Examples of org.htmlparser.Parser

org.htmlparser.Parser

ahoo.com",new DefaultHTMLParserFeedback()); // In this example, we are registering all the common scanners parser.registerScanners(); for (NodeIterator i = parser.elements();e.hasMoreNodes();) { Node node = i.nextNode(); node.print(); } Below is some sample code to parse Yahoo.com and print only the text information. This scanning will run faster, as there are no scanners registered here.

 Parser parser = new Parser("http://www.yahoo.com",new DefaultHTMLParserFeedback()); // In this example, none of the scanners need to be registered // as a string node is not a tag to be scanned for. for (NodeIterator i = parser.elements();e.hasMoreNodes();) { Node node = i.nextNode(); if (node instanceof StringNode) {        	 StringNode stringNode = (StringNode)node;         System.out.println(stringNode.getText());     }  }

The above snippet will print out only the text contents in the html document.
Here's another snippet that will only print out the link urls in a document. This is an example of adding a link scanner.

 Parser parser = new Parser("http://www.yahoo.com",new DefaultHTMLParserFeedback()); parser.addScanner(new LinkScanner("-l")); for (NodeIterator i = parser.elements();e.hasMoreNodes();) { Node node = i.nextNode();     if (node instanceof LinkTag) { LinkTag linkTag = (LinkTag)node;         System.out.println(linkTag.getLink());     }  }

@see Parser#elements()

        throws Exception
    {
        expected = removeEscapeCharacters(expected);
        actual = removeEscapeCharacters(actual);


        Parser expectedParser = Parser.createParser(expected);
        Parser resultParser = Parser.createParser(actual);


        NodeIterator expectedIterator = expectedParser.elements();
        NodeIterator actualIterator = resultParser.elements();
        displayMessage =
            createGenericFailureMessage(displayMessage, expected, actual);


        Node nextExpectedNode = null, nextActualNode = null;
        do

View Full Code Here

    }


    public void testZeroArgConstructor()
        throws IOException, ClassNotFoundException, ParserException
    {
        Parser parser;
        byte[] data;


        parser = new Parser();
        data = pickle(parser);
        parser = (Parser) unpickle(data);
    }

View Full Code Here

    }


    public void testSerializable()
        throws IOException, ClassNotFoundException, ParserException
    {
        Parser parser;
        Vector vector;
        NodeIterator enumeration;
        byte[] data;


        parser =
            new Parser("http://htmlparser.sourceforge.net/test/example.html");
        enumeration = parser.elements();
        vector = new Vector(50);
        while (enumeration.hasMoreNodes())
            vector.addElement(enumeration.nextNode());


        data = pickle(parser);
        parser = (Parser) unpickle(data);


        enumeration = parser.elements();
        while (enumeration.hasMoreNodes())
            assertEquals(
                "Nodes before and after serialization differ",
                ((Node) vector.remove(0)).toHtml(),
                ((Node) enumeration.nextNode()).toHtml());

View Full Code Here

    }


    public void testSerializableScanners()
        throws IOException, ClassNotFoundException, ParserException
    {
        Parser parser;
        Vector vector;
        NodeIterator enumeration;
        byte[] data;


        parser =
            new Parser("http://htmlparser.sourceforge.net/test/example.html");
        parser.registerScanners();
        enumeration = parser.elements();
        vector = new Vector(50);
        while (enumeration.hasMoreNodes())
            vector.addElement(enumeration.nextNode());


        data = pickle(parser);
        parser = (Parser) unpickle(data);


        enumeration = parser.elements();
        while (enumeration.hasMoreNodes())
            assertEquals(
                "Nodes before and after serialization differ",
                ((Node) vector.remove(0)).toHtml(),
                ((Node) enumeration.nextNode()).toHtml());

