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

extends HTMLEditorKit

     
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.util.Enumeration;
import javax.swing.text.AttributeSet;
import javax.swing.text.MutableAttributeSet;
import javax.swing.text.html.HTML;
import javax.swing.text.html.HTMLEditorKit;
public class Main {
  public static void main(String[] args) throws Exception {
    ParserGetter kit = new ParserGetter();
    HTMLEditorKit.Parser parser = kit.getParser();
    HTMLEditorKit.ParserCallback callback = new ReportAttributes();
    URL u = new URL("http://www.jexp.ru");
    InputStream in = u.openStream();
    InputStreamReader r = new InputStreamReader(in);
    parser.parse(r, callback, false);
  }
}
class ReportAttributes extends HTMLEditorKit.ParserCallback {
  public void handleStartTag(HTML.Tag tag, MutableAttributeSet attributes, int position) {
    this.listAttributes(attributes);
  }
  private void listAttributes(AttributeSet attributes) {
    Enumeration e = attributes.getAttributeNames();
    while (e.hasMoreElements()) {
      Object name = e.nextElement();
      Object value = attributes.getAttribute(name);
      if (!attributes.containsAttribute(name.toString(), value)) {
        System.out.println("containsAttribute() fails");
      }
      if (!attributes.isDefined(name.toString())) {
        System.out.println("isDefined() fails");
      }
      System.out.println(name + "=" + value);
    }
  }
  public void handleSimpleTag(HTML.Tag tag, MutableAttributeSet attributes, int position) {
    this.listAttributes(attributes);
  }
}
class ParserGetter extends HTMLEditorKit {
  public HTMLEditorKit.Parser getParser() {
    return super.getParser();
  }
}

extends HTMLEditorKit.ParserCallback

     
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.util.Enumeration;
import javax.swing.text.AttributeSet;
import javax.swing.text.MutableAttributeSet;
import javax.swing.text.html.HTML;
import javax.swing.text.html.HTMLEditorKit;
public class Main {
  public static void main(String[] args) throws Exception {
    ParserGetter kit = new ParserGetter();
    HTMLEditorKit.Parser parser = kit.getParser();
    HTMLEditorKit.ParserCallback callback = new ReportAttributes();
    URL u = new URL("http://www.jexp.ru");
    InputStream in = u.openStream();
    InputStreamReader r = new InputStreamReader(in);
    parser.parse(r, callback, false);
  }
}
class ReportAttributes extends HTMLEditorKit.ParserCallback {
  public void handleStartTag(HTML.Tag tag, MutableAttributeSet attributes, int position) {
    this.listAttributes(attributes);
  }
  private void listAttributes(AttributeSet attributes) {
    Enumeration e = attributes.getAttributeNames();
    while (e.hasMoreElements()) {
      Object name = e.nextElement();
      Object value = attributes.getAttribute(name);
      if (!attributes.containsAttribute(name.toString(), value)) {
        System.out.println("containsAttribute() fails");
      }
      if (!attributes.isDefined(name.toString())) {
        System.out.println("isDefined() fails");
      }
      System.out.println(name + "=" + value);
    }
  }
  public void handleSimpleTag(HTML.Tag tag, MutableAttributeSet attributes, int position) {
    this.listAttributes(attributes);
  }
}
class ParserGetter extends HTMLEditorKit {
  public HTMLEditorKit.Parser getParser() {
    return super.getParser();
  }
}

HTMLEditorKit: createDefaultDocument()

 
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());
      }
    }
  }
}

HTMLEditorKit.Parser: parse(Reader r, ParserCallback cb, boolean i)

 
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());
      }
    }
  }
}

new HTMLEditorKit()

 
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());
      }
    }
  }
}