Perl regex extracting domain name from URL

http://stackoverflow.com/questions/11875630/how-do-i-get-the-host-name-from-a-url-in-perl-using-regex

code.use strict;
use warnings;

use URI::Split qw/ uri_split uri_join /;

my $scheme_host = do {
  my (@parts) = uri_split 'http://linux.pacific.net.au/primary.xml.gz';
  uri_join @parts[0,1];
};

print $scheme_host;
code..


If cannot install module:

code.use strict;
use warnings;

my $url = 'http://linux.pacific.net.au/primary.xml.gz';

my ($scheme_host) = $url =~ m|^( .*?\. [^/]+ )|x;

print $scheme_host;
code..

outputs: http://linux.pacific.net.au


br. http://stackoverflow.com/questions/2497215/extract-domain-name-from-url

code.#!/usr/bin/perl -w
use strict;

my $url = $ARGV[0];

if($url =~ /([^:]*:\/\/)?([^\/]+\.[^\/]+)/g) {
  print $2;
}
code..

Usage:

code.
./test.pl 'https://example.com'
example.com

./test.pl 'https://www.example.com/'
www.example.com

./test.pl 'example.org/'
example.org

 ./test.pl 'example.org'
example.org

./test.pl 'example'  -> no output
code..


_"And if you just want the domain and not the full host + domain use this instead:"_

code.#!/usr/bin/perl -w
use strict;

my $url = $ARGV[0];
if($url =~ /([^:]*:\/\/)?([^\/]*\.)*([^\/\.]+\.[^\/]+)/g) {
  print $3;
}
code..


br. http://stackoverflow.com/questions/15627892/perl-regex-to-get-the-root-domain-of-a-url

code.$facebook = "www.facebook.com/xxxxxxxxxxx";

$facebook =~ s/www\.(.*\.com).*/$1/; # get what is between www. and .com

print $facebook;
code..

_"Returns"_

facebook.com

_"You may also want to make this work for .net, .org, etc. Something like:"_

code.s/www\.(.*\.(?:net|org|com)).*/$1/;
code..


br. http://www.perlmonks.org/?node_id=670802



br. http://www.willmaster.com/blog/perl/extracting-domain-name-from-url.php

_"First, remove the http/https and possible www. from the front of the URL:"_

code.$url =~ s!^https?://(?:www\.)?!!i;
code..

_"Then, strip off everything from the first "/" to the end of the URL (doing nothing if there is no "/"):"_

code.$url =~ s!/.*!!;
code..

_"Last, in case the URL was http://example.com?stuff or http://example.com#stuff or http://example.com:80/whatever, also strip off everything from the first "?" or "#" or ":", if present:"_

code.$url =~ s/[\?\#\:].*//;
code..

_"The value of $url is now the domain name by itself."_


 #perl  - #programming - #regex