import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Example {
public static void main(String[] args) {
final String regex = "(?i)\\s((?:https?:\\/\\/|www\\d{0,3}[.]|[a-z0-9.\\-]+[.][a-z]{2,4}\\/)(?:[^\\s()<>]+|\\(([^\\s()<>]+|(\\([^\\s()<>]+\\)))*\\))+(?:\\(([^\\s()<>]+|(\\([^\\s()<>]+\\)))*\\)|[^\\s`!()\\[\\]\\{\\};:'\\\".,<>?«»“”‘’]))";
final String string = "<a href=\"https://example.com/page.php?goto=200\">https://example.com/page.php?goto=200</a>The problem occurs when I have almost identical links. For example: https://example.com/page.php?goto=200 and https://example.com/page.php\n"
+ "<a href=\"https://example.com/page.php?goto=200\">https://example.com/page.php?goto=200</a>";
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