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.


        createParser(
            "view these documents, you must have <A href='http://www.adobe.com'>Adobe \n"
                + "Acrobat Reader</A> installed on your computer.");
        Parser.setLineSeparator("\r\n");
        parser.addScanner(new LinkScanner("-l"));
        parseAndAssertNodeCount(3);
        // The first node should be a HTMLStringNode-  with the text - view these documents, you must have 
        assertTrue(
            "First node should be a HTMLStringNode",
            node[0] instanceof StringNode);

View Full Code Here

     * The string node is not correctly identified
     */
    public void testTagCharsInStringNode() throws ParserException
    {
        createParser("<a href=\"http://asgard.ch\">[> ASGARD <]</a>");
        parser.addScanner(new LinkScanner("-l"));
        parseAndAssertNodeCount(1);
        assertTrue(
            "Node identified must be a link tag",
            node[0] instanceof LinkTag);
        LinkTag linkTag = (LinkTag) node[0];

View Full Code Here

                + "&nbsp;&#8226;&nbsp;<a href=/advanced_search?hl=en>Advanced&nbsp;Search</a><br>&nbsp;&#8226;"
                + "&nbsp;<a href=/preferences?hl=en>Preferences</a><br>&nbsp;&#8226;&nbsp;<a href=/"
                + "language_tools?hl=en>Language Tools</a></font></td></tr></table></form>");


        parser.addScanner(new FormScanner("", parser));
        parser.addScanner(new LinkScanner());
        parseAndAssertNodeCount(1);
        assertTrue("Should be a HTMLFormTag", node[0] instanceof FormTag);
        FormTag formTag = (FormTag) node[0];
        LinkTag[] linkTag = new LinkTag[10];
        int i = 0;

View Full Code Here

                + "<INPUT TYPE=\"checkbox\">\n"
                + "<P>\n"
                + "<INPUT TYPE=\"SUBMIT\">\n"
                + "</FORM>");
        parser.addScanner(new FormScanner("", parser));
        parser.addScanner(new LinkScanner());
        parseAndAssertNodeCount(6);
        assertTrue("Fifth Node is a link", node[4] instanceof LinkTag);
        LinkTag linkTag = (LinkTag) node[4];
        assertEquals("Link Text", "Yahoo!\r\n", linkTag.getLinkText());
        assertEquals("Link URL", "http://www.yahoo.com", linkTag.getLink());

View Full Code Here

                "registerScanners() should be called first, when no other scanner has been registered.");
            System.err.println(
                "Other scanners already exist, hence this method call wont have any effect");
            return;
        }
        LinkScanner linkScanner = new LinkScanner(LinkTag.LINK_TAG_FILTER);
        // Note - The BaseHREF and Image scanners share the same
        // link processor - internally linked up with the factory
        // method in the link scanner class
        addScanner(linkScanner);
        addScanner(linkScanner.createImageScanner(ImageTag.IMAGE_TAG_FILTER));
        addScanner(new ScriptScanner("-s"));
        addScanner(new StyleScanner("-t"));
        addScanner(new JspScanner("-j"));
        addScanner(new AppletScanner("-a"));
        addScanner(new MetaTagScanner("-m"));
        addScanner(new TitleScanner("-T"));
        addScanner(new DoctypeScanner("-d"));
        addScanner(new FormScanner("-f", this));
        addScanner(new FrameSetScanner("-r"));
        addScanner(linkScanner.createBaseHREFScanner("-b"));
        addScanner(new BulletListScanner("-bulletList", this));
        //  addScanner(new SpanScanner("-p"));
        addScanner(new DivScanner("-div"));
        addScanner(new TableScanner(this));
    }

View Full Code Here

    }


    public static Parser createLinkRecognizingParser(String inputHTML)
    {
        Parser parser = createParser(inputHTML);
        parser.addScanner(new LinkScanner(LinkTag.LINK_TAG_FILTER));
        return parser;
    }

View Full Code Here

        // add body tag scanner
        parser.addScanner(new BodyScanner());
        // add BaseHRefTag scanner
        parser.addScanner(new BaseHrefScanner());
        // add ImageTag and BaseHrefTag scanners
        LinkScanner linkScanner= new LinkScanner(LinkTag.LINK_TAG_FILTER);
        // parser.addScanner(linkScanner);
        parser.addScanner(
            linkScanner.createImageScanner(ImageTag.IMAGE_TAG_FILTER));
        parser.addScanner(
            linkScanner.createBaseHREFScanner("-b"));
                            // Taken from org.htmlparser.Parser
        // add input tag scanner
        parser.addScanner(new InputTagScanner());
        // add applet tag scanner
        parser.addScanner(new AppletScanner());

View Full Code Here

    super(name);
  }


  public void testAccessKey() throws ParserException {
    createParser("<a href=\"http://www.kizna.com/servlets/SomeServlet?name=Sam Joseph\" accessKey=1>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", "http://www.kizna.com/servlets/SomeServlet?name=Sam Joseph", linkTag
        .getLink());

View Full Code Here

        "<A HREF=\"s/8741\"><IMG BORDER=\"0\" WIDTH=\"16\" SRC=\"http://us.i1.yimg.com/us.yimg.com/i/i16/mov_popc.gif\" HEIGHT=\"16\">This is a test\r\n</A>",
        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

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.