Package org.htmlparser.tags

Examples of org.htmlparser.tags.MetaTag

391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
                 i.hasMoreNodes();)
            {
                Node node = i.nextNode();
                if (node instanceof MetaTag)
                {
                    MetaTag meta = (MetaTag) node;
                    if ( meta.getHttpEquiv() != null &&
                            meta.getHttpEquiv().equalsIgnoreCase(YADIS_XRDS_LOCATION) )
                    {
                        if ( xrdsLocation != null )
                            throw new YadisException(
                                "More than one " + YADIS_XRDS_LOCATION +
                                "META tags found in HEAD: " + head.toHtml(),
                                YadisResult.HTMLMETA_INVALID_RESPONSE);

                        xrdsLocation = meta.getMetaContent();
                        if (DEBUG)
                            _log.debug("Found " + YADIS_XRDS_LOCATION + "META tags.");
                    }
                }
            }
View Full Code Here
130
131
132
133
134
135
136
137
138
139
140
141
142
              _keywords.add(kw);
            }
          }
          */
        } else if ( n.getClass() == MetaTag.class ) {
          MetaTag t = (MetaTag)n;
          if (t.getAttribute("name") != null && t.getAttribute("name").equals("keywords") ) {
            String[] kws = t.getAttribute("content").split(",");
            for( String kw : kws ) {
              _keywords.add(kw);
            }
          }
        }
View Full Code Here
486
487
488
489
490
491
492
493
494
495
496
        String url = "http://htmlparser.sourceforge.net/test/gb2312Charset.html";
        int i;
        Node[] nodes;

        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
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
    {
        String url;
        int bookmark;
        NodeList list;
        NodeList robots;
        MetaTag robot;
        String content;
        File file;
        File dir;
        PrintWriter out;

        // get the next URL and add it to the done pile
        url = (String)mPages.remove (0);
        System.out.println ("processing " + url);
        mFinished.add (url);

        try
        {
            bookmark = mPages.size ();
            // fetch the page and gather the list of nodes
            mParser.setURL (url);
            try
            {
                list = new NodeList ();
                for (NodeIterator e = mParser.elements (); e.hasMoreNodes (); )
                    list.add (e.nextNode ()); // URL conversion occurs in the tags
            }
            catch (EncodingChangeException ece)
            {
                // fix bug #998195 SiteCatpurer just crashed
                // try again with the encoding now set correctly
                // hopefully mPages, mImages, mCopied and mFinished won't be corrupted
                mParser.reset ();
                list = new NodeList ();
                for (NodeIterator e = mParser.elements (); e.hasMoreNodes (); )
                    list.add (e.nextNode ());
            }

            // handle robots meta tag according to http://www.robotstxt.org/wc/meta-user.html
            // <meta name="robots" content="index,follow" />
            // <meta name="robots" content="noindex,nofollow" />
            robots = list.extractAllNodesThatMatch (
                new AndFilter (
                    new NodeClassFilter (MetaTag.class),
                    new HasAttributeFilter ("name", "robots")), true);
            if (0 != robots.size ())
            {
                robot = (MetaTag)robots.elementAt (0);
                content = robot.getAttribute ("content").toLowerCase ();
                if ((-1 != content.indexOf ("none")) || (-1 != content.indexOf ("nofollow")))
                    // reset mPages
                    for (int i = bookmark; i < mPages.size (); i++)
                        mPages.remove (i);
                if ((-1 != content.indexOf ("none")) || (-1 != content.indexOf ("noindex")))
View Full Code Here
313
314
315
316
317
318
319
320
321
322
323
        registerTag (new ImageTag ());
        registerTag (new InputTag ());
        registerTag (new JspTag ());
        registerTag (new LabelTag ());
        registerTag (new LinkTag ());
        registerTag (new MetaTag ());
        registerTag (new ObjectTag ());
        registerTag (new OptionTag ());
        registerTag (new ParagraphTag ());
        registerTag (new ProcessingInstructionTag ());
        registerTag (new ScriptTag ());
View Full Code Here
220
221
222
223
224
225
226
227
228
229
230
231
232
        assertTrue("The HTML tag should have 3 nodes", 3 == htmlTag.getChildCount ());
        assertTrue("The first child should be a HEAD tag",htmlTag.getChild(0) instanceof HeadTag);
        HeadTag headTag = (HeadTag)htmlTag.getChild(0);
        assertTrue("The HEAD tag should have 2 nodes", 2 == headTag.getChildCount ());
        assertTrue("The second child should be a META tag",headTag.getChild(1) instanceof MetaTag);
        MetaTag metaTag = (MetaTag)headTag.getChild(1);

