import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Example {
public static void main(String[] args) {
final String regex = "(?<=https?://)(?:\\w+\\.)+(?<domain>\\w+\\.\\w+)[/\\s$]";
final String string = "https://www.subdomain.example.com/folder/folder\n\n\n"
+ "valid.domains.below\n"
+ "schools.k12 \n"
+ "newTLD.clothing text thtat should not be matched \n"
+ "good.photography\n"
+ "x.a-b.com\n"
+ "x-y.a-b.net\n"
+ "x-y.a-b-c.co.uk\n"
+ "x.0ac.com\n"
+ "schools.k12\n"
+ "newTLD.clothing\n"
+ "good.photography\n"
+ "0-1-2.3-4.co\n"
+ "a-----b.com\n\n"
+ "hello he.llo-o.com/okayokay/\n\n"
+ "https://www.11737.se/hello/\n\n"
+ "http://www.11377.se/hello/\n\n"
+ "www.11773.se/hello/\n\n\n"
+ "invalid-.domains for fun\n"
+ "-domain.com\n"
+ "domain--.com\n"
+ "-domain-.-.com\n"
+ "domain.000\n"
+ ".domain.net\n"
+ "domain.net.\n"
+ "sub.-domain.com\n"
+ "sub.domain-.com\n"
+ "sub-.domain.com\n"
+ "-sub.domain.com\n\n";
final Pattern pattern = Pattern.compile(regex, Pattern.MULTILINE);
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