Java by API/javax.swing.text.html/HTML

Материал из Java эксперт
Перейти к: навигация, поиск

HTML.Attribute.HREF

   <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.jexp.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>



HTML: getAllAttributeKeys()

   <source lang="java">

import javax.swing.text.html.HTML; public class Main { 

 public static void main(String[] args) {
   HTML.Tag[] tags = HTML.getAllTags();
   HTML.Attribute[] attrs = HTML.getAllAttributeKeys();
   System.out.println("HTML Tags:");
   for (int i = 0; i < tags.length - 1; i++) {
     System.out.print(tags[i] + ", ");
     if ((i % 8) == 7) {
       System.out.println("");
     }
   }
   System.out.println(tags[tags.length - 1]);
   System.out.println("\n\nHTML Attributes:");
   for (int i = 0; i < attrs.length - 1; i++) {
     System.out.print(attrs[i] + ", ");
     if ((i % 8) == 7) {
       System.out.println("");
     }
   }
   System.out.println(attrs[attrs.length - 1]);
 }

} 


 </source>



HTML.Tag

   <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.jexp.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);
   ElementIterator iterator = new ElementIterator(htmlDoc);
   Element element;
   while ((element = iterator.next()) != null) {
     AttributeSet attributes = element.getAttributes();
     Object name = attributes.getAttribute(StyleConstants.NameAttribute);
     if ((name instanceof HTML.Tag) && (name == HTML.Tag.H1)) {
       StringBuffer text = new StringBuffer();
       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;
           text.append(htmlDoc.getText(startOffset, length));
         }
       }
       System.out.println(name + ": " + text.toString());
     }
   }
 }

} 


 </source>



HTML.Tag.A

   <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.jexp.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>



HTML.Tag.CONTENT

   <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.jexp.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);
   ElementIterator iterator = new ElementIterator(htmlDoc);
   Element element;
   while ((element = iterator.next()) != null) {
     AttributeSet attributes = element.getAttributes();
     Object name = attributes.getAttribute(StyleConstants.NameAttribute);
     if ((name instanceof HTML.Tag) && (name == HTML.Tag.H1)) {
       StringBuffer text = new StringBuffer();
       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;
           text.append(htmlDoc.getText(startOffset, length));
         }
       }
       System.out.println(name + ": " + text.toString());
     }
   }
 }

} 


 </source>



HTML: Tag[] getAllTags()

   <source lang="java">

import javax.swing.text.html.HTML; public class Main { 

 public static void main(String[] args) {
   HTML.Tag[] list = HTML.getAllTags();
   for (int i = 0; i < list.length; i++) {
     System.out.println((i + 1) + ": " + list[i]);
   }
 }

} /*1: a 2: address 3: applet 4: area 5: b 6: base 7: basefont 8: big 9: blockquote 10: body 11: br 12: caption 13: center 14: cite 15: code 16: dd 17: dfn 18: dir 19: div 20: dl 21: dt 22: em 23: font 24: form 25: frame 26: frameset 27: h1 28: h2 29: h3 30: h4 31: h5 32: h6 33: head 34: hr 35: html 36: i 37: img 38: input 39: isindex 40: kbd 41: li 42: link 43: map 44: menu 45: meta 46: nobr 47: noframes 48: object 49: ol 50: option 51: p 52: param 53: pre 54: samp 55: script 56: select 57: small 58: span 59: strike 60: s 61: strong 62: style 63: sub 64: sup 65: table 66: td 67: textarea 68: th 69: title 70: tr 71: tt 72: u 73: ul 74: var

  • /




 </source>



HTML.Tag.H1

   <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.jexp.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);
   ElementIterator iterator = new ElementIterator(htmlDoc);
   Element element;
   while ((element = iterator.next()) != null) {
     AttributeSet attributes = element.getAttributes();
     Object name = attributes.getAttribute(StyleConstants.NameAttribute);
     if ((name instanceof HTML.Tag) && (name == HTML.Tag.H1)) {
       StringBuffer text = new StringBuffer();
       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;
           text.append(htmlDoc.getText(startOffset, length));
         }
       }
       System.out.println(name + ": " + text.toString());
     }
   }
 }

} 


 </source>
Источник — «http://www.jexp.ru/index.php?title=Java_by_API/javax.swing.text.html/HTML&oldid=1933»