Examples of org.htmlparser.Parser.elements()

org.htmlparser.Parser.elements()
ahoo.com"); parser.registerScanners(); for (NodeIterator i = parser.elements();i.hasMoreElements();) { Node node = i.nextHTMLNode(); if (node instanceof StringNode) { // Downcasting to StringNode StringNode stringNode = (StringNode)node; // Do whatever processing you want with the string node System.out.println(stringNode.getText()); } // Check for the node or tag that you want if (node instanceof ...) { // Downcast, and process } }

  public void testDoubleQuotedCharset() throws ParserException {
    Parser parser;
    String url = "http://htmlparser.sourceforge.net/test/DoublequotedCharset.html";


    parser = new Parser(url);
    for (NodeIterator e = parser.elements(); e.hasMoreNodes();)
      e.nextNode();
    assertTrue("Wrong encoding", parser.getEncoding().equals("UTF-8"));
  }


  /**

View Full Code Here

  public void testSingleQuotedCharset() throws ParserException {
    Parser parser;
    String url = "http://htmlparser.sourceforge.net/test/SinglequotedCharset.html";


    parser = new Parser(url);
    for (NodeIterator e = parser.elements(); e.hasMoreNodes();)
      e.nextNode();
    assertTrue("Wrong encoding", parser.getEncoding().equals("UTF-8"));
  }


  /**

View Full Code Here

        }
      };
      parser.setConnection(connection);
      // must be the default
      assertTrue("Wrong encoding", parser.getEncoding().equals("ISO-8859-1"));
      for (NodeIterator e = parser.elements(); e.hasMoreNodes();)
        e.nextNode();
      assertTrue("Wrong encoding", parser.getEncoding().equals("windows-1252"));
    } catch (Exception e) {
      fail(e.getMessage());
    }

View Full Code Here

    String url = "http://htmlparser.sourceforge.net/test/This is a Test Page.html";


    parser = new Parser(url);
    Node node[] = new Node[30];
    int i = 0;
    for (NodeIterator e = parser.elements(); e.hasMoreNodes();) {
      node[i] = e.nextNode();
      i++;


    }
    assertEquals("Expected nodes", 12, i);

View Full Code Here

  Vector formChildren;


  public void setUp() throws Exception {
    Parser parser = Parser.createParser(FormScannerTest.FORM_HTML);
    parser.registerScanners();
    NodeIterator e = parser.elements();
    Node node = e.nextNode();
    formTag = (FormTag) node;
    formChildren = new Vector();
    for (SimpleNodeIterator se = formTag.children(); se.hasMoreNodes();) {
      formChildren.addElement(se.nextNode());

View Full Code Here

    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

      // 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

  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

    // Ideally, this should be upgraded to work with Objects (IE)
    // and archives (.jar and .zip) files as well.


    try {
      // we start to iterate through the elements
      for (NodeIterator e = htmlParser.elements(); e.hasMoreNodes();) {
        Node node = e.nextNode();
        String binUrlStr = null;


        // first we check to see if body tag has a
        // background set and we set the NodeIterator

View Full Code Here

0 1 2 3 4 5 6 7 8

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.