Package org.htmlparser.tags

Examples of org.htmlparser.tags.LinkTag

269
270
271
272
273
274
275
276
277
278
279
280
281
        return;
      }

      for (int i = 0; i < list.size(); i++)
      {
        LinkTag link = (LinkTag) list.elementAt(i);
        String anchor = link.getLinkText();
        String url = normalizeURL(link.extractLink());

        if (url == null)
        {
          continue;
        }
View Full Code Here
198
199
200
201
202
203
204
205
206
207
208
209
210
        reporter.incrCounter(LinkCounter.PARSER_FAILED, 1);
        return;
      }

      for(int i = 0; i < list.size(); i++) {
        LinkTag link = (LinkTag) list.elementAt(i);
        String anchor = link.getLinkText();
        String url = link.extractLink();

        if(url == null) {
          continue;
        }
View Full Code Here
154
155
156
157
158
159
160
161
162
163
164
165
166
                    {
                        // then we need to download the binary
                        binUrlStr= input.getAttribute("src");
                    }
        } else if (node instanceof LinkTag){
          LinkTag link = (LinkTag)node;
          if (link.getChild(0) instanceof ImageTag){
            ImageTag img = (ImageTag)link.getChild(0);
            binUrlStr = img.getImageURL();
          }
        } else if (node instanceof ScriptTag){
          ScriptTag script = (ScriptTag)node;
          binUrlStr = script.getAttribute("src");
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
    protected URL[] extractLinks () throws ParserException
    {
        NodeFilter filter;
        NodeList list;
        Vector vector;
        LinkTag link;
        URL[] ret;

        mParser.reset ();
        filter = new NodeClassFilter (LinkTag.class);
        try
        {
            list = mParser.extractAllNodesThatMatch (filter);
        }
        catch (EncodingChangeException ece)
        {
            mParser.reset ();
            list = mParser.extractAllNodesThatMatch (filter);
        }
        vector = new Vector();
        for (int i = 0; i < list.size (); i++)
            try
            {
                link = (LinkTag)list.elementAt (i);
                vector.add(new URL (link.getLink ()));
            }
            catch (MalformedURLException murle)
            {
                //vector.remove (i);
                //i--;
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
          new TagNameFilter("META")
          }
      );
      NodeList list = par.parse( filter );
      System.out.println("Url: " + _url.toString() + " found " + list.size() + " items.");
      LinkTag lt = null;
      for (SimpleNodeIterator e = list.elements (); e.hasMoreNodes (); ) {
        Node n = e.nextNode();
        if (n.getClass() == LinkTag.class ) {
          lt = (LinkTag)n;
          if ( FileTypes.isAllowedFileType(lt.getLink())) {
            String url = par.getLexer().getPage().getAbsoluteURL(lt.getLink());
            URL c;
            try {
              c = new URL(url);
              Page p = new Page(c.toString());
              if ( _crawler != null ) {
View Full Code Here
152
153
154
155
156
157
158
159
160
161
162
163
164
                if (ATT_IS_IMAGE.equalsIgnoreCase(tag.getAttribute(ATT_TYPE))) {
                    // then we need to download the binary
                    binUrlStr = tag.getAttribute(ATT_SRC);
                }
            } else if (tag instanceof LinkTag) {
                LinkTag link = (LinkTag) tag;
                if (link.getChild(0) instanceof ImageTag) {
                    ImageTag img = (ImageTag) link.getChild(0);
                    binUrlStr = img.getImageURL();
                }
            } else if (tag instanceof ScriptTag) {
                binUrlStr = tag.getAttribute(ATT_SRC);
            } else if (tag instanceof FrameTag) {
View Full Code Here
150
151
152
153
154
155
156
157
158
159
160
161
162
                if (ATT_IS_IMAGE.equalsIgnoreCase(tag.getAttribute(ATT_TYPE))) {
                    // then we need to download the binary
                    binUrlStr = tag.getAttribute(ATT_SRC);
                }
            } else if (tag instanceof LinkTag) {
                LinkTag link = (LinkTag) tag;
                if (link.getChild(0) instanceof ImageTag) {
                    ImageTag img = (ImageTag) link.getChild(0);
                    binUrlStr = img.getImageURL();
                }
            } else if (tag instanceof ScriptTag) {
                binUrlStr = tag.getAttribute(ATT_SRC);
            } else if (tag instanceof FrameTag) {
View Full Code Here
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
    protected URL[] extractLinks () throws ParserException
    {
        NodeFilter filter;
        NodeList list;
        Vector vector;
        LinkTag link;
        URL[] ret;

        mParser.reset ();
        filter = new NodeClassFilter (LinkTag.class);
        try
        {
            list = mParser.extractAllNodesThatMatch (filter);
        }
        catch (EncodingChangeException ece)
        {
            mParser.reset ();
            list = mParser.extractAllNodesThatMatch (filter);
        }
        vector = new Vector();
        for (int i = 0; i < list.size (); i++)
            try
            {
                link = (LinkTag)list.elementAt (i);
                vector.add(new URL (link.getLink ()));
            }
            catch (MalformedURLException murle)
            {
                //vector.remove (i);
                //i--;
View Full Code Here
312
313
314
315
316
317
318
319
320
321
322
        registerTag (new HeadingTag ());
        registerTag (new ImageTag ());
        registerTag (new InputTag ());
        registerTag (new JspTag ());
        registerTag (new LabelTag ());
        registerTag (new LinkTag ());
        registerTag (new MetaTag ());
        registerTag (new ObjectTag ());
        registerTag (new OptionTag ());
        registerTag (new ParagraphTag ());
        registerTag (new ProcessingInstructionTag ());
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
94
95
        // The first node should be a Text-  with the text - view these documents, you must have
        assertTrue("First node should be a Text",node[0] instanceof Text);
        Text stringNode = (Text)node[0];
        assertEquals("Text of the Text","view these documents, you must have ",stringNode.getText());
        assertTrue("Second node should be a link node",node[1] instanceof LinkTag);
        LinkTag linkNode = (LinkTag)node[1];
        assertEquals("Link is","http://www.adobe.com",linkNode.getLink());
        assertEquals("Link text is","Adobe \nAcrobat Reader",linkNode.getLinkText());

        assertTrue("Third node should be a string node",node[2] instanceof Text);
        Text stringNode2 = (Text)node[2];
        assertEquals("Contents of third node"," installed on your computer.",stringNode2.getText());
    }
View Full Code Here
TOP

Related Classes of org.htmlparser.tags.LinkTag

  • com.almilli.movierentals.blockbuster.BlockbusterService
  • com.almilli.movierentals.netflix.NetFlixService
  • com.knowgate.hipermail.HtmlMimeBodyPart
  • de.jungblut.crawl.extraction.OutlinkExtractor
  • edu.umd.cloud9.webgraph.ClueExtractLinks$Map
  • edu.umd.cloud9.webgraph.TrecExtractLinks$Map
  • hudson.plugins.rubyMetrics.rcov.RcovParser
  • hudson.plugins.rubyMetrics.saikuro.SaikuroParser
  • modelcrawler.Page
  • net.sf.regain.crawler.preparator.HtmlPreparator
    • 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.