Java Tutorial/Swing/HTML Document

ElementIterator Class

   <source lang="java">

import java.io.BufferedReader; import java.io.InputStream; import java.io.InputStreamReader; import java.net.URL; import java.net.URLConnection; import javax.swing.text.AttributeSet; import javax.swing.text.html.HTML; import javax.swing.text.html.HTMLDocument; import javax.swing.text.html.HTMLEditorKit; import javax.swing.text.html.parser.ParserDelegator; public class MainClass {

 public static void main(String args[]) throws Exception {
   URL url = new URL("http://www.google.ru");
   URLConnection connection = url.openConnection();
   InputStream is = connection.getInputStream();
   InputStreamReader isr = new InputStreamReader(is);
   BufferedReader br = new BufferedReader(isr);
   HTMLEditorKit htmlKit = new HTMLEditorKit();
   HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
   HTMLEditorKit.Parser parser = new ParserDelegator();
   HTMLEditorKit.ParserCallback callback = htmlDoc.getReader(0);
   parser.parse(br, callback, true);
   for (HTMLDocument.Iterator iterator = htmlDoc.getIterator(HTML.Tag.A); iterator.isValid(); iterator
       .next()) {
     AttributeSet attributes = iterator.getAttributes();
     String srcString = (String) attributes.getAttribute(HTML.Attribute.HREF);
     System.out.print(srcString);
     int startOffset = iterator.getStartOffset();
     int endOffset = iterator.getEndOffset();
     int length = endOffset - startOffset;
     String text = htmlDoc.getText(startOffset, length);
     System.out.println(" � " + text);
   }
 }

}</source>

url?sa=p&pref=ig&pval=3&q=http://www.google.ca/ig%3Fhl%3Den&usg=__o-KrRDBI3nbRElKzYEMqfOl3_t0= � Personalize this page
https://www.google.ru/accounts/Login?continue=http://www.google.ca/&hl=en � Sign in
  http://images.google.ca/imghp?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=wi � Images
  http://groups.google.ca/grphp?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=wg � Groups
  http://news.google.ca/nwshp?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=wn � News
  /maps?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=wl � Maps
  http://scholar.google.ru/schhp?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=ws � Scholar
  /intl/en/options/ � more��
  /advanced_search?hl=en � Advanced Search
  /preferences?hl=en � Preferences
  /language_tools?hl=en � Language Tools

Finding out interested element

   <source lang="java">

import java.io.BufferedReader; import java.io.InputStream; import java.io.InputStreamReader; import java.net.URL; import java.net.URLConnection; import javax.swing.text.AttributeSet; import javax.swing.text.html.HTML; import javax.swing.text.html.HTMLDocument; import javax.swing.text.html.HTMLEditorKit; import javax.swing.text.html.parser.ParserDelegator; public class MainClass {

 public static void main(String args[]) throws Exception {
   URL url = new URL("http://www.google.ru");
   URLConnection connection = url.openConnection();
   InputStream is = connection.getInputStream();
   InputStreamReader isr = new InputStreamReader(is);
   BufferedReader br = new BufferedReader(isr);
   HTMLEditorKit htmlKit = new HTMLEditorKit();
   HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
   HTMLEditorKit.Parser parser = new ParserDelegator();
   HTMLEditorKit.ParserCallback callback = htmlDoc.getReader(0);
   parser.parse(br, callback, true);
   for (HTMLDocument.Iterator iterator = htmlDoc.getIterator(HTML.Tag.A); iterator.isValid(); iterator
       .next()) {
     AttributeSet attributes = iterator.getAttributes();
     String srcString = (String) attributes.getAttribute(HTML.Attribute.HREF);
     System.out.print(srcString);
     int startOffset = iterator.getStartOffset();
     int endOffset = iterator.getEndOffset();
     int length = endOffset - startOffset;
     String text = htmlDoc.getText(startOffset, length);
     System.out.println(" � " + text);
   }
 }

