ch12.085_prob

Perl Best Practices the source code

##############################################################################
## Code fragment (NOT RECOMMENDED) from Chapter 12 of "Perl Best Practices" ##
##     Copyright (c) O'Reilly & Associates, 2005. All Rights Reserved.      ##
##  See: http://www.oreilly.com/pