Is there a good way to remove HTML from a Java string? A simple regex like
replaceAll("\\\\<.*?>", &quo
Here's a lightly more fleshed out update to try to handle some formatting for breaks and lists. I used Amaya's output as a guide.
import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;
import java.util.Stack;
import java.util.logging.Logger;
import javax.swing.text.MutableAttributeSet;
import javax.swing.text.html.HTML;
import javax.swing.text.html.HTMLEditorKit;
import javax.swing.text.html.parser.ParserDelegator;
public class HTML2Text extends HTMLEditorKit.ParserCallback {
private static final Logger log = Logger
.getLogger(Logger.GLOBAL_LOGGER_NAME);
private StringBuffer stringBuffer;
private Stack indentStack;
public static class IndexType {
public String type;
public int counter; // used for ordered lists
public IndexType(String type) {
this.type = type;
counter = 0;
}
}
public HTML2Text() {
stringBuffer = new StringBuffer();
indentStack = new Stack();
}
public static String convert(String html) {
HTML2Text parser = new HTML2Text();
Reader in = new StringReader(html);
try {
// the HTML to convert
parser.parse(in);
} catch (Exception e) {
log.severe(e.getMessage());
} finally {
try {
in.close();
} catch (IOException ioe) {
// this should never happen
}
}
return parser.getText();
}
public void parse(Reader in) throws IOException {
ParserDelegator delegator = new ParserDelegator();
// the third parameter is TRUE to ignore charset directive
delegator.parse(in, this, Boolean.TRUE);
}
public void handleStartTag(HTML.Tag t, MutableAttributeSet a, int pos) {
log.info("StartTag:" + t.toString());
if (t.toString().equals("p")) {
if (stringBuffer.length() > 0
&& !stringBuffer.substring(stringBuffer.length() - 1)
.equals("\n")) {
newLine();
}
newLine();
} else if (t.toString().equals("ol")) {
indentStack.push(new IndexType("ol"));
newLine();
} else if (t.toString().equals("ul")) {
indentStack.push(new IndexType("ul"));
newLine();
} else if (t.toString().equals("li")) {
IndexType parent = indentStack.peek();
if (parent.type.equals("ol")) {
String numberString = "" + (++parent.counter) + ".";
stringBuffer.append(numberString);
for (int i = 0; i < (4 - numberString.length()); i++) {
stringBuffer.append(" ");
}
} else {
stringBuffer.append("* ");
}
indentStack.push(new IndexType("li"));
} else if (t.toString().equals("dl")) {
newLine();
} else if (t.toString().equals("dt")) {
newLine();
} else if (t.toString().equals("dd")) {
indentStack.push(new IndexType("dd"));
newLine();
}
}
private void newLine() {
stringBuffer.append("\n");
for (int i = 0; i < indentStack.size(); i++) {
stringBuffer.append(" ");
}
}
public void handleEndTag(HTML.Tag t, int pos) {
log.info("EndTag:" + t.toString());
if (t.toString().equals("p")) {
newLine();
} else if (t.toString().equals("ol")) {
indentStack.pop();
;
newLine();
} else if (t.toString().equals("ul")) {
indentStack.pop();
;
newLine();
} else if (t.toString().equals("li")) {
indentStack.pop();
;
newLine();
} else if (t.toString().equals("dd")) {
indentStack.pop();
;
}
}
public void handleSimpleTag(HTML.Tag t, MutableAttributeSet a, int pos) {
log.info("SimpleTag:" + t.toString());
if (t.toString().equals("br")) {
newLine();
}
}
public void handleText(char[] text, int pos) {
log.info("Text:" + new String(text));
stringBuffer.append(text);
}
public String getText() {
return stringBuffer.toString();
}
public static void main(String args[]) {
String html = "paragraph at start
hello
What is happening?this is a
mutiline paragraph
- This
- is
- an
- ordered
- list
with
- another
- list
- This
- is
- sdasd
- sdasda
- asda
aasdas
- sdada
- fsdfsdfsd
- vbcvcvbcvb
- cvbcvbc
- vbcbcvbcvb
- cvbcv
- cool
stuff
- cool
";
System.out.println(convert(html));
}
}