Examples of org.htmlparser.scanners.LinkScanner

org.htmlparser.scanners.LinkScanner
Scans for the Link Tag. This is a subclass of TagScanner, and is called using a variant of the template method. If the evaluate() method returns true, that means the given string contains an image tag. Extraction is done by the scan method thereafter by the user of this class.

            linkTag.toHtml());
    }


    public void testEvaluate()
    {
        LinkScanner scanner = new LinkScanner("-l");
        boolean retVal = scanner.evaluate("   a href ", null);
        assertEquals(
            "Evaluation of the Link tag",
            new Boolean(true),
            new Boolean(retVal));
    }

View Full Code Here

    public void testExtractLinkInvertedCommasBug() throws ParserException
    {
        String tagContents = "a href=r/anorth/top.html";
        Tag tag = new Tag(new TagData(0, 0, tagContents, ""));
        String url = "c:\\cvs\\html\\binaries\\yahoo.htm";
        LinkScanner scanner = new LinkScanner("-l");
        assertEquals(
            "Extracted Link",
            "r/anorth/top.html",
            scanner.extractLink(tag, url));
    }

View Full Code Here

     * This is the reproduction of a bug which produces multiple text copies.
     */
    public void testExtractLinkInvertedCommasBug2() throws ParserException
    {
        createParser("<a href=\"http://cbc.ca/artsCanada/stories/greatnorth271202\" class=\"lgblacku\">Vancouver schools plan 'Great Northern Way'</a>");
        parser.addScanner(new LinkScanner("-l"));
        parseAndAssertNodeCount(1);
        assertTrue("The node should be a link tag", node[0] instanceof LinkTag);
        LinkTag linkTag = (LinkTag) node[0];
        assertStringEquals(
            "Extracted Text",

View Full Code Here

     * Links with spaces in them will get their spaces absorbed
     */
    public void testLinkSpacesBug() throws ParserException
    {
        createParser("<a href=\"http://www.kizna.com/servlets/SomeServlet?name=Sam Joseph\">Click Here</A>");
        parser.addScanner(new LinkScanner("-l"));
        parseAndAssertNodeCount(1);
        assertTrue("The node should be a link tag", node[0] instanceof LinkTag);
        LinkTag linkTag = (LinkTag) node[0];
        assertEquals(
            "Link URL of link tag",

View Full Code Here

        createParser(
            "<LI><font color=\"FF0000\" size=-1><b>Tech Samachar:</b></font><a \n"
                + "href=\"http://ads.samachar.com/bin/redirect/tech.txt?http://www.samachar.com/tech\n"
                + "nical.html\"> Journalism 3.0</a> by Rajesh Jain");
        Parser.setLineSeparator("\r\n");
        parser.addScanner(new LinkScanner("-l"));
        parseAndAssertNodeCount(8);
        assertTrue(
            "Seventh node should be a link tag",
            node[6] instanceof LinkTag);
        LinkTag linkTag = (LinkTag) node[6];

View Full Code Here

    {
        createParser(
            "<A HREF=\"mytest.html\"> Hello World</A>",
            "http://www.yahoo.com");
        // Register the image scanner
        parser.addScanner(new LinkScanner("-l"));
        parseAndAssertNodeCount(1);
        assertTrue(
            "Node identified should be HTMLLinkTag",
            node[0] instanceof LinkTag);
        LinkTag linkTag = (LinkTag) node[0];

View Full Code Here

    {
        createParser(
            "<A HREF=\"abc/def/mytest.html\"> Hello World</A>",
            "http://www.yahoo.com");
        // Register the image scanner
        parser.addScanner(new LinkScanner("-l"));
        parseAndAssertNodeCount(1);
        assertTrue(
            "Node identified should be HTMLLinkTag",
            node[0] instanceof LinkTag);
        LinkTag linkTag = (LinkTag) node[0];

View Full Code Here

    {
        createParser(
            "<A HREF=\"../abc/def/mytest.html\"> Hello World</A>",
            "http://www.yahoo.com/ghi");
        // Register the image scanner
        parser.addScanner(new LinkScanner("-l"));
        parseAndAssertNodeCount(1);
        assertTrue(
            "Node identified should be HTMLLinkTag",
            node[0] instanceof LinkTag);
        LinkTag linkTag = (LinkTag) node[0];

View Full Code Here

    {
        createParser(
            "<A HREF=\"mytest.html\"><IMG SRC=\"abcd.jpg\">Hello World</A>",
            "http://www.yahoo.com");
        // Register the image scanner
        LinkScanner linkScanner = new LinkScanner("-l");
        parser.addScanner(linkScanner);
        parser.addScanner(linkScanner.createImageScanner("-i"));


        parseAndAssertNodeCount(1);
        assertTrue("Node should be a link node", node[0] instanceof LinkTag);


        LinkTag linkTag = (LinkTag) node[0];

View Full Code Here

    public void testReplaceFaultyTagWithEndTag() throws ParserException
    {
        String currentLine =
            "<p>Site Comments?<br><a href=\"mailto:sam@neurogrid.com?subject=Site Comments\">Mail Us<a></p>";
        Tag tag = new Tag(new TagData(85, 87, "a", currentLine));
        LinkScanner linkScanner = new LinkScanner();
        String newLine =
            linkScanner.replaceFaultyTagWithEndTag(tag, currentLine);
        assertEquals(
            "Expected replacement",
            "<p>Site Comments?<br><a href=\"mailto:sam@neurogrid.com?subject=Site Comments\">Mail Us</A></p>",
            newLine);
    }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.htmlparser.scanners.LinkScanner

org.apache.jmeter.protocol.http.parser.HtmlParserHTMLParser

org.htmlparser.Parser

org.htmlparser.tags.data.LinkData

org.htmlparser.tags.LinkTag

org.htmlparser.tests.parserHelperTests.StringParserTest

org.htmlparser.tests.scannersTests.BaseHREFScannerTest

org.htmlparser.tests.scannersTests.FormScannerTest

org.htmlparser.tests.scannersTests.LinkScannerTest

org.htmlparser.tests.tagTests.LinkTagTest

org.htmlparser.util.LinkProcessor

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.