Package org.exoplatform.services.html

Examples of org.exoplatform.services.html.HTMLDocument

46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
      System.out.println("FILE PATH: " + this.file_.getCanonicalPath());
   }

   public void testCharsetWithFile() throws Exception
   {
      HTMLDocument document = HTMLParser.createDocument(this.file_, null);
      assertNotNull(document);
      assertEquals("ASCII", HTMLParser.getCharset());
      assertNotSame("UTF-8", HTMLParser.getCharset());
      System.out.println("CHARSET: " + HTMLParser.getCharset());

      System.out.println("DOCUMENT-TEXTVALUE: " + document.getTextValue());
      System.out.println("DOCUMENT-ROOT: " + document.getRoot().getName().toString());
      System.out.println("CLASS: " + document.getClass().getName() + "\n");

      System.out.println("DOCUMENT-DOCTYPE-TEXTVALUE: " + document.getDoctype().getTextValue());
      System.out.println("DOCUMENT-DOCTYPE-VALUE: " + new String(document.getDoctype().getValue()));
      System.out.println("DOCUMENT-DOCTYPE-NAME: " + document.getDoctype().getName().toString());
   }
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
      System.out.println("DOCUMENT-DOCTYPE-NAME: " + document.getDoctype().getName().toString());
   }

   public void testCharsetWithURL() throws Exception
   {
      HTMLDocument document;
      try
      {
         URL url_ = new URL("http://www.24h.com.vn");
         document = HTMLParser.createDocument(url_.openConnection().getInputStream(), null);
         document = HTMLParser.createDocument(url_.openStream(), null);
      }
      catch (java.net.UnknownHostException e)
      {
         return;
      }
      catch (java.net.ConnectException e)
      {
         return;
      }

      assertNotNull(document);
      assertNotNull(document.getRoot());
   }
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
99
100
101
   public void testCharsetWithTEXT() throws Exception
   {
      String text =
         "<html>" + "<head>" + "</head>" + "<body>" + "<h1>This is a HTML file for testing!</h1>" + "</body>"
            + "</html>";
      HTMLDocument document = HTMLParser.createDocument(text);
      assertNotNull(document);
      NodePath path = NodePathParser.toPath("html.body.h1");
      HTMLNode node = NodePathUtil.lookFor(document.getRoot(), path);
      assertNotNull(node);
      assertEquals(node.getName(), Name.H1);
      assertEquals(node.getName().toString(), "H1");
      System.out.println("NAME: " + node.getName());
      System.out.println("VALUE: " + new String(node.getValue()));
View Full Code Here
153
154
155
156
157
158
159
160
161
162
163
164
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
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
            + "<td>Cell 1</td><td>Cell 2</td>" + "<td>cell 3</td><td>Cell 4 </td>" + "</tr>" + "<tr>" + "<td>"
            + "<a href=\"/homepage.html\">HomePage</a>" + "</td>" + "<td>" + "<a href=\"/sitemap.html\">SiteMap</a>"
            + "</td>" + "</tr>" + "</tbody>" + "</table>" + "<!--This is a comment! -->"
            + "<img src=\"/images/home.gif\" alt=\"short desc\" usemap=\"#homePage.htm\" />" + "</body>" + "</html>";

      HTMLDocument document = HTMLParser.createDocument(text);
      assertNotNull(document);
      assertEquals(5, document.getRoot().getChildrenNode().get(1).getChildrenNode().size());
      //Note-Begin.
      assertEquals(document.getRoot().getChildrenNode().get(1).getChildren().size(), document.getRoot()
         .getChildrenNode().get(1).getChildrenNode().size());
      //Note-End.
      System.out.println("\n CHECK DOCUMENT:");
      for (HTMLNode child : document.getRoot().getChildrenNode().get(1).getChildrenNode())
      {
         System.out.println(child.getName().toString() + " : " + new String(child.getValue()));
      }

      HyperLinkUtil hyperlinkUtil = new HyperLinkUtil();
      List<String> linkList = new ArrayList<String>();

      //SiteLink---------------------------------------------------------------------------------
      linkList = hyperlinkUtil.getSiteLink(document.getRoot());
      assertEquals(3, linkList.size());
      assertEquals("http://www.exoplatform.com", linkList.get(0).toString());

