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 } }


        try
        {
            parser = new Parser("http://www.sony.co.jp", Parser.DEVNULL);
            assertEquals("Character set by default is ISO-8859-1", "ISO-8859-1", parser.getEncoding ());
            enumeration = parser.elements();
            // search for the <BODY> tag
            while (enumeration.hasMoreNodes ())
                if (enumeration.nextNode () instanceof BodyTag)
                    break;
            assertTrue("Character set should be Shift_JIS", parser.getEncoding ().equalsIgnoreCase ("Shift_JIS"));

View Full Code Here


        parser = new Parser(url);
        parser.setNodeFactory (new PrototypicalNodeFactory (new MetaTag ()));
        i = 0;
        nodes = new Node[30];
        for (NodeIterator e = parser.elements(); e.hasMoreNodes();)
            nodes[i++] = e.nextNode();
        assertEquals ("Expected nodes", 23, i);
    }


    /**

View Full Code Here

    {
        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

    {
        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"));
    }


    // This test is commented out because the URL no longer has a comma delimited character set.

View Full Code Here


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


        }
        assertEquals("Expected nodes",20,i);

View Full Code Here

        Parser parser = new Parser("http://education.yahoo.com/",new DefaultParserFeedback());
        parser.setNodeFactory (new PrototypicalNodeFactory (new ImageTag ()));
        setParser (parser);
        int parserImgTagCount = 0;
        Node node;
        for (NodeIterator e= parser.elements();e.hasMoreNodes();) {
            node = e.nextNode();
            if (node instanceof ImageTag) {
                parserImgTagCount++;
            }
        }

View Full Code Here


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


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


        nextExpectedNode = null;
        nextActualNode = null;
        tag1 = null;

View Full Code Here

        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);

View Full Code Here

            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 (),
                enumeration.nextNode ().toHtml ());

View Full Code Here

        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);

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.