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.apache.wookie.util.html.HtmlCleaner

  /**
   * tests that user scripts are placed after injected scripts
   */
  @Test
  public void injectScriptWithUserScript(){
    HtmlCleaner cleaner = new HtmlCleaner();
    String content = "<head><script type=\"text/javascript\" src=\"user.js\"></script></head>";
    String out = "";
    StringWriter writer = new StringWriter();
    try {
      cleaner.setReader(new StringReader(content));
      cleaner.injectScript("inject.js");
      cleaner.process(writer);
      out = writer.getBuffer().toString();
      assertEquals("<html><head><script type=\"text/javascript\" src=\"inject.js\"></script><script type=\"text/javascript\" src=\"user.js\"></script></head><body></body></html>", out);
    } catch (IOException e) {
      fail();
    }

View Full Code Here

Examples of org.apache.wookie.util.html.HtmlCleaner

  /**
   * tests that user scripts are placed after injected scripts and are not reordered
   */
  @Test
  public void injectScriptWithUserScriptNoReorder(){
    HtmlCleaner cleaner = new HtmlCleaner();
    String content = "<head><script type=\"text/javascript\" src=\"user.js\"></script><script type=\"text/javascript\">google.load(\"dojo\", \"1.4.1\");</script></head>";
    String out = "";
    StringWriter writer = new StringWriter();
    try {
      cleaner.setReader(new StringReader(content));
      cleaner.injectScript("inject.js");
      cleaner.process(writer);
      out = writer.getBuffer().toString();
      assertEquals("<html><head><script type=\"text/javascript\" src=\"inject.js\"></script><script type=\"text/javascript\" src=\"user.js\"></script><script type=\"text/javascript\">google.load(\"dojo\", \"1.4.1\");</script></head><body></body></html>", out);
    } catch (IOException e) {
      fail();
    }

View Full Code Here

Examples of org.apache.wookie.util.html.HtmlCleaner

  /**
   * tests injecting stylesheet
   */
  @Test
  public void injectStylesheet(){
    HtmlCleaner cleaner = new HtmlCleaner();
    String content = "";
    String out = "";
    StringWriter writer = new StringWriter();
    try {
      cleaner.setReader(new StringReader(content));
      cleaner.injectStylesheet("test.css");
      cleaner.process(writer);
      out = writer.getBuffer().toString();
      assertEquals("<html><head><link type=\"text/css\" rel=\"stylesheet\" href=\"test.css\" /></head><body></body></html>", out);
    } catch (IOException e) {
      fail();
    }

View Full Code Here

Examples of org.apache.wookie.util.html.HtmlCleaner

    }
  }


  @Test (expected = IOException.class)
  public void nullReader() throws IOException{
    HtmlCleaner cleaner = new HtmlCleaner();
    StringWriter writer = new StringWriter();
    cleaner.setReader(null);
    cleaner.injectStylesheet("test.css");
    cleaner.process(writer);
    fail();
  }

View Full Code Here

Examples of org.apache.wookie.util.html.HtmlCleaner

    cleaner.process(writer);
    fail();
  }
  @Test (expected = IOException.class)
  public void nullContentInReader() throws IOException{
    HtmlCleaner cleaner = new HtmlCleaner();
    StringWriter writer = new StringWriter();
    cleaner.setReader(new FileReader("bogus.html"));
    cleaner.injectStylesheet("test.css");
    cleaner.process(writer);
  }

View Full Code Here

Examples of org.apache.wookie.util.html.HtmlCleaner

    cleaner.process(writer);
  }


  @Test  (expected = IOException.class)
  public void nullWriter() throws IOException{
    HtmlCleaner cleaner = new HtmlCleaner();
    FileWriter writer = null;
    cleaner.setReader(new StringReader("test"));
    cleaner.injectStylesheet("test.css");
    cleaner.process(writer);
  }

View Full Code Here

Examples of org.htmlcleaner.HtmlCleaner

  }
  
  public static Collection<String> findAllLinkHref(String html, String hostUrl) throws Exception{
    Collection<String> urls = new ArrayList<String>();
    
    HtmlCleaner cleaner = new HtmlCleaner();
    TagNode node = cleaner.clean(html);
    Object[] ns = node.evaluateXPath("//a[@href]");
    for (Object object : ns) {
      TagNode node2=(TagNode) object;
      String href = node2.getAttributeByName("href");
      if (href == null || href.trim().length() == 0)

View Full Code Here

Examples of org.htmlcleaner.HtmlCleaner

    
    return map;
  }
  
  private List<Map<String, Object>> parseHtml(Page page) throws Exception{
    HtmlCleaner cleaner = new HtmlCleaner();
    cleaner.getProperties().setTreatUnknownTagsAsContent(true);
    String html = page.getContent();
    TagNode rootNode = cleaner.clean(html);
    fel.getContext().set("$page_content", html);
        final List<Field> fields = target.getModel().getField();
    String isModelArray = target.getModel().getIsArray();
    String modelXpath = target.getModel().getXpath();
    List<Map<String, Object>> list = new ArrayList<Map<String, Object>>();

View Full Code Here

Examples of org.htmlcleaner.HtmlCleaner

    System.out.println(objs);
  }
  
  public static Object evalXpath(String html, String xpath, String attribute){
    List<Object> result = new ArrayList<Object>();
    HtmlCleaner cleaner = new HtmlCleaner();
    try {
      TagNode tagNode = cleaner.clean(html);
      Object[] nodeVals = tagNode.evaluateXPath(xpath);
      for (Object tag : nodeVals){
        TagNode _tag = (TagNode)tag;
        Object val = null;
        if (attribute != null)

View Full Code Here

Examples of org.htmlcleaner.HtmlCleaner

        xml = CommonUtil.toXml((Node)node, keepHeader);
        return CommonUtil.toHTML(xml);
      }else if (node instanceof TagNode){
        StringWriter sw = new StringWriter();
        //TODO 从配置文件里加载这个CleanerProperties
        CleanerProperties prop = new HtmlCleaner().getProperties();
        SimpleXmlSerializer ser = new SimpleXmlSerializer(prop);
        ser.write((TagNode)node, sw, "UTF-8");
          String html = sw.getBuffer().toString();
          if (keepHeader)
            xml = html;

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.