}</source>

url?sa=p&pref=ig&pval=3&q=http://www.google.ca/ig%3Fhl%3Den&usg=__o-KrRDBI3nbRElKzYEMqfOl3_t0= � Personalize this page
https://www.google.ru/accounts/Login?continue=http://www.google.ca/&hl=en � Sign in
  http://images.google.ca/imghp?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=wi � Images
  http://groups.google.ca/grphp?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=wg � Groups
  http://news.google.ca/nwshp?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=wn � News
  /maps?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=wl � Maps
  http://scholar.google.ru/schhp?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=ws � Scholar
  /intl/en/options/ � more��
  /advanced_search?hl=en � Advanced Search
  /preferences?hl=en � Preferences
  /language_tools?hl=en � Language Tools

HTML Tag Constants

1. A
2. DIR
3. IMG
4. SCRIPT
5. ADDRESS
6. DIV
7. IMPLIED
8. SELECT
9. APPLET
10. DL
11. INPUT
12. SMALL
13. AREA
14. DT
15. ISINDEX
16. SPAN
17. B
18. EM
19. KBD
20. STRIKE
21. BASE
22. FONT
23. LI
24. STRONG
25. BASEFONT
26. FORM
27. LINK
28. STYLE
29. BIG
30. FRAME
31. MAP
32. SUB
33. BLOCKQUOTE
34. FRAMESET
35. MENU
36. SUP
37. BODY
38. H1
39. META
40. TABLE
41. BR
42. H2
43. NOFRAMES
44. TD
45. CAPTION
46. H3
47. OBJECT
48. TEXTAREA
49. CENTER
50. H4
51. OL
52. TH
53. CITE
54. H5
55. OPTION
56. TITLE
57. CODE
58. H6
59. P
60. TR
61. COMMENT
62. HEAD
63. PARAM
64. TT
65. CONTENT
66. HR
67. PRE
68. U
69. DD
70. HTML
71. S
72. UL
73. DFN
74. I
75. SAMP
76. VAR

HyperlinkListener Example

   <source lang="java">

import java.io.IOException; import java.net.URL; import javax.swing.JEditorPane; import javax.swing.JFrame; import javax.swing.JScrollPane; import javax.swing.event.HyperlinkEvent; import javax.swing.event.HyperlinkListener; import javax.swing.text.Document; class ActivatedHyperlinkListener implements HyperlinkListener {

 JEditorPane editorPane;
 public ActivatedHyperlinkListener(JEditorPane editorPane) {
   this.editorPane = editorPane;
 }
 public void hyperlinkUpdate(HyperlinkEvent hyperlinkEvent) {
   HyperlinkEvent.EventType type = hyperlinkEvent.getEventType();
   final URL url = hyperlinkEvent.getURL();
   if (type == HyperlinkEvent.EventType.ENTERED) {
     System.out.println("URL: " + url);
   } else if (type == HyperlinkEvent.EventType.ACTIVATED) {
     System.out.println("Activated");
     Document doc = editorPane.getDocument();
     try {
       editorPane.setPage(url);
     } catch (IOException ioException) {
       System.out.println("Error following link, Invalid link");
       editorPane.setDocument(doc);
     }
   }
 }

} public class EditorPaneSample {

 public static void main(String args[]) {
   JFrame frame = new JFrame("EditorPane Example");
   frame.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);
   try {
     JEditorPane editorPane = new JEditorPane("http://www.google.ru");
     editorPane.setEditable(false);
     HyperlinkListener hyperlinkListener = new ActivatedHyperlinkListener(editorPane);
     editorPane.addHyperlinkListener(hyperlinkListener);
     JScrollPane scrollPane = new JScrollPane(editorPane);
     frame.add(scrollPane);
   } catch (IOException e) {
     System.err.println("Unable to load: " + e);
   }
   frame.setSize(640, 480);
   frame.setVisible(true);
 }

