Package org.htmlparser.util

Examples of org.htmlparser.util.NodeList

224
225
226
227
228
229
230
231
232
233
234
235
236
    SortedSet<HtmlConverterPSpan> linebreaksFromHtmlTags = new TreeSet<HtmlConverterPSpan>();

    // process
    try {
      Parser parser = new Parser(documentText);
      NodeList list = parser.parse(null);
      HtmlConverterVisitor visitor = new HtmlConverterVisitor(newlineInducingTags, skipWhitespaces);
      list.visitAllNodesWith(visitor);
      visibleSpansSoFar = visitor.getTextSpans();
      linebreaksFromHtmlTags = visitor.getLinebreaksFromHtmlTags();
    } catch (ParserException e) {
      throw new AnalysisEngineProcessException(e);
    }
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
62
63
    String documentText = jcas.getDocumentText();
    List<AnnotationFS> annotations = new ArrayList<AnnotationFS>();
    List<AnnotationFS> annotationStack = new ArrayList<AnnotationFS>();
    try {
      Parser parser = new Parser(documentText);
      NodeList list = parser.parse(null);
      HtmlVisitor visitor = new HtmlVisitor(jcas, onlyContent);
      list.visitAllNodesWith(visitor);
      annotations = visitor.getAnnotations();
      annotationStack = visitor.getAnnotationStack();
    } catch (ParserException e) {
      throw new AnalysisEngineProcessException(e);
    }
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
88
89
      }

      String document = sb.toString();

      Parser parser = new Parser(document);
      NodeList list = parser.parse(null);
      HtmlDocumentationVisitor visitor = new HtmlDocumentationVisitor(document);
      list.visitAllNodesWith(visitor);
      map.putAll(visitor.getMap());
    } catch (Exception e) {
      RutaIdeUIPlugin.error(e);
    }
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
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
        try{

            htmlBuffer = "<html>" + htmlBuffer + "</html>";
            Parser parser = new Parser();
            parser.setInputHTML(htmlBuffer);
            NodeList nodelist = parser.parse(null);

            NodeList tableList = nodelist.extractAllNodesThatMatch(new TagNameFilter("TABLE"), true);
            NodeList  headList = tableList.extractAllNodesThatMatch(new TagNameFilter("THEAD"), true);
            NodeList  footList = tableList.extractAllNodesThatMatch(new TagNameFilter("TFOOT"), true);
            NodeList  rowList = tableList.extractAllNodesThatMatch(new TagNameFilter("TR"), true);
           
            //Create a ParserUtils var
            ParserUtils pu = new ParserUtils();
            //Set rowCount to size of rowList
            rowCount = rowList.size();
           
           
            HSSFFont boldFont = wb.createFont();
            boldFont.setBoldweight(HSSFFont.BOLDWEIGHT_BOLD);
            HSSFCellStyle boldStyle = wb.createCellStyle();
            boldStyle.setFont(boldFont);
            boldStyle.setWrapText(true);
           
            //Loop through excel 'Rows'
            for ( int i = 0; i < rowList.size(); i++ ) {
                HSSFRow row;
                String htmlRow = rowList.elementAt(i).toHtml().trim();
                String[] splitHtmlRow;
                List<String> elements = new ArrayList<String>();
               
                if(i == 0 && headList.size() == 1){
                    row = sheet.createRow((short) i);
                    htmlRow = htmlRow.replace("<th></th>","<th> </th>");
                    htmlRow = htmlRow.replace("<TH></TH>","<th> </th>");
                    htmlRow = htmlRow.replace("</span>", " </span>");
                    elements.add("tr");
                    elements.add("th");
                    if (htmlRow.indexOf("<a href=") > -1) {
                      elements.add("a");
                    }
                    if (htmlRow.indexOf("<span ") > -1) {
                      elements.add("span");
                    }
                } else if(i == 1 && footList.size() == 1){
                    row = sheet.createRow((short) rowList.size() - 1);
                    htmlRow = pu.trimTags(htmlRow, new String[]{"span"},false,false);
                    htmlRow = htmlRow.replace("<td></td>","<td> </td>");
                    htmlRow = htmlRow.replace("<TD></TD>","<td> </td>");
                    elements.add("tr");
                    elements.add("td");
View Full Code Here
19
20
21
22
23
24
25
26
27
28
29
30
31
 
  protected Node getElementById(Parser parser, String id) {
    parser.reset();
    NodeFilter filter = new CssSelectorNodeFilter("#" + id);
    try {
      NodeList list = parser.extractAllNodesThatMatch(filter);
      if (list.size() > 0) {
        return list.elementAt(0);
      }
    } catch (ParserException e) {
      // TODO Auto-generated catch block
      e.printStackTrace();
    }
View Full Code Here
23
24
25
26
27
28
29
30
31
32
33
34
35
    protected static Node getElementById(Parser parser, String id) {
        parser.reset();
        NodeFilter filter = new CssSelectorNodeFilter("#" + id);
        try {
            NodeList list = parser.extractAllNodesThatMatch(filter);
            if (list.size() > 0) {
                return list.elementAt(0);
            }
        } catch (ParserException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
View Full Code Here
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
        try
        {
            Parser parser = Parser.createParser(htmlData, null);

            NodeList heads = parser.parse(new TagNameFilter("HEAD"));
            if (heads.size() != 1)
                throw new DiscoveryException(
                        "HTML response must have exactly one HEAD element, " +
                                "found " + heads.size() + " : " + heads.toHtml());
            Node head = heads.elementAt(0);
            for (NodeIterator i = head.getChildren().elements();
                 i.hasMoreNodes();)
            {
                Node node = i.nextNode();
                if (node instanceof TagNode)
View Full Code Here
107
108
109
110
111
112
113
114
115
116
117
118
      return fetchCount;
   }

   private int fetchBoards(File rootDir, Parser parser, OrFilter filter, int bingoIdx) throws Exception {
      int fetchCount = 0;
      NodeList list = parser.extractAllNodesThatMatch(filter);
      SimpleNodeIterator simpleNodeIterator = list.elements();
      while (simpleNodeIterator.hasMoreNodes()) {
         Node node = simpleNodeIterator.nextNode();
         if (node instanceof ImageTag) {
            ImageTag img = (ImageTag) node;
            String attribute = img.getAttribute("src");
View Full Code Here
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
  } 

  private void trouverLiens() throws Exception{
    Parser parser;
    NodeList listUrlNode;
    NodeList listTitleNode;
    String tmpString;
    String tmpLien;
    String tmpValeur;
    LinkedList<HashMap> listUrl = new LinkedList<HashMap>();
    HashMap<String, String> tmpHashMap;
    String tmpRecherche;
    int i=0;

    try {
      tmpRecherche = "http://www.imdb.com/find?s=tt&q=" + localParent.getJValeurNom().getText().replaceAll(" ", "+");

      parser = new Parser(tmpRecherche);

      listTitleNode = parser.extractAllNodesThatMatch(new NodeClassFilter (TitleTag.class));
      //On commence par d�tecter le titre
      for(i = 0;i < listTitleNode.size(); i++){
        tmpString = listTitleNode.elementAt(i).toHtml();
        if(tmpString.indexOf("IMDb Title  Search") <= -1){
          urlFilm = tmpRecherche;
        }
      }
View Full Code Here
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
  }

  private void recupererInfoFilm() throws Exception{
    Parser divParser;
    NodeList listDiv;
    Node tmpNode; 

    boolean acteursVu = false;
    boolean titreVu = false;
    boolean realisateurVu = false;
    boolean paysVu = false;
    boolean tempsVu = false;
    boolean genreVu = false;
    boolean awardsVu = false;
    boolean dateSortieVue = false;
    boolean imageVues = false;
    int indexDeb = 0;
    int indexFin = 0;


    try{
      divParser = new Parser(urlFilm);
      listDiv = divParser.extractAllNodesThatMatch (new NodeClassFilter (Div.class));
      for (int i = 0; i < listDiv.size(); i++){
        NodeList tmpDivNodeContent = listDiv.elementAt(i).getChildren();

        if(tmpDivNodeContent != null){
          for(int j = 0; j< tmpDivNodeContent.size(); j++){
            tmpNode = tmpDivNodeContent.elementAt(j);

            if(tmpNode.toHtml().indexOf("alt=\"Cast\"") > -1 && !acteursVu){
              LinkedList<Acteurs> tmpListActeur = new LinkedList<Acteurs>();
              Acteurs tmpActeur = null;
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.