      System.out.println("\nSHOW ALL HYPERLINKs: ");
      for (int i = 0; i < linkList.size(); i++)
      {
         System.out.println(linkList.get(i).toString());
      }

      HTMLNode tableNode = NodePathUtil.lookFor(document.getRoot(), NodePathParser.toPath("html.body.table"));
      linkList.clear();
      linkList = hyperlinkUtil.getSiteLink(tableNode);
      assertEquals(2, linkList.size());
      assertEquals("/homepage.html", linkList.get(0).toString());

      //ImageLink--------------------------------------------------------------------------------
      String imageLink = hyperlinkUtil.getSingleImageLink(document.getRoot());
      assertEquals("/images/home.gif", imageLink);
      System.out.println("\nIMAGE-LINK: " + imageLink);

      //CreateFullNormalLink.---------------------------------------------------------------------   
      HTMLNode bodyNode = document.getRoot().getChildrenNode().get(1);
      assertEquals(bodyNode.getName(), Name.BODY);
      /*
      URL url_ = new URL("http://www.exoplatform.com");   
      assertNotNull(url_);   
      hyperlinkUtil.createFullNormalLink(bodyNode, url_);
      */
      linkList.clear();
      linkList = hyperlinkUtil.getSiteLink(document.getRoot());
      System.out.println("\nSHOW ALL HYPERLINKs: ");
      for (int i = 0; i < linkList.size(); i++)
      {
         System.out.println(linkList.get(i).toString());
      }
      HTMLNode row2Node = tableNode.getChildren().get(0).getChildrenNode().get(1);
      assertNotNull(row2Node);
      assertEquals(row2Node.getName(), Name.TR);
      assertEquals("tr", new String(row2Node.getValue()));
      //System.out.println("ROW2: " + row2Node.getTextValue());
      HTMLNode row2Cell2 = row2Node.getChildrenNode().get(1);

      assertNotNull(new URL("http://www.mysite.net"));
      URLCreator urlCreator = new URLCreator();
      hyperlinkUtil.createFullNormalLink(row2Cell2, new URL("http://www.mysite.net"), urlCreator);
      linkList.clear();
      linkList = hyperlinkUtil.getSiteLink(document.getRoot());
      System.out.println("\nSHOW ALL HYPERLINKs: ");
      for (int i = 0; i < linkList.size(); i++)
      {
         System.out.println(linkList.get(i).toString());
      }

      //CreateFullImageLink.-----------------------------------------------------------------------
      hyperlinkUtil.createFullImageLink(document.getRoot(), new URL("http://www.myImageLink.net"));
      System.out.println("\nNEW IMAGE_LINK1:" + hyperlinkUtil.getSingleImageLink(document.getRoot()));
      hyperlinkUtil.createFullImageLink(document.getRoot(), new URL("http://www.exo.com"), new URLCreator());
      System.out.println("\nNEW IMAGE_LINK2:" + hyperlinkUtil.getSingleImageLink(document.getRoot()));
   }
View Full Code Here
70
71
72
73
74
75
76
77
78
      {
         HTMLNode element = lookFor(root, path);
         if (element != null)
            html.addChild(element);
      }
      HTMLDocument document = new HTMLDocument();
      document.setRoot(html);
      return document;
   }
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
      return newNode;
   }

   public static synchronized HTMLDocument createDocument(char[] data) throws Exception
   {
      HTMLDocument document = new HTMLDocument();
      CharsToken tokens = new CharsToken();
      tokens.setDocument(document);
      ParserService.getTokenParser().createBeans(tokens, data);
      ParserService.parse(tokens, document);
      return document;
View Full Code Here
TOP

Related Classes of org.exoplatform.services.html.HTMLDocument

  • org.exoplatform.services.html.parser.HTMLParser
  • org.exoplatform.services.html.path.NodePathUtil
  • org.exoplatform.services.parser.html.test.TestExceptionParser
  • org.exoplatform.services.parser.html.test.TestFileDetect
  • org.exoplatform.services.parser.html.test.TestHTMLParser
  • org.exoplatform.services.parser.html.test.TestNodeParser
  • org.exoplatform.services.parser.html.test.TestURL
  • org.exoplatform.test.crawler.CrawlerService
  • org.exoplatform.test.crawler.SingleCrawlThread
    • 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.