Package org.htmlparser.util

Examples of org.htmlparser.util.NodeList

64
65
66
67
68
69
70
71
72
73
74
75
      factory.setTextPrototype(new HighlightTextNode("",t2hl,lt,rt));
      Parser htmlParser = new Parser();
      htmlParser.setNodeFactory(factory);
      Parser.createParser(content,"UTF-8");
      htmlParser.setInputHTML(content);
      NodeList nodeList = htmlParser.parse(null);
      content = nodeList.toHtml();
    }catch(Exception e){
      logger.error(e);
    }
    return content;
  }
View Full Code Here
217
218
219
220
221
222
223
224
225
226
227
228
229
    SortedSet<HtmlConverterPSpan> linebreaksFromHtmlTags = new TreeSet<HtmlConverterPSpan>();

    // process
    try {
      Parser parser = new Parser(documentText);
      NodeList list = parser.parse(null);
      HtmlConverterVisitor visitor = new HtmlConverterVisitor(newlineInducingTags);
      list.visitAllNodesWith(visitor);
      visibleSpansSoFar = visitor.getTextSpans();
      linebreaksFromHtmlTags = visitor.getLinebreaksFromHtmlTags();
    } catch (ParserException e) {
      throw new AnalysisEngineProcessException(e);
    }
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
    String html = Common.getInputHtmlGBK(urlStr);
    parser.setInputHTML(html);
    String filerStr = "li";
    NodeFilter filter = new TagNameFilter(filerStr);
    // 取得页面内容中标签为"dl"
    NodeList nodeList = parser.extractAllNodesThatMatch(filter);

    Tag tag = (Tag) nodeList.elementAt(0);

    return tag.toHtml();
  }
View Full Code Here
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
   */
  public static <T extends TagNode> List<T> parseTags(String html, final Class<T> tagType, final String attrbuteName, final String attrbutValue) {
    try {
      Parser parser = new Parser();
      parser.setInputHTML(html);
      NodeList list = parser.parse(new NodeFilter() {

        public boolean accept(Node node) {
          if (node.getClass() == tagType) {
            T tagNode = (T) node;
            if (attrbuteName == null) {
              return true;
            }
            String attrValue = tagNode.getAttribute(attrbuteName);
            if (attrValue != null && attrValue.equals(attrbutValue)) {
              return true;
            }
          }

          return false;
        }
      });
      List<T> tagsList = new ArrayList<T>();
      for (int i = 0; i < list.size(); i++) {
        T t = (T) list.elementAt(i);
        tagsList.add(t);
      }
      return tagsList;
    } catch (Exception e) {
      e.printStackTrace();
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
93
94
        parser.visitAllNodesWith(page);
        assertStringEquals(
            "title",
            "Welcome to the HTMLParser website",
            page.getTitle());
        NodeList bodyNodes = page.getBody();
        assertEquals("number of nodes in body", 1, bodyNodes.size());
        Node node = bodyNodes.elementAt(0);
        assertTrue(
            "expected stringNode but was " + node.getClass().getName(),
            node instanceof StringNode);
        assertStringEquals(
            "body contents",
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
    public void testCreatePageWithTables() throws Exception
    {
        createParser(PAGE_WITH_TABLE);
        HtmlPage page = new HtmlPage(parser);
        parser.visitAllNodesWith(page);
        NodeList bodyNodes = page.getBody();
        assertEquals("number of nodes in body", 2, bodyNodes.size());
        assertXmlEquals(
            "body html",
            "Welcome to HTMLParser"
                + "<table>"
                + "<tr>"
                + "  <td>cell 1</td>"
                + "  <td>cell 2</td>"
                + "</tr>"
                + "</table>",
            bodyNodes.asHtml());
        TableTag tables[] = page.getTables();
        assertEquals("number of tables", 1, tables.length);
        assertEquals("number of rows", 1, tables[0].getRowCount());
        TableRow row = tables[0].getRow(0);
        assertEquals("number of columns", 2, row.getColumnCount());
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
73
74
        parser.addScanner(new TitleScanner(""));
        parser.addScanner(new HtmlScanner());
        parseAndAssertNodeCount(1);
        assertType("html tag", Html.class, node[0]);
        Html html = (Html) node[0];
        NodeList nodeList = new NodeList();
        html.collectInto(nodeList, TitleTag.class);
        assertEquals("nodelist size", 1, nodeList.size());
        Node node = nodeList.elementAt(0);
        assertType("expected title tag", TitleTag.class, node);
        TitleTag titleTag = (TitleTag) node;
        assertStringEquals("title", "Some Title", titleTag.getTitle());
    }
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
70
    public void testCreation()
    {
        StringNode stringNode =
            new StringNode(new StringBuffer("Script Code"), 0, 0);
        NodeList childVector = new NodeList();
        childVector.add(stringNode);
        ScriptTag scriptTag =
            new ScriptTag(
                new TagData(0, 10, "Tag Contents", "tagline"),
                new CompositeTagData(null, null, childVector));
View Full Code Here
70
71
72
73
74
75
76
77
78
        this.tag = tag;
        this.url = url;
        this.reader = reader;
        this.currLine = currLine;
        this.endTag = null;
        this.nodeList = new NodeList();
        this.endTagFound = false;
        this.balance_quotes = balance_quotes;
    }
View Full Code Here
61
62
63
64
65
66
67
68
69
    {
        super(tagData, compositeTagData);
        this.appletClass = compositeTagData.getStartTag().getAttribute("CODE");
        this.codeBase = compositeTagData.getStartTag().getAttribute("CODEBASE");
        this.archive = compositeTagData.getStartTag().getAttribute("ARCHIVE");
        NodeList children = compositeTagData.getChildren();
        appletParams = new Hashtable();
        createAppletParamsTable(children);
    }
View Full Code Here
TOP

Related Classes of org.htmlparser.util.NodeList

  • com.almilli.htmlparser.NodeCollector
  • com.almilli.movierentals.blockbuster.BlockbusterService
  • com.almilli.movierentals.netflix.NetFlixService
  • com.knowgate.hipermail.HtmlMimeBodyPart
  • com.lanyuan.util.HttpClientUtils
  • com.vgo.movie.thread.DetailFilmThread
  • com.waxayaz.TomcatMI.core.utils.repoManager.TomcatRepositoryManager
  • fitnesse.fixtures.PageDriver
  • fitnesse.slim.converters.MapEditor
  • fitnesse.testsystems.slim.HtmlSlimTestSystem
    • 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.