Last active
January 2, 2019 21:50
-
-
Save EliasRanz/ff40397864310338a17f916c8777d737 to your computer and use it in GitHub Desktop.
Link Utility that allows you to extract urls from a given text of string. Utilized by my Twitch moderator bot.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import java.util.ArrayList; | |
import java.util.List; | |
import java.util.regex.Matcher; | |
import java.util.regex.Pattern; | |
public class LinkUtil { | |
public static List<String> extractUrls(String text) { | |
List<String> containedUrls = new ArrayList<>(); | |
Pattern urlPattern = Pattern.compile( | |
"(?:(?:https?|ftp):\\/\\/)?(?:\\S+(?::\\S*)?@)?(?:(?!10(?:\\.\\d{1,3}){3})(?!127(?:\\.\\d{1,3}){3})(?!169\\.254(?:\\.\\d{1,3}){2})(?!192\\.168(?:\\.\\d{1,3}){2})(?!172\\.(?:1[6-9]|2\\d|3[0-1])(?:\\.\\d{1,3}){2})(?:[1-9]\\d?|1\\d\\d|2[01]\\d|22[0-3])(?:\\.(?:1?\\d{1,2}|2[0-4]\\d|25[0-5])){2}(?:\\.(?:[1-9]\\d?|1\\d\\d|2[0-4]\\d|25[0-4]))|(?:(?:[a-z\\x{00a1}-\\x{ffff}0-9]+-?)*[a-z\\x{00a1}-\\x{ffff}0-9]+)(?:\\.(?:[a-z\\x{00a1}-\\x{ffff}0-9]+-?)*[a-z\\x{00a1}-\\x{ffff}0-9]+)*(?:\\.(?:[a-z\\x{00a1}-\\x{ffff}]{2,})))(?::\\d{2,5})?(?:\\/[^\\s]*)?", | |
Pattern.CASE_INSENSITIVE | Pattern.MULTILINE | Pattern.DOTALL); | |
Matcher urlMatcher = urlPattern.matcher(text); | |
while (urlMatcher.find()) { | |
String url = text.substring(urlMatcher.start(0), urlMatcher.end()); | |
containedUrls.add(url); | |
} | |
return new ArrayList<>(new HashSet<>(containedUrls)); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Test cases: https://regex101.com/r/nvCTnh/2/
Regex courtesy of diegoperini's entry on https://mathiasbynens.be/demo/url-regex
Usage example:
The
new ArrayList<>(new HashSet<>(containedUrls))
will get rid of duplicate results, which should make parsing more efficient.