}</source>

Iterating Across HTML Documents for Links

   <source lang="java">

import java.io.BufferedReader; import java.io.InputStream; import java.io.InputStreamReader; import java.net.URL; import java.net.URLConnection; import javax.swing.text.AttributeSet; import javax.swing.text.html.HTML; import javax.swing.text.html.HTMLDocument; import javax.swing.text.html.HTMLEditorKit; import javax.swing.text.html.parser.ParserDelegator; public class MainClass {

 public static void main(String args[]) throws Exception {
   URL url = new URL("http://www.google.ru");
   URLConnection connection = url.openConnection();
   InputStream is = connection.getInputStream();
   InputStreamReader isr = new InputStreamReader(is);
   BufferedReader br = new BufferedReader(isr);
   HTMLEditorKit htmlKit = new HTMLEditorKit();
   HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
   HTMLEditorKit.Parser parser = new ParserDelegator();
   HTMLEditorKit.ParserCallback callback = htmlDoc.getReader(0);
   parser.parse(br, callback, true);
   for (HTMLDocument.Iterator iterator = htmlDoc.getIterator(HTML.Tag.A); iterator.isValid(); iterator
       .next()) {
     AttributeSet attributes = iterator.getAttributes();
     String srcString = (String) attributes.getAttribute(HTML.Attribute.HREF);
     System.out.print(srcString);
     int startOffset = iterator.getStartOffset();
     int endOffset = iterator.getEndOffset();
     int length = endOffset - startOffset;
     String text = htmlDoc.getText(startOffset, length);
     System.out.println(" - " + text);
   }
 }

}</source>

url?sa=p&pref=ig&pval=3&q=http://www.google.ca/ig%3Fhl%3Den&usg=__o-KrRDBI3nbRElKzYEMqfOl3_t0= � Personalize this page
https://www.google.ru/accounts/Login?continue=http://www.google.ca/&hl=en � Sign in
  http://images.google.ca/imghp?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=wi � Images
  http://groups.google.ca/grphp?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=wg � Groups
  http://news.google.ca/nwshp?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=wn � News
  /maps?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=wl � Maps
  http://scholar.google.ru/schhp?ie=ISO-8859-1&oe=ISO-8859-1&hl=en&tab=ws � Scholar
  /intl/en/options/ � more��
  /advanced_search?hl=en � Advanced Search
  /preferences?hl=en � Preferences
  /language_tools?hl=en � Language Tools

Look for specific tag types, such as HTML.Tag.H1, HTML.Tag.H2

   <source lang="java">

import java.io.BufferedReader; import java.io.InputStream; import java.io.InputStreamReader; import java.net.URL; import java.net.URLConnection; import javax.swing.text.AttributeSet; import javax.swing.text.Element; import javax.swing.text.ElementIterator; import javax.swing.text.StyleConstants; import javax.swing.text.html.HTML; import javax.swing.text.html.HTMLDocument; import javax.swing.text.html.HTMLEditorKit; import javax.swing.text.html.parser.ParserDelegator; public class MainClass {

 public static void main(String args[]) throws Exception {
   URL url = new URL("http://www.google.ru");
   URLConnection connection = url.openConnection();
   InputStream is = connection.getInputStream();
   InputStreamReader isr = new InputStreamReader(is);
   BufferedReader br = new BufferedReader(isr);
   HTMLEditorKit htmlKit = new HTMLEditorKit();
   HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
   HTMLEditorKit.Parser parser = new ParserDelegator();
   HTMLEditorKit.ParserCallback callback = htmlDoc.getReader(0);
   parser.parse(br, callback, true);
   Element element;
   ElementIterator iterator = new ElementIterator(htmlDoc);
   while ((element = iterator.next()) != null) {
     AttributeSet attributes = element.getAttributes();
     Object name = attributes.getAttribute(StyleConstants.NameAttribute);
   
     if ((name instanceof HTML.Tag)
         && (name == HTML.Tag.H1 || name == HTML.Tag.H2 || name == HTML.Tag.P )) {
       // Build up content text as it may be within multiple elements
       int count = element.getElementCount();
       for (int i = 0; i < count; i++) {
         Element child = element.getElement(i);
         AttributeSet childAttributes = child.getAttributes();
         if (childAttributes.getAttribute(StyleConstants.NameAttribute) == HTML.Tag.CONTENT) {
           int startOffset = child.getStartOffset();
           int endOffset = child.getEndOffset();
           int length = endOffset - startOffset;
           System.out.println(htmlDoc.getText(startOffset, length));
         }
       }
     }
   }
 }

}</source>