View Full Code Here

     * See also feature request #725376 Handle script in attributes.
     * Only perform this test if it's version 1.4 or higher.
     */
    public void testJspWithinAttributes()
    {
        Parser parser;


        parser = new Parser();
        if (1.4 <= Parser.getVersionNumber())
        {
            getParameterTableFor("a href=\"<%=Application(\"sURL\")%>/literature/index.htm");
            assertStringEquals(
                "href",

View Full Code Here

     * See feature request #725376 Handle script in attributes.
     * Only perform this test if it's version 1.4 or higher.
     */
    public void testScriptedTag()
    {
        Parser parser;


        parser = new Parser();
        if (1.4 <= Parser.getVersionNumber())
        {
            getParameterTableFor("body onLoad=defaultStatus=''");
            String name = (String) table.get(Tag.TAGNAME);
            assertNotNull("No Tag.TAGNAME", name);

View Full Code Here

    this.file = file;
    this.numTimes = numTimes;    
  }


  public void beginTestWithoutScanners() throws ParserException {
    Parser parser;
    long sumTimes=0;
    double avg=0;
    System.out.println("***************************************");
    System.out.println("*  Test Without Scanners Registered   *");
    System.out.println("***************************************");        
    for (int i=0;i<=numTimes;i++) {
      // Create the parser object
      parser = new Parser(file,new DefaultParserFeedback());
      Node node;
      long start=System.currentTimeMillis();
      for (NodeIterator e = parser.elements();e.hasMoreNodes();) {
        node = e.nextNode();
      }
      long elapsedTime=System.currentTimeMillis()-start;
      if (i!=0)
      sumTimes += elapsedTime;

View Full Code Here

    System.out.println("Average Time : "+avg+" ms");
    System.out.println("***************************************");
  }


  public void beginTestWithScanners() throws ParserException {
    Parser parser;
    long sumTimes=0;
    double avg=0;
    System.out.println("***************************************");
    System.out.println("*    Test With Scanners Registered    *");
    System.out.println("***************************************");          
    for (int i=0;i<=numTimes;i++) {
      // Create the parser object
      parser = new Parser(file,new DefaultParserFeedback());
      parser.registerScanners();
      Node node;
      long start=System.currentTimeMillis();
      for (NodeIterator e = parser.elements();e.hasMoreNodes();) {
        node = e.nextNode();
      }
      long elapsedTime=System.currentTimeMillis()-start;
      if (i!=0)
      sumTimes += elapsedTime;

View Full Code Here

        return imgTagCount;
    }


    public int countImageTagsWithHTMLParser() throws ParserException
    {
        Parser parser =
            new Parser("http://www.yahoo.com", new DefaultParserFeedback());
        parser.addScanner(new ImageScanner("-i", new LinkProcessor()));
        int parserImgTagCount = 0;
        Node node;
        for (NodeIterator e = parser.elements(); e.hasMoreNodes();)
        {
            node = (Node) e.nextNode();
            if (node instanceof ImageTag)
            {
                parserImgTagCount++;

View Full Code Here


    private void identify(String string) throws Exception
    {
        String[] tagsBeingChecked = { "TABLE", "DIV", "SPAN" };


        Parser parser = new Parser("http://www.amazon.com");
        TagFindingVisitor tagFinder =
            new TagFindingVisitor(tagsBeingChecked, true);
        parser.visitAllNodesWith(tagFinder);
        for (int i = 0; i < tagsBeingChecked.length; i++)
        {
            System.out.println(
                "Number of "
                    + tagsBeingChecked[i]

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.htmlparser.Parser

cn.edu.pku.dr.requirement.elicitation.tools.HtmlTransformer

com.gnizr.core.util.FormatUtil

com.knowgate.hipermail.DBMimeMessage

com.knowgate.hipermail.HtmlMimeBodyPart

com.lanyuan.util.HttpClientUtils

com.vgo.movie.thread.DetailFilmThread

com.waxayaz.TomcatMI.core.utils.repoManager.TomcatRepositoryManager

com.wordpress.util.StringUtil

fitnesse.fixtures.PageDriver

fitnesse.slim.converters.MapEditor

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.