в 17:44, 31 мая 2010

2010-05-31T17:44:27Z

Admin: 1 версия

2010-05-31T15:31:23Z

1 версия

Новая страница

== 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>



<pre class=codeResult>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</pre>

== 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>



<pre class=codeResult>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</pre>

== HTML Tag Constants ==

<OL><LI>A</LI><LI>DIR</LI><LI>IMG</LI><LI>SCRIPT</LI><LI>ADDRESS</LI><LI>DIV</LI><LI>IMPLIED</LI><LI>SELECT</LI><LI>APPLET</LI><LI>DL</LI><LI>INPUT</LI><LI>SMALL</LI><LI>AREA</LI><LI>DT</LI><LI>ISINDEX</LI><LI>SPAN</LI><LI>B</LI><LI>EM</LI><LI>KBD</LI><LI>STRIKE</LI><LI>BASE</LI><LI>FONT</LI><LI>LI</LI><LI>STRONG</LI><LI>BASEFONT</LI><LI>FORM</LI><LI>LINK</LI><LI>STYLE</LI><LI>BIG</LI><LI>FRAME</LI><LI>MAP</LI><LI>SUB</LI><LI>BLOCKQUOTE</LI><LI>FRAMESET</LI><LI>MENU</LI><LI>SUP</LI><LI>BODY</LI><LI>H1</LI><LI>META</LI><LI>TABLE</LI><LI>BR</LI><LI>H2</LI><LI>NOFRAMES</LI><LI>TD</LI><LI>CAPTION</LI><LI>H3</LI><LI>OBJECT</LI><LI>TEXTAREA</LI><LI>CENTER</LI><LI>H4</LI><LI>OL</LI><LI>TH</LI><LI>CITE</LI><LI>H5</LI><LI>OPTION</LI><LI>TITLE</LI><LI>CODE</LI><LI>H6</LI><LI>P</LI><LI>TR</LI><LI>COMMENT</LI><LI>HEAD</LI><LI>PARAM</LI><LI>TT</LI><LI>CONTENT</LI><LI>HR</LI><LI>PRE</LI><LI>U</LI><LI>DD</LI><LI>HTML</LI><LI>S</LI><LI>UL</LI><LI>DFN</LI><LI>I</LI><LI>SAMP</LI><LI>VAR</LI></OL>

== 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>



<pre class=codeResult>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</pre>

== 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>

← Предыдущая	Версия 17:44, 31 мая 2010
(нет различий)

Java Tutorial/Swing/HTML Document - История изменений

в 17:44, 31 мая 2010

Admin: 1 версия