import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Example {
public static void main(String[] args) {
final String regex = "<?[^<>]*>|<[^>]*";
final String string = "Strip all HTML tags from a string. HTML tags are enclosed in < and >.\n\n"
+ "The regex will be applied on a line-by-line basis, meaning partial tags will need to be handled by the regex. Don't worry about opening or closing tags; we just want to get rid of them all.\n\n"
+ "Note: This task is meant to be a learning exercise, and not necessarily the best way to parse HTML";
final Pattern pattern = Pattern.compile(regex);
final Matcher matcher = pattern.matcher(string);
while (matcher.find()) {
System.out.println("Full match: " + matcher.group(0));
for (int i = 1; i <= matcher.groupCount(); i++) {
System.out.println("Group " + i + ": " + matcher.group(i));
}
}
}
}
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Java, please visit: https://docs.oracle.com/javase/7/docs/api/java/util/regex/Pattern.html