);
          hash = HashCodeUtil.hash(hash, c);
          if (c.height > height)
            height = c.height;

View Full Code Here

   * @throws TemplateNotFoundException
   *             if this template doesn't match the given document.
   * @throws IOException
   */
  public String clean(String document) throws IOException {
    TagNode root = parse(document); 
    Traverser.traverse(root, new Pruner(mapping));
    return write(root); 
  }

View Full Code Here

0 1 2 3 4 5 6

TOP

Related Classes of org.htmlcleaner.TagNode

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.