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.

  /**
   * 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", "Vancouver schools plan 'Great Northern Way'", linkTag.getLinkText());
  }

View Full Code Here

   * Bug pointed out by Sam Joseph (sam@neurogrid.net) 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", "http://www.kizna.com/servlets/SomeServlet?name=Sam Joseph", linkTag
        .getLink());

View Full Code Here

  public void testMultipleLineBug() throws ParserException {
    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];
    String exp = new String("http://ads.samachar.com/bin/redirect/tech.txt?http://www.samachar.com/technical.html");
    // assertEquals("Length of link tag",exp.length(),

View Full Code Here

  }


  public void testRelativeLinkScan() throws ParserException {
    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];
    assertEquals("Expected Link", "http://www.yahoo.com/mytest.html", linkTag.getLink());
  }

View Full Code Here

  }


  public void testRelativeLinkScan2() throws ParserException {
    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];
    assertStringEquals("Expected Link", "http://www.yahoo.com/abc/def/mytest.html", linkTag.getLink());
  }

View Full Code Here

  }


  public void testRelativeLinkScan3() throws ParserException {
    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];
    assertStringEquals("Expected Link", "http://www.yahoo.com/abc/def/mytest.html", linkTag.getLink());
  }

View Full Code Here

   * Test scan with data which is of diff nodes type
   */
  public void testScan() throws ParserException {
    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

  }


  public void testInsertEndTagBeforeTag() throws ParserException {
    String currentLine = "<a href=s/7509><b>Yahoo! Movies</b></a>";
    Tag tag = new Tag(new TagData(0, 14, "a href=s/7509", currentLine));
    LinkScanner linkScanner = new LinkScanner();
    String newLine = linkScanner.insertEndTagBeforeNode(tag, currentLine);
    assertEquals("Expected insertion", "</A><a href=s/7509><b>Yahoo! Movies</b></a>", newLine);
  }

View Full Code Here

   * &lt;A&gt;Revision&lt;\a&gt; Reported by Mazlan Mat
   */
  public void testFreshMeatBug() throws ParserException {
    createParser("<a>Revision</a>", "http://www.yahoo.com");
    // Register the image scanner
    parser.addScanner(new LinkScanner("-l"));


    parseAndAssertNodeCount(3);
    assertTrue("Node 0 should be a tag", node[0] instanceof Tag);
    Tag tag = (Tag) node[0];
    assertEquals("Tag Contents", "a", tag.getText());

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.