Package org.htmlparser.tags

Examples of org.htmlparser.tags.LinkTag

302
303
304
305
306
307
308
309
310
311
312
313
        Node node = col.children().nextNode();
        assertType(
            "Node identified should be HTMLLinkTag",
            LinkTag.class,
            node);
        LinkTag linkTag = (LinkTag) node;
        Node nodeInsideLink = linkTag.children().nextNode();
        assertType(
            "Tag within link should be an image tag",
            ImageTag.class,
            nodeInsideLink);
        ImageTag imageTag = (ImageTag) nodeInsideLink;
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
        for (NodeIterator e = parser.elements(); e.hasMoreNodes();)
        {
            Node node = e.nextNode();
            if (node instanceof LinkTag)
            {
                LinkTag linkTag = (LinkTag) node;
                {
                    if (!linkTag.isMailLink())
                    {
                        if (linkTag.getLink().toUpperCase().indexOf("HTM")
                            != -1
                            || linkTag.getLink().toUpperCase().indexOf("COM")
                                != -1
                            || linkTag.getLink().toUpperCase().indexOf("ORG")
                                != -1)
                        {
                            if (crawlDepth > 0)
                            {
                                Parser newParser =
                                    new Parser(
                                        linkTag.getLink(),
                                        new DefaultParserFeedback());
                                newParser.registerScanners();
                                System.out.print(
                                    "Crawling to " + linkTag.getLink());
                                crawl(newParser, crawlDepth - 1);
                            }
                            else
                                System.out.println(linkTag.getLink());
                        }
                    }
                }
            }
        }
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
111
        System.out.println("Ripping Site " + resourceLocation);
        try
        {
            for (Enumeration e = ripper.rip(); e.hasMoreElements();)
            {
                LinkTag tag = (LinkTag) e.nextElement();
                System.out.println("Ripped mail address : " + tag.getLink());
            }
        }
        catch (ParserException e)
        {
            e.printStackTrace();
View Full Code Here
122
123
124
125
126
127
128
129
130
131
132
133
        for (NodeIterator e = parser.elements(); e.hasMoreNodes();)
        {
            node = e.nextNode();
            if (node instanceof LinkTag)
            {
                LinkTag linkTag = (LinkTag) node;
                if (linkTag.isMailLink())
                    mailAddresses.addElement(linkTag);
            }
        }
        return mailAddresses.elements();
    }
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
77
78
    {
        System.out.println("Parsing " + location + " for links...");
        Node[] links = parser.extractAllNodesThatAre(LinkTag.class);
        for (int i = 0; i < links.length; i++)
        {
            LinkTag linkTag = (LinkTag) links[i];
            // Print it
            //      System.out.println(linkTag.toString());
            System.out.println(linkTag.getLink());
            // To extract only mail addresses, uncomment the following line
            //      if (linkTag.isMailLink()) System.out.println(linkTag.getLink());
        }
    }
View Full Code Here
182
183
184
185
186
187
188
189
190
191
192
193
194
            }
            else if (node instanceof LinkTag)
            {
                // Node is a link
                // Cast it to an HTMLLinkTag
                LinkTag linkNode = (LinkTag) node;
                // Retrieve the data from the object and print it
                buffer.append(linkNode.getLinkText());
            }
            else if (node instanceof Tag)
            {
                String contents = ((Tag) node).getText();
                if (contents.equals("BR") || contents.equals("P"))
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
99
    {
        createParser("<A HREF=\".foo.txt\">Foo</A>", "http://www.oygevalt.com");
        parser.registerScanners();
        parseAndAssertNodeCount(1);
        assertTrue(node[0] instanceof LinkTag);
        LinkTag linkTag = (LinkTag) node[0];
        assertStringEquals(
            "link",
            "http://www.oygevalt.com/foo.txt",
            linkTag.getLink());
        assertEquals("link", "Foo", linkTag.getLinkText());
    }
View Full Code Here
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
            "view these documents, you must have ",
            stringNode.getText());
        assertTrue(
            "Second node should be a link node",
            node[1] instanceof LinkTag);
        LinkTag linkNode = (LinkTag) node[1];
        assertEquals("Link is", "http://www.adobe.com", linkNode.getLink());
        assertEquals(
            "Link text is",
            "Adobe \r\nAcrobat Reader",
            linkNode.getLinkText());

        assertTrue(
            "Third node should be a string node",
            node[2] instanceof StringNode);
        StringNode stringNode2 = (StringNode) node[2];
View Full Code Here
127
128
129
130
131
132
133
134
135
        parser.addScanner(new LinkScanner("-l"));
        parseAndAssertNodeCount(1);
        assertTrue(
            "Node identified must be a link tag",
            node[0] instanceof LinkTag);
        LinkTag linkTag = (LinkTag) node[0];
        assertEquals("[> ASGARD <]", linkTag.getLinkText());
        assertEquals("http://asgard.ch", linkTag.getLink());
    }
View Full Code Here
346
347
348
349
350
351
352
353
354
355
                + "</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());
        assertType("Sixth Node", FormTag.class, node[5]);
    }
View Full Code Here
TOP

Related Classes of org.htmlparser.tags.LinkTag

  • com.almilli.movierentals.blockbuster.BlockbusterService
  • com.almilli.movierentals.netflix.NetFlixService
  • com.knowgate.hipermail.HtmlMimeBodyPart
  • de.jungblut.crawl.extraction.OutlinkExtractor
  • edu.umd.cloud9.webgraph.ClueExtractLinks$Map
  • edu.umd.cloud9.webgraph.TrecExtractLinks$Map
  • hudson.plugins.rubyMetrics.rcov.RcovParser
  • hudson.plugins.rubyMetrics.saikuro.SaikuroParser
  • modelcrawler.Page
  • net.sf.regain.crawler.preparator.HtmlPreparator
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.