Package org.htmlparser

Examples of org.htmlparser.NodeFilter

274
275
276
277
278
279
280
281
282
283
284
        throw new IllegalArgumentException ("pseudoclasses not implemented yet");
    }

    private NodeFilter parseAttributeExp ()
    {
        NodeFilter ret = null;
        if (tokentype == NAME)
        {
            String attrib = token;
            nextToken ();
            if ("]".equals (token))
View Full Code Here
95
96
97
98
99
100
101
102
103
104
105
    public TableColumn[] getColumns ()
    {
        NodeList kids;
        NodeClassFilter cls;
        HasParentFilter recursion;
        NodeFilter filter;
        TableColumn[] ret;

        kids = getChildren ();
        if (null != kids)
        {
View Full Code Here
145
146
147
148
149
150
151
152
153
154
155
    public TableHeader[] getHeaders ()
    {
        NodeList kids;
        NodeClassFilter cls;
        HasParentFilter recursion;
        NodeFilter filter;
        TableHeader[] ret;

        kids = getChildren ();
        if (null != kids)
        {
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
    public TableRow[] getRows ()
    {
        NodeList kids;
        NodeClassFilter cls;
        HasParentFilter recursion;
        NodeFilter filter;
        TableRow[] ret;

        kids = getChildren ();
        if (null != kids)
        {
View Full Code Here
92
93
94
95
96
97
98
99
100
101
102
      setContent(sb.toString());
     
      par.reset();
      _links.clear();
     
      NodeFilter filter = new OrFilter( new NodeFilter[] {
          new TagNameFilter("A"),
          new TagNameFilter("META")
          }
      );
      NodeList list = par.parse( filter );
View Full Code Here
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
     */
    public void extractLinks(Asset asset, InputStream content)
    {
        ByteArrayOutputStream output = null;
        Parser                parser = null;
        NodeFilter            filter = null;
        NodeList              list   = null;
       
       
        // PRECONDITIONS
        assert asset != null : "asset must not be null.";
       
        // Body
        if (content != null)
        {
            try
            {
                IOUtils.copy(content, output);
               
                //####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
332
333
334
335
336
337
338
339
340
341
342
            // recurseHtmlNodes(nodelist, base);
        } // else maybe it is a parsed Flash document? Anyone? :-)
    }
   
    private void processHtml(HttpUrl base, NodeList nodelist) {
        NodeFilter filter = new HasAttributeFilter("href");
        filter = new OrFilter(filter, new HasAttributeFilter("src"));
        filter = new OrFilter(filter, new HasAttributeFilter("onclick"));
        filter = new OrFilter(filter, new HasAttributeFilter("onblur"));
        try {
            NodeList links = nodelist.extractAllNodesThatMatch(filter);
View Full Code Here
106
107
108
109
110
111
112
113
114
115
116
     * Get the underlying node filter object.
     * @return The node filter object suitable for serialization.
     */
    public NodeFilter getNodeFilter ()
    {
        NodeFilter filter;
        HasChildFilter ret;
       
        ret = new HasChildFilter ();

        ret.setRecursive (mFilter.getRecursive ());
View Full Code Here
139
140
141
142
143
144
145
146
147
148
149
     * Get the underlying node filter's subordinate filters.
     * @return The node filter object's contained filters.
     */
    public NodeFilter[] getSubNodeFilters ()
    {
        NodeFilter filter;
        NodeFilter[] ret;

        filter = mFilter.getChildFilter ();
        if (null != filter)
            ret = new NodeFilter[] { filter };
View Full Code Here
147
148
149
150
151
152
153
154
155
156
157
        return (false);
    }

    private NodeFilter parse ()
    {
        NodeFilter ret;
       
        ret = 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.