Package org.htmlparser.util

Examples of org.htmlparser.util.NodeIterator

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
        assertStringEquals("Raw String", html, bodyTag.toHtml());
    }

    public void testAttributes ()
    {
        NodeIterator iterator;
        Node node;

        try
        {
            createParser("<body style=\"margin-top:4px; margin-left:20px;\" title=\"body\">");
            parser.setNodeFactory (new PrototypicalNodeFactory (new BodyTag ()));
            iterator = parser.elements ();
            node = null;
            while (iterator.hasMoreNodes ())
            {
                node = iterator.nextNode ();
                if (node instanceof BodyTag)
                {
                    assertNotNull ("no style attribute", ((BodyTag)node).getAttribute ("STYLE"));
                    assertNotNull ("no title attribute", ((BodyTag)node).getAttribute ("TITLE"));
                }
                else
                    fail ("not a body tag");
                assertTrue ("more than one node", !iterator.hasMoreNodes ());
            }
            assertNotNull ("no elements", node);
        }
        catch (ParserException pe)
        {
View Full Code Here
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
    {
        String html = "<html><head><title>sample title</title></head><body inserterr=\"true\" yomama=\"false\"><h3 id=\"heading\">big </invalid>heading</h3><ul id=\"things\"><li><br word=\"broken\"/>&gt;moocow<li><applet/>doohickey<li class=\"last\"><b class=\"item\">final<br>item</b></ul></body></html>";
        Lexer l;
        Parser p;
        CssSelectorNodeFilter it;
        NodeIterator i;
        int count;

        l = new Lexer (html);
        p = new Parser (l);
        it = new CssSelectorNodeFilter ("li + li");
        count = 0;
        for (i = p.extractAllNodesThatMatch (it).elements (); i.hasMoreNodes ();)
        {
            assertEquals ("tag name wrong", "LI", ((Tag)i.nextNode()).getTagName());
            count++;
        }
        assertEquals ("wrong count", 2, count);
    }
View Full Code Here
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
            + "Conference final. <p>\n"
            + "</body></html>\n";
        Lexer lexer;
        Parser parser;
        RegexFilter filter;
        NodeIterator iterator;
        int count;

        lexer = new Lexer (html);
        parser = new Parser (lexer);
        filter = new RegexFilter ("(19|20)\\d\\d([- \\\\/.](0[1-9]|1[012])[- \\\\/.](0[1-9]|[12][0-9]|3[01]))?");
        count = 0;
        for (iterator = parser.extractAllNodesThatMatch (filter).elements (); iterator.hasMoreNodes ();)
        {
            assertEquals ("text wrong", target, iterator.nextNode ().toHtml ());
            count++;
        }
        assertEquals ("wrong count", 1, count);
    }
View Full Code Here
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
            ClassNotFoundException,
            ParserException
    {
        Parser parser;
        Vector vector;
        NodeIterator enumeration;
        byte[] data;

        parser = new Parser ("http://htmlparser.sourceforge.net/test/example.html");
        enumeration = parser.elements ();
        vector = new Vector (50);
        while (enumeration.hasMoreNodes ())
            vector.addElement (enumeration.nextNode ());

        data = pickle (parser);
        parser = (Parser)unpickle (data);

        enumeration = parser.elements ();
        while (enumeration.hasMoreNodes ())
            assertEquals (
                "Nodes before and after serialization differ",
                ((Node)vector.remove (0)).toHtml (),
                enumeration.nextNode ().toHtml ());
    }
View Full Code Here
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
            ClassNotFoundException,
            ParserException
    {
        Parser parser;
        Vector vector;
        NodeIterator enumeration;
        byte[] data;

        parser = new Parser ("http://htmlparser.sourceforge.net/test/example.html");
        enumeration = parser.elements ();
        vector = new Vector (50);
        while (enumeration.hasMoreNodes ())
            vector.addElement (enumeration.nextNode ());

        data = pickle (parser);
        parser = (Parser)unpickle (data);

        enumeration = parser.elements ();
        while (enumeration.hasMoreNodes ())
            assertEquals (
                "Nodes before and after serialization differ",
                ((Node)vector.remove (0)).toHtml (),
                enumeration.nextNode ().toHtml ());
    }
View Full Code Here
61
62
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
    }

    public void getParameterTableFor(String tagContents, boolean dump)
    {
        String html;
        NodeIterator iterator;
        Node node;

