Package org.htmlparser.tags

Examples of org.htmlparser.tags.MetaTag

61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
   {
    String metadata = ""; String author = "";
    for (int i = 0; i < nodelist2.size(); i++)
    { if (nodelist2.elementAt(i) == null) continue;
    String meta = nodelist2.elementAt(i).getText(); meta = StringTools.filterChars(meta);
    MetaTag mtag = new MetaTag(); mtag.setText("<" + meta + ">");
    String tagName = mtag.getMetaTagName();
    if (tagName == null) continue;
    if (tagName.equalsIgnoreCase("keywords"))
    { metadata += mtag.getMetaContent(); }
    if (tagName.equalsIgnoreCase("authors") ||
      tagName.equalsIgnoreCase("author") )
    { author += mtag.getMetaContent(); }
    } // end of for
    doc.setAuthor(author); doc.setMetadata(metadata);
   } // eod of if

   //*-- Populate the contents of the contents with the entire text from the  web page
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
        parser.registerScanners();

        parseAndAssertNodeCount(9);
        assertTrue("Node 5 should be META Tag", node[4] instanceof MetaTag);
        MetaTag metaTag;
        metaTag = (MetaTag) node[4];
        assertStringEquals(
            "Meta Tag 4 Name",
            "description",
            metaTag.getMetaTagName());
        assertStringEquals(
            "Meta Tag 4 Contents",
            "Protecting the internet community through technology, not legislation.  SpamCop eliminates spam.  Automatically file spam reports with the network administrators who can stop spam at the source.  Subscribe, and filter your email through powerful statistical analysis before it reaches your inbox.",
            metaTag.getMetaContent());
        assertStringEquals(
            "toHTML()",
            "<META CONTENT=\"Protecting the internet community through technology, not legislation.  SpamCop eliminates spam.  Automatically file spam reports with the network administrators who can stop spam at the source.  Subscribe, and filter your email through powerful statistical analysis before it reaches your inbox.\" NAME=\"description\">",
            metaTag.toHtml());
    }
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
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
        parser.addScanner(scanner);

        parseAndAssertNodeCount(11);
        assertTrue("Node 5 should be End Tag", node[5] instanceof EndTag);
        assertTrue("Node 6 should be META Tag", node[6] instanceof MetaTag);
        MetaTag metaTag;
        metaTag = (MetaTag) node[6];
        assertEquals(
            "Meta Tag 6 Name",
            "description",
            metaTag.getMetaTagName());
        assertEquals(
            "Meta Tag 6 Contents",
            "Protecting the internet community through technology, not legislation.  SpamCop eliminates spam.  Automatically file spam reports with the network administrators who can stop spam at the source.  Subscribe, and filter your email through powerful statistical analysis before it reaches your inbox.",
            metaTag.getMetaContent());

        assertTrue("Node 7 should be META Tag", node[7] instanceof MetaTag);
        assertTrue("Node 8 should be META Tag", node[8] instanceof MetaTag);
        assertTrue("Node 9 should be META Tag", node[9] instanceof MetaTag);

        metaTag = (MetaTag) node[7];
        assertEquals("Meta Tag 7 Name", "keywords", metaTag.getMetaTagName());
        assertEquals(
            "Meta Tag 7 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 7 Http-Equiv", metaTag.getHttpEquiv());

        metaTag = (MetaTag) node[8];
        assertEquals("Meta Tag 8 Name", "language", metaTag.getMetaTagName());
        assertEquals("Meta Tag 8 Contents", "en", metaTag.getMetaContent());
        assertNull("Meta Tag 8 Http-Equiv", metaTag.getHttpEquiv());

        metaTag = (MetaTag) node[9];
        assertEquals("Meta Tag 9 Name", "owner", metaTag.getMetaTagName());
        assertEquals(
            "Meta Tag 9 Contents",
            "service@admin.spamcop.net",
            metaTag.getMetaContent());
        assertNull("Meta Tag 9 Http-Equiv", metaTag.getHttpEquiv());