        assertStringEquals(
            "content",
            "text/html; charset=iso-8859-1",
            metaTag.getAttribute("CONTENT")
        );
    }
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
            new PrototypicalNodeFactory (
                new Tag[]
                {
                    new TitleTag (),
                    new StyleTag (),
                    new MetaTag (),
                }));
        parseAndAssertNodeCount(7);
        assertTrue(node[2] instanceof TitleTag);
        // check the title node
        TitleTag titleTag = (TitleTag) node[2];
View Full Code Here
169
170
171
172
173
174
175
176
177
178
179
            new PrototypicalNodeFactory (
                new Tag[]
                {
                    new TitleTag (),
                    new BaseHrefTag (),
                    new MetaTag (),
                    new StyleTag (),
                }));
        parseAndAssertNodeCount(7);
        assertTrue(node[2] instanceof TitleTag);
        TitleTag titleTag = (TitleTag) node[2];
View Full Code Here
67
68
69
70
71
72
73
74
75
76
        assertTrue("HTML node should have two children",2 == html.getChildCount ());
        assertTrue("Second node should be an HEAD node",html.getChild(1) instanceof HeadTag);
        HeadTag head = (HeadTag)html.getChild(1);
        assertTrue("HEAD node should have eleven children",11 == head.getChildCount ());
        assertTrue("Third child should be a title tag",head.getChild(2) instanceof MetaTag);
        MetaTag metaTag = (MetaTag)head.getChild(2);
        assertStringEquals("Meta Tag Name",description,metaTag.getMetaTagName());
        assertStringEquals("Meta Tag Contents",content,metaTag.getMetaContent());
        assertStringEquals("toHTML()",tag,metaTag.toHtml());
    }
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
121
122
123
124
125
        tag + "\n"+
        "<META name=\"keywords\" content=\"SpamCop spam cop email filter abuse header headers parse parser utility script net net-abuse filter mail program system trace traceroute dns\">\n"+
        "<META name=\"language\" content=\"en\">\n"+
        "<META name=\"owner\" content=\"service@admin.spamcop.net\">\n"+
        "<META HTTP-EQUIV=\"content-type\" CONTENT=\"text/html; charset=ISO-8859-1\">");
        parser.setNodeFactory (new PrototypicalNodeFactory (new MetaTag ()));
        parseAndAssertNodeCount(18);
        assertTrue("Node 8 should be End Tag",node[7] instanceof Tag && ((Tag)node[7]).isEndTag ());
        assertTrue("Node 10 should be META Tag",node[9] instanceof MetaTag);
        MetaTag metaTag;
        metaTag = (MetaTag) node[9];
        assertEquals("Meta Tag 10 Name",description,metaTag.getMetaTagName());
        assertEquals("Meta Tag 10 Contents",content,metaTag.getMetaContent());

        assertTrue("Node 12 should be META Tag",node[11] instanceof MetaTag);
        assertTrue("Node 14 should be META Tag",node[13] instanceof MetaTag);
        assertTrue("Node 16 should be META Tag",node[15] instanceof MetaTag);
        assertTrue("Node 18 should be META Tag",node[17] instanceof MetaTag);

        metaTag = (MetaTag) node[11];
        assertEquals("Meta Tag 12 Name","keywords",metaTag.getMetaTagName());
        assertEquals("Meta Tag 12 Contents","SpamCop spam cop email filter abuse header headers parse parser utility script net net-abuse filter mail program system trace traceroute dns",metaTag.getMetaContent());
        assertNull("Meta Tag 12 Http-Equiv",metaTag.getHttpEquiv());

        metaTag = (MetaTag) node[13];
        assertEquals("Meta Tag 14 Name","language",metaTag.getMetaTagName());
        assertEquals("Meta Tag 14 Contents","en",metaTag.getMetaContent());
        assertNull("Meta Tag 14 Http-Equiv",metaTag.getHttpEquiv());

        metaTag = (MetaTag) node[15];
        assertEquals("Meta Tag 16 Name","owner",metaTag.getMetaTagName());
        assertEquals("Meta Tag 16 Contents","service@admin.spamcop.net",metaTag.getMetaContent());
        assertNull("Meta Tag 16 Http-Equiv",metaTag.getHttpEquiv());

        metaTag = (MetaTag) node[17];
        assertNull("Meta Tag 18 Name",metaTag.getMetaTagName());
        assertEquals("Meta Tag 18 Contents","text/html; charset=ISO-8859-1",metaTag.getMetaContent());
        assertEquals("Meta Tag 18 Http-Equiv","content-type",metaTag.getHttpEquiv());
    }
View Full Code Here
TOP

Related Classes of org.htmlparser.tags.MetaTag

  • modelcrawler.Page
  • org.htmlparser.Attribute
  • org.htmlparser.Parser
  • org.htmlparser.parserapplications.SiteCapturer
  • org.htmlparser.PrototypicalNodeFactory
  • org.htmlparser.scanners.MetaTagScanner
  • org.htmlparser.tests.parserHelperTests.StringParserTest
  • org.htmlparser.tests.ParserTest
  • org.htmlparser.tests.scannersTests.MetaTagScannerTest
  • org.htmlparser.tests.tagTests.MetaTagTest
    • 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.