Package org.htmlparser.tags

Examples of org.htmlparser.tags.TitleTag

51
52
53
54
55
56
57
58
59
    parser.addScanner(new StyleScanner("-s"));
    parser.addScanner(new MetaTagScanner("-m"));
    parseAndAssertNodeCount(7);
    assertTrue(node[2] instanceof TitleTag);
    // check the title node
    TitleTag titleTag = (TitleTag) node[2];
    assertEquals("Title", "Yahoo!", titleTag.getTitle());
    assertEquals("Title Scanner", titleScanner, titleTag.getThisScanner());
  }
View Full Code Here
66
67
68
69
70
71
72
73
74
    createParser("<TITLE>SISTEMA TERRA, VOL. VI , No. 1-3, December 1997</TITLE\n" + "</HEAD>");
    TitleScanner titleScanner = new TitleScanner("-t");
    parser.addScanner(titleScanner);
    parseAndAssertNodeCount(2);
    assertTrue("First Node is a title tag", node[0] instanceof TitleTag);
    TitleTag titleTag = (TitleTag) node[0];
    assertEquals("Title", "SISTEMA TERRA, VOL. VI , No. 1-3, December 1997", titleTag.getTitle());

  }
View Full Code Here
82
83
84
85
86
87
88
89
90
        + "</TITLE></head><body>\n" + "<body><html>");
    TitleScanner titleScanner = new TitleScanner("-t");
    parser.addScanner(titleScanner);
    parseAndAssertNodeCount(7);
    assertTrue("Third tag should be a title tag", node[2] instanceof TitleTag);
    TitleTag titleTag = (TitleTag) node[2];
    assertEquals("Title", "Double tags can hang the code\r\n", titleTag.getTitle());

  }
View Full Code Here
96
97
98
99
100
101
102
103
  public void testNoEndTitleTag() throws ParserException {
    createParser("<TITLE>KRP VALIDATION<PROCESS/TITLE>");
    TitleScanner titleScanner = new TitleScanner("-t");
    parser.addScanner(titleScanner);
    parseAndAssertNodeCount(1);
    TitleTag titleTag = (TitleTag) node[0];
    assertEquals("Expected title", "KRP VALIDATION", titleTag.getTitle());
  }
View Full Code Here
105
106
107
108
109
110
111
112
  public void testTitleTagContainsJspTag() throws ParserException {
    createParser("<html><head><title><%=gTitleString%></title><base href=http://www.yahoo.com/ target=_top><meta http-equiv=\"PICS-Label\" content='(PICS-1.1 \"http://www.icra.org/ratingsv02.html\" l r (cz 1 lz 1 nz 1 oz 1 vz 1) gen true for \"http://www.yahoo.com\" r (cz 1 lz 1 nz 1 oz 1 vz 1) \"http://www.rsac.org/ratingsv01.html\" l r (n 0 s 0 v 0 l 0) gen true for \"http://www.yahoo.com\" r (n 0 s 0 v 0 l 0))'><style>a.h{background-color:#ffee99}</style></head>");
    parser.registerScanners();
    parseAndAssertNodeCount(7);
    assertTrue(node[2] instanceof TitleTag);
    TitleTag titleTag = (TitleTag) node[2];
    assertStringEquals("HTML Rendering", "<TITLE><%=gTitleString%></TITLE>", titleTag.toHtml());
  }
View Full Code Here
78
79
80
81
82
83
84
85
86
87
    String title = "";
    Parser parser = new Parser(html);
    NodeList matches = parser.extractAllNodesThatMatch(TITLE_FILTER);
    SimpleNodeIterator it = matches.elements();
    while (it.hasMoreNodes()) {
      TitleTag node = (TitleTag) it.nextNode();
      title = node.getTitle().trim();
    }
    return title;
  }
View Full Code Here
TOP

Related Classes of org.htmlparser.tags.TitleTag

  • de.jungblut.crawl.extraction.ArticleContentExtrator
  • org.htmlparser.PrototypicalNodeFactory
  • org.htmlparser.scanners.TitleScanner
  • org.htmlparser.tests.scannersTests.HtmlTest
  • org.htmlparser.tests.scannersTests.TitleScannerTest
  • org.htmlparser.tests.tagTests.BaseHrefTagTest
  • org.htmlparser.tests.tagTests.BodyTagTest
  • org.htmlparser.tests.tagTests.HtmlTagTest
  • org.htmlparser.tests.tagTests.MetaTagTest
  • org.htmlparser.tests.tagTests.TitleTagTest
    • 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.