        html = "<" + tagContents + ">";
        createParser (html);
        parser.setNodeFactory (new PrototypicalNodeFactory (true));
        try
        {
            iterator = parser.elements ();
            node = iterator.nextNode ();
            if (node instanceof Tag)
            {
                tag = (Tag)node;
                attributes = tag.getAttributesEx ();
                if (dump)
                {
                    for (int i = 0; i < attributes.size (); i++)
                    {
                        System.out.print ("Attribute #" + i);
                        Attribute attribute = (Attribute)attributes.elementAt (i);
                        if (null != attribute.getName ())
                            System.out.print (" Name: '" + attribute.getName () + "'");
                        if (null != attribute.getAssignment ())
                            System.out.print (" Assignment: '" + attribute.getAssignment () + "'");
                        if (0 != attribute.getQuote ())
                            System.out.print (" Quote: " + attribute.getQuote ());
                        if (null != attribute.getValue ())
                            System.out.print (" Value: '" + attribute.getValue () + "'");
                        System.out.println ();
                    }
                    System.out.println ();
                }
            }
            else
                attributes = null;
            String string = node.toHtml ();
            assertEquals ("toHtml differs", html, string);
            assertTrue ("shouldn't be any more nodes", !iterator.hasMoreNodes ());
        }
        catch (ParserException pe)
        {
            fail (pe.getMessage ());
        }
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
        final String DOCTYPE = "<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.0 Transitional//EN\">";
        final String HTML = DOCTYPE + "\n<HTML>\n  <HEAD>\n    <TITLE>HTMLParserDocTypeBugTest</TITLE>\n  </HEAD>\n  <BODY>\n    HTMLParser DOCTYPE node bug test.\n  </BODY>\n</HTML>";

        createParser(HTML);

        NodeIterator e = parser.elements();
        Node node = e.nextNode();

        // First node is doctype
        assertStringEquals("Doctype element output is incorrect.", DOCTYPE, node.toHtml());
    }
View Full Code Here
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
     */
    public void testJIS ()
        throws ParserException
    {
        Parser parser;
        NodeIterator iterator;
       
        parser = new Parser ("http://www.009.com/");
        try
        {
            iterator = parser.elements ();
            while (iterator.hasMoreNodes ())
                checkTagNames (iterator.nextNode ());
        }
        catch (EncodingChangeException ece)
        {
            parser.reset ();
            iterator = parser.elements ();
            while (iterator.hasMoreNodes ())
                checkTagNames (iterator.nextNode ());
        }
    }
View Full Code Here
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
    public void testConjoined ()
        throws
            ParserException
    {
        StringBuffer buffer;
        NodeIterator iterator;
        Node node;
        String expected;

        expected = "The Title\nThis is the body.";
        String html1 = "<html><title>The Title\n</title>" +
            "<body>This is <a href=\"foo.html\">the body</a>.</body></html>";
        createParser (html1);
        buffer = new StringBuffer ();
        for (iterator = parser.elements (); iterator.hasMoreNodes (); )
        {
            node = iterator.nextNode ();
            String text = node.toPlainTextString ();
            buffer.append (text);
        }
        assertStringEquals ("conjoined text", expected, buffer.toString ());

        String html2 = "<html><title>The Title</title>\n" +
            "<body>This is <a href=\"foo.html\">the body</a>.</body></html>";
        createParser (html2);
        buffer = new StringBuffer ();
        for (iterator = parser.elements (); iterator.hasMoreNodes (); )
        {
            node = iterator.nextNode ();
            String text = node.toPlainTextString ();
            buffer.append (text);
        }
        assertStringEquals ("conjoined text", expected, buffer.toString ());
       
        String html3 = "<html><title>The Title</title>" +
            "<body>\nThis is <a href=\"foo.html\">the body</a>.</body></html>";
        createParser (html3);
        buffer = new StringBuffer ();
        for (iterator = parser.elements (); iterator.hasMoreNodes (); )
        {
            node = iterator.nextNode ();
            String text = node.toPlainTextString ();
            buffer.append (text);
        }
        assertStringEquals ("conjoined text", expected, buffer.toString ());
    }
View Full Code Here
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
     */
    public void testStackOverflow ()
        throws
            ParserException
    {
        NodeIterator iterator;
        Node node;
        String html;
                                                                                                                                                       
        html = "<a href = \"http://test.com\" />";
        createParser (html);
        for (iterator = parser.elements (); iterator.hasMoreNodes (); )
        {
            node = iterator.nextNode ();
            String text = node.toHtml ();
            assertStringEquals ("no overflow", html, text);
        }
        html = "<a href=\"http://test.com\"/>";
        createParser (html);
        for (iterator = parser.elements (); iterator.hasMoreNodes (); )
        {
            node = iterator.nextNode ();
            String text = node.toHtml ();
            assertStringEquals ("no overflow", html, text);
        }
        html = "<a href = \"http://test.com\"/>";
        createParser (html);
        for (iterator = parser.elements (); iterator.hasMoreNodes (); )
        {
            node = iterator.nextNode ();
            String text = node.toHtml ();
            assertStringEquals ("no overflow", html, text);
        }
    }
View Full Code Here
TOP

Related Classes of org.htmlparser.util.NodeIterator

  • com.almilli.htmlparser.BetweenFilter
  • com.almilli.movierentals.blockbuster.BlockbusterService
  • com.almilli.movierentals.netflix.NetFlixService
  • org.htmlparser.Parser
  • org.htmlparser.tests.filterTests.FilterTest
  • org.htmlparser.tests.InstanceofPerformanceTest
  • org.htmlparser.tests.lexerTests.AttributeTests
  • org.htmlparser.tests.lexerTests.LexerTests
  • org.htmlparser.tests.ParserTest
  • org.htmlparser.tests.ParserTestCase
    • 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.