import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Example {
public static void main(String[] args) {
final String regex = "(?i)(?(DEFINE)(?<proto>(?:https?:)?\\/\\/)(?<port>:[0-9]{2,5})(?<tld>(?:a(?:[cd]|e(?:ro)?|[fgil-oqr]|s(?:ia)?|[tuwxz])|b(?:[abd-h]|iz?|[jl-oq-tvwyz])|c(?:at?|[cdf-ik-n]|o(?:m|op)?|[ru-z])|d[ejkmoz]|e[ceghr-u]|f[i-kmor]|g[abd-il-np-uwy]|h[kmnrtu]|i(?:[delm]|n(?:fo|t)?|[oq-t])|j(?:[em]|o(?:bs)?|p)|k[eg-imnprwyz]|l[a-cikr-vy]|m(?:[ac-hk]|lc?|[mn]|o(?:bi)?|[p-t]|u(?:seum)?|[v-z])|n(?:a(?:me)?|c|et?|[fgilopruz])|o(?:m|rg)|p(?:[ae-hk-n]|ost|ro?|[stwy])|qa|r[eosuw]|s(?:[a-eg-or]|t(?:udio)?|[uvx-z])|t(?:[cd]|el|[f-hj-p]|r(?:avel)?|[tvwz])|u[agkmsyz]|v[aceginu]|w[fs]|y[et]|z[amw]))(?<path>(\\/(?:[a-z0-9+%-]\\.?)+)*\\/?)(?<query>\\?[a-z+&$_.-][a-z0-9;:@&%=+\\/.-]*)(?<hash>\\#[a-z_.-][a-z0-9+$%_.-]*)(?<subdomain>[a-z0-9\\-\\.]+\\.)(?<yt_domain>(?:www\\.)?(?:youtube\\.com|youtu\\.be)\\/)(?<yt_hash>(?:[\\w-]{10,12})+)(?<yt_video>(?&proto)?(?&yt_domain)+(?:watch)?(?:\\/embed\\/|\\?v=)+(?&yt_hash)+))((?&yt_video).*(*SKIP)(*FAIL)|(?&proto)?(?&subdomain)(?&tld)(?&port)?(?&path)?(?&query)?(?&hash)?)";
final String string = "Lines which should be partially or fully matched:\n\n\n"
+ "http:www.google.com/\n"
+ " http//www.google.com/\n"
+ "http://www.google.com/\n"
+ " ://www.google.com/\n"
+ " www.google.com/\n"
+ " www.google.com:8000\n"
+ " www.google.com/?key=value\n"
+ " github.io\n"
+ " www.google.com/abc/def/ijk#123\n"
+ " www.google.com/abc/def/ijk?v=123123123\n"
+ " www.google.com/abc/def/watch?v=1231231231\n"
+ "https://www.youtube.com/channel/UCgeu2xe0XRscaKyvBt3WgmQ\n"
+ "http://www.google.com/?key=value\n"
+ "http://www.youtube.com/ \n\n"
+ "However, it should skip (do not match lines) which contain youtube video ID):\n\n\n"
+ "http://www.youtube.com/watch?v=B5Gj78s6H7w&feature=youtu.be\n"
+ "https://www.youtube.com/embed/y19EaW2X7ac\n"
+ " music.youtube.com/embed/y19EaW2X7ac\n"
+ "https://www.youtube.com/watch?v=B5Gj78s6H7w&feature=youtu.be\n"
+ "https://www.youtube.com/watch?feature=youtu.be&v=B5Gj78s6H7w\n"
+ "https://www.youtu.be/B5Gj78s6H7w&feature=youtu.be\n"
+ "https://www.youtu.be/B5Gj78s6H7w\n";
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