        metaTag = (MetaTag) node[10];
        assertNull("Meta Tag 10 Name", metaTag.getMetaTagName());
        assertEquals(
            "Meta Tag 10 Contents",
            "text/html; charset=ISO-8859-1",
            metaTag.getMetaContent());
        assertEquals(
            "Meta Tag 10 Http-Equiv",
            "content-type",
            metaTag.getHttpEquiv());

        assertEquals("This Scanner", scanner, metaTag.getThisScanner());
    }
View Full Code Here
122
123
124
125
126
127
128
129
130
131
132
133
            "http://www.google.com/test/index.html");
        MetaTagScanner scanner = new MetaTagScanner("-t");
        parser.addScanner(scanner);
        parseAndAssertNodeCount(1);
        assertTrue("Node should be meta tag", node[0] instanceof MetaTag);
        MetaTag metaTag = (MetaTag) node[0];
        assertEquals("Meta Tag Name", "Description", metaTag.getMetaTagName());
        assertEquals(
            "Content",
            "Ethnoburb </I>versus Chinatown: Two Types of Urban Ethnic Communities in Los Angeles",
            metaTag.getMetaContent());
    }
View Full Code Here
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
                + "</head>"
                + "</html>");
        parser.registerScanners();
        parseAndAssertNodeCount(5);
        assertType("Meta Tag expected", MetaTag.class, node[2]);
        MetaTag metaTag = (MetaTag) node[2];

        assertStringEquals(
            "http-equiv",
            "content-type",
            metaTag.getHttpEquiv());
        assertStringEquals(
            "content",
            "text/html; charset=windows-1252",
            metaTag.getMetaContent());
    }
View Full Code Here
179
180
181
182
183
184
185
186
                + "</body>"
                + "</html>");
        parser.registerScanners();
        parseAndAssertNodeCount(11);
        assertType("meta tag", MetaTag.class, node[3]);
        MetaTag metaTag = (MetaTag) node[3];
        assertStringEquals("meta content", "a<b", metaTag.getMetaContent());
    }
View Full Code Here
59
60
61
62
63
64
65
        Hashtable table = tag.getAttributes();
        String metaTagName = (String) table.get("NAME");
        String metaTagContents = (String) table.get("CONTENT");
        String httpEquiv = (String) table.get("HTTP-EQUIV");

        return new MetaTag(tagData, httpEquiv, metaTagName, metaTagContents);
    }
View Full Code Here
277
278
279
280
281
282
283
284
285
286
287
288
                + "</body>"
                + "</html>");
        parser.registerScanners();
        parseAndAssertNodeCount(10);
        assertType("fourth node", MetaTag.class, node[4]);
        MetaTag metaTag = (MetaTag) node[4];

        assertStringEquals(
            "content",
            "text/html; charset=iso-8859-1",
            metaTag.getAttribute("CONTENT"));
    }
View Full Code Here
884
885
886
887
888
889
890
891
892
893
894
     */
    public NodeIterator elements() throws ParserException
    {
        boolean remove_scanner;
        Node node;
        MetaTag meta;
        String httpEquiv;
        String charset;
        boolean restart;
        EndTag end;
        IteratorImpl ret;
View Full Code Here
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
        boolean remove_scanner,
        IteratorImpl ret)
        throws ParserException
    {
        Node node;
        MetaTag meta;
        String httpEquiv;
        String charset;
        EndTag end;
        if (null != url_conn)
            try
            {
                if (null == scanners.get("-m"))
                {
                    addScanner(new MetaTagScanner("-m"));
                    remove_scanner = true;
                }

                /* pre-read up to </HEAD> looking for charset directive */
                while (null != (node = ret.peek()))
                {
                    if (node instanceof MetaTag)
                    { // check for charset on Content-Type
                        meta = (MetaTag) node;
                        httpEquiv = meta.getAttribute("HTTP-EQUIV");
                        if ("Content-Type".equalsIgnoreCase(httpEquiv))
                        {
                            charset = getCharset(meta.getAttribute("CONTENT"));
                            if (!charset.equalsIgnoreCase(character_set))
                            { // oops, different character set, restart
                                character_set = charset;
                                recreateReader();
                                ret =
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.