Package org.htmlparser

Examples of org.htmlparser.NodeFilter

922
923
924
925
926
927
928
929
930
931
932
            }
     
            String url = MessageFormat.format(SEARCH_POPULAR_URL, URLEncoder.encode(query, "UTF-8"), start);
      parser.setURL(url);

      NodeFilter discFilter = new AndFilter(
          new NodeClassFilter(TableRow.class),
          new HasChildFilter(new HasChildFilter(new CssClassFilter("searchDisplay")))
      );

      NodeCollector infoCollector = new NodeCollector(new NodeFilter[] {
View Full Code Here
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
      if (log.isDebugEnabled()) {
        log.debug("Adding movie at url " + url);
      }
      parser.setURL(url);

      NodeFilter discFilter = new AndFilter(
        new CssClassFilter("disc"),
        new HasChildFilter(new HasChildFilter(
            new HasAttributeFilter("href", "/catalog/movieDetails/" + item.getMovieId())))
      );
     
      NodeFilter removeFilter = new AndFilter(
          new NodeClassFilter(LinkTag.class),
          new CssClassFilter("bvr-qremove")
      );

      NodeList discNodes = parser.extractAllNodesThatMatch(discFilter);
View Full Code Here
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
            Node infoNode = infoCollector.getNode(i++);
           
            //info
            NodeList list = new NodeList();
            NodeFilter groupsFilter = new CssClassFilter("movieInfo");
            infoNode.collectInto(list, groupsFilter);
            setListValues(item, list);
           
            //summary
            list.removeAll();
            NodeFilter summaryFilter = new CssClassFilter("summary");
            infoNode.collectInto(list, summaryFilter);
            item.setSummary(NodeUtils.getTextData(list));
           
            item.addDetailFlag(MovieItem.DETAIL_MEDIUM);
           
View Full Code Here
589
590
591
592
593
594
595
596
597
598
599
        }
        return item;
    }
 
  private void parseMovieQueue(Node queue, List<MovieItem> items) {
    NodeFilter discFilter = new CssClassFilter("disc");

        NodeCollector infoCollector = new NodeCollector(new NodeFilter[] {
                new CssClassFilter("bvr-qremove"),
                new AndFilter(new NodeClassFilter(LinkTag.class),
                        new HasParentFilter(new CssClassFilter("title"))),
View Full Code Here
908
909
910
911
912
913
914
915
916
917
918
    }
      if (categories == null) {
      try {
        parser.setURL(CATEGORY_LIST_URL);
 
        NodeFilter categoryFilter = new AndFilter(
            new HasAncestorFilter(
                                new OrFilter(new CssClassFilter("column33"),
                                        new CssClassFilter("column34"))),
            new CssClassFilter("listMain")
        );
View Full Code Here
938
939
940
941
942
943
944
945
946
947
948
     
      return categories;
    }
   
    private void parseCategory(Node categoryNode, List<Category> categories) throws ParserException {
      NodeFilter linkFilter = new NodeClassFilter(LinkTag.class);
     
      NodeList links = new NodeList();
      categoryNode.collectInto(links, linkFilter);
     
      if (links.size() == 0) {
View Full Code Here
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
     */
    public void parseHtml(URI uri, InputStream content)
    {
        ByteArrayOutputStream output = null;  //####TODO: Add in MIME type detection to this stream
        Parser                parser = null;
        NodeFilter            filter = null;
        NodeList              list   = null;
       
       
        if (uriFilter.isURIInternal(uri) && content != null)
        {
            log.debug("Parsing HTML from URI " + uri.toString());
       
            try
            {
                log.debug("Copying content.");
       
                output = new ByteArrayOutputStream();
                IOUtils.copy(content, output);
               
                log.debug("Creating filter.");
       
                //####TODO: Dependency inject this crap
                filter = new AndFilter(new NodeClassFilter(LinkTag.class),
                                       new NodeFilter()
                                       {
                                           public boolean accept(Node node)
                                           {
                                               return(!((LinkTag)node).isMailLink());
                                           }
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
     * @return A list of all links on the page as URLs.
     * @exception ParserException If the parse fails.
     */
    protected URL[] extractLinks () throws ParserException
    {
        NodeFilter filter;
        NodeList list;
        Vector vector;
        LinkTag link;
        URL[] ret;

View Full Code Here
152
153
154
155
156
157
158
159
160
161
162
        return (false);
    }

    private NodeFilter parse ()
    {
        NodeFilter ret;
       
        ret = null;
        do
        {
            switch (tokentype)
View Full Code Here
195
196
197
198
199
200
201
202
203
204
205
    }

    private NodeFilter parseSimple ()
    {
        boolean done = false;
        NodeFilter ret = null;

        if (token != null)
            do
            {
                switch (tokentype)
View Full Code Here
TOP

Related Classes of org.htmlparser.NodeFilter

  • cn.edu.pku.dr.requirement.elicitation.tools.HtmlTransformer
  • com.almilli.movierentals.blockbuster.BlockbusterService
  • com.almilli.movierentals.netflix.NetFlixService
  • com.lanyuan.util.HttpClientUtils
  • fitnesse.fixtures.PageDriver
  • htmltrans.HtmlTransformer
  • modelcrawler.Page
  • net.sf.sitstart.svc.internal.impl.HtmlParserLinkExtractor
  • net.sf.sitstart.svc.responseparser.impl.HtmlParserResponseParser
  • org.htmlparser.beans.LinkBean
    • 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.