What is the fastest way to get the domain/host name from a URL?
You want to be rather careful with implementing a "fast" way unpicking URLs. There is a lot of potential variability in URLs that could cause a "fast" method to fail. For example:
The scheme (protocol) part can be written in any combination of upper and lower case letters; e.g. "http", "Http" and "HTTP" are equivalent.
The authority part can optionally include a user name and / or a port number as in "http://[email protected]:8080/index.html".
Since DNS is case insensitive, the hostname part of a URL is also (effectively) case insensitive.
It is legal (though highly irregular) to %-encode unreserved characters in the scheme or authority components of a URL. You need to take this into account when matching (or stripping) the scheme, or when interpreting the hostname. An hostname with %-encoded characters is defined to be equivalent to one with the %-encoded sequences decoded.
Now, if you have total control of the process that generates the URLs you are stripping, you can probably ignore these niceties. But if they are harvested from documents or web pages, or entered by humans, you would be well advised to consider what might happen if your code encounters an "unusual" URL.
If your concern is the time taken to construct URL objects, consider using URI objects instead. Among other good things, URI objects don't attempt a DNS lookup of the hostname part.
Try method : getDomainFromUrl() in that class
package com.visc.mobilesecurity.childrencare.utils;
import android.content.Context;
import com.visc.mobilesecurity.antitheft.backwardcompatibility.FroyoSupport;
import com.visc.mobilesecurity.antitheft.util.AntiTheftUtils;
import com.visc.mobilesecurity.constant.Key;
import com.visc.mobilesecurity.util.Prefs;
import org.json.JSONObject;
import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
/**
* Created by thongnv12 on 3/9/2018.
*/
public class ChildcareUtils {
public static final String[] NATION_DOMAIN = {"af", "ax", "al", "dz", "as", "ad", "ao", "ai", "aq", "ag", "ar", "am", "aw", "ac", "au", "at", "az", "bs", "bh", "bd", "bb", "eus",
"by", "be", "bz", "bj", "bm", "bt", "bo", "bq", "ba", "bw", "bv", "br", "io", "vg", "bn", "bg", "bf", "mm", "bi", "kh", "cm", "ca", "cv", "cat", "ky", "cf", "td", "cl",
"cn", "cx", "cc", "co", "km", "cd", "cg", "ck", "cr", "ci", "hr", "cu", "cw", "cy", "cz", "dk", "dj", "dm", "do", "tl", "ec", "eg", "sv", "gq", "er", "ee", "et", "eu",
"fk", "fo", "fm", "fj", "fi", "fr", "gf", "pf", "tf", "ga", "gal", "gm", "ps", "ge", "de", "gh", "gi", "gr", "gl", "gd", "gp", "gu", "gt", "gg", "gn", "gw", "gy", "ht",
"hm", "hn", "hk", "hu", "is", "in", "id", "ir", "iq", "ie", "im", "il", "it", "jm", "jp", "je", "jo", "kz", "ke", "ki", "kw", "kg", "la", "lv", "lb", "ls", "lr", "ly",
"li", "lt", "lu", "mo", "mk", "mg", "mw", "my", "mv", "ml", "mt", "mh", "mq", "mr", "mu", "yt", "mx", "md", "mc", "mn", "me", "ms", "ma", "mz", "mm", "na", "nr", "np",
"nl", "nc", "nz", "ni", "ne", "ng", "nu", "nf", "kp", "mp", "no", "om", "pk", "pw", "ps", "pa", "pg", "py", "pe", "ph", "pn", "pl", "pt", "pr", "qa", "ro", "ru", "rw",
"re", "bq", "bl", "sh", "kn", "lc", "mf", "fr", "pm", "vc", "ws", "sm", "st", "sa", "sn", "rs", "sc", "sl", "sg", "bq", "sx", "sk", "si", "sb", "so", "so", "za", "gs",
"kr", "ss", "es", "lk", "sd", "sr", "sj", "sz", "se", "ch", "sy", "tw", "tj", "tz", "th", "tg", "tk", "to", "tt", "tn", "tr", "tm", "tc", "tv", "ug", "ua", "ae", "uk",
"us", "vi", "uy", "uz", "vu", "va", "ve", "vn", "wf", "eh", "zm", "zw"};
public static boolean isInNationString(String str) {
for (int index = 0; index < NATION_DOMAIN.length; index++) {
if (NATION_DOMAIN[index].equals(str)) {
return true;
}
}
return false;
}
public static String getDomainFromUrl(String urlStr) {
try {
String result = null;
// URL url = new URL(urlStr);
// result = url.getHost();
// return result;
//
// for test
// check dau cach
if (urlStr.contains(" ")) {
return null;
}
// replace
urlStr = urlStr.replace("https://", "");
urlStr = urlStr.replace("http://", "");
urlStr = urlStr.replace("www.", "");
//
String[] splitStr = urlStr.split("/");
String domainFull = splitStr[0];
String[] splitDot = domainFull.split("\\.");
if (splitDot.length < 2) {
return null;
}
String nationStr = splitDot[splitDot.length - 1];
if (isInNationString(nationStr)) {
if (splitDot.length < 4) {
result = domainFull;
} else {
StringBuilder strResult = new StringBuilder();
int lengthDot = splitDot.length;
strResult.append(splitDot[lengthDot - 3]).append(".");
strResult.append(splitDot[lengthDot - 2]).append(".");
strResult.append(splitDot[lengthDot - 1]);
result = strResult.toString();
}
} else {
if (splitDot.length < 3) {
result = domainFull;
} else {
StringBuilder strResult = new StringBuilder();
int lengthDot = splitDot.length;
strResult.append(splitDot[lengthDot - 2]).append(".");
strResult.append(splitDot[lengthDot - 1]);
result = strResult.toString();
}
}
return result;
} catch (Exception ex) {
ex.printStackTrace();
return null;
}
}
}
I wrote a method (see below) which extracts a url's domain name and which uses simple String matching. What it actually does is extract the bit between the first "://" (or index 0 if there's no "://" contained) and the first subsequent "/" (or index String.length() if there's no subsequent "/"). The remaining, preceding "www(_)*." bit is chopped off. I'm sure there'll be cases where this won't be good enough but it should be good enough in most cases!
I read here that the java.net.URI class could do this (and was preferred to the java.net.URL class) but I encountered problems with the URI class. Notably, URI.getHost() gives a null value if the url does not include the scheme, i.e. the "http(s)" bit.
/**
* Extracts the domain name from {@code url}
* by means of String manipulation
* rather than using the {@link URI} or {@link URL} class.
*
* @param url is non-null.
* @return the domain name within {@code url}.
*/
public String getUrlDomainName(String url) {
String domainName = new String(url);
int index = domainName.indexOf("://");
if (index != -1) {
// keep everything after the "://"
domainName = domainName.substring(index + 3);
}
index = domainName.indexOf('/');
if (index != -1) {
// keep everything before the '/'
domainName = domainName.substring(0, index);
}
// check for and remove a preceding 'www'
// followed by any sequence of characters (non-greedy)
// followed by a '.'
// from the beginning of the string
domainName = domainName.replaceFirst("^www.*?\\.", "");
return domainName;
}
If you want to handle https etc, I suggest you do something like this:
int slashslash = url.indexOf("//") + 2;
domain = url.substring(slashslash, url.indexOf('/', slashslash));
Note that this is includes the www part (just as URL.getHost() would do) which is actually part of the domain name.
Edit Requested via comments
Here are two methods that might be helpful:
/**
* Will take a url such as http://www.stackoverflow.com and return www.stackoverflow.com
*
* @param url
* @return
*/
public static String getHost(String url){
if(url == null || url.length() == 0)
return "";
int doubleslash = url.indexOf("//");
if(doubleslash == -1)
doubleslash = 0;
else
doubleslash += 2;
int end = url.indexOf('/', doubleslash);
end = end >= 0 ? end : url.length();
int port = url.indexOf(':', doubleslash);
end = (port > 0 && port < end) ? port : end;
return url.substring(doubleslash, end);
}
/** Based on : http://grepcode.com/file/repository.grepcode.com/java/ext/com.google.android/android/2.3.3_r1/android/webkit/CookieManager.java#CookieManager.getBaseDomain%28java.lang.String%29
* Get the base domain for a given host or url. E.g. mail.google.com will return google.com
* @param host
* @return
*/
public static String getBaseDomain(String url) {
String host = getHost(url);
int startIndex = 0;
int nextIndex = host.indexOf('.');
int lastIndex = host.lastIndexOf('.');
while (nextIndex < lastIndex) {
startIndex = nextIndex + 1;
nextIndex = host.indexOf('.', startIndex);
}
if (startIndex > 0) {
return host.substring(startIndex);
} else {
return host;
}
}