Hello EZ,
this code snippet checks a given URL for redirects. I.e. if there is someone providing a shortened link with services like TinyURL can check the real URL here without visiting the site.
import java.io.IOException;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.Scanner;
public class RedirectLocationScanner {
public static void main(final String[] args) throws IOException {
String urlStr = null;
if (!(args.length == 1)) {
Scanner scan = new Scanner(System.in);
System.out.println("URL?");
urlStr = scan.nextLine();
scan.close();
} else {
urlStr = args[0];
}
if(!urlStr.startsWith("http://")){
urlStr = "http://" + urlStr;
}
URL url = new URL(urlStr);
HttpURLConnection.setFollowRedirects(false);
String redirectLoc = url.openConnection().getHeaderField("Location");
if(redirectLoc == null){
System.out.println("No redirect.");
} else {
System.out.println("real URL: " + redirectLoc);
}
}
}
__________________________________________________________________
This code is an updated version, that also scans for target links in ad link services like adfly, adfoc and linkbucks.
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.net.URLConnection;
import java.util.Scanner;
public class LinkScanner {
private static final String[] adServiceStrings = { "adf.ly", "adfoc.us",
"any.gs", "tinylinks,co", "linkbucks.com", "yyv.co", "miniurls.co",
"qqc.co", "whackyvidz.com", "ultrafiles.net", "dyo.gs",
"megaline.co", "uberpicz.com", "linkgalleries.net", "qvvo.com",
"urlbeat.net", "seriousfiles.com", "zxxo.net", "ugalleries.net",
"picturesetc.net" };
private static final String USAGE = "java -jar scanner.jar <URL>";
public static void main(String[] args) {
try {
if (args.length == 1) {
System.out.println("Target URL: ");
scanAndPrint(args[0]);
} else if (args.length == 0) {
Scanner scan = new Scanner(System.in);
System.out.println("URL?");
String url = scan.nextLine();
scanAndPrint(url);
} else {
System.out.println(USAGE);
}
} catch (IOException e) {
System.err.println(e.getMessage());
}
}
private static void scanAndPrint(String string) throws IOException {
System.out.println("Scanning ...");
String target = new LinkScanner().scan(string);
if (target != null) {
System.out.println("Target URL: ");
System.out.println(target);
} else {
System.err.println("No target URL found");
}
}
public String scan(String urlStr) throws IOException {
if (!urlStr.startsWith("http://")) {
urlStr = "http://" + urlStr;
}
URL url = new URL(urlStr);
HttpURLConnection.setFollowRedirects(false);
if (isAdServiceLink(urlStr)) {
return handleAdLink(url);
} else {
return handleRedirect(url);
}
}
private boolean isAdServiceLink(String urlStr) {
for (String str : adServiceStrings) {
if (urlStr.contains(str)) {
return true;
}
}
return false;
}
private String handleRedirect(URL url) throws IOException {
return url.openConnection().getHeaderField("Location");
}
private String handleAdLink(URL url) throws IOException {
URLConnection urlc = url.openConnection();
urlc.addRequestProperty("user-agent", "Firefox");
BufferedReader in = null;
try {
in = new BufferedReader(
new InputStreamReader(urlc.getInputStream()));
String line;
while ((line = in.readLine()) != null) {
if (line.contains("var zzz =")) {
return extractADFlyURL(line);
}
if (line.contains("var click_url =")
&& !line.contains("//var click_url =")) {
return extractADFocURL(line);
}
if (line.contains("Lbjs.TargetUrl =")) {
return extractLinkBucksURL(line);
}
}
throw new IOException("Unable to find target URL in link");
} finally {
if (in != null) {
in.close();
}
}
}
private String extractLinkBucksURL(String line) {
String go = line.split("'")[1];
return go;
}
private String extractADFocURL(String line) throws IOException {
String go = line.split("\"")[1];
return go;
}
private String extractADFlyURL(String line) throws IOException {
String go = line.split("'")[1];
String redirect = handleRedirect(new URL("http://adf.ly" + go));
if (redirect == null) {
return go;
}
return redirect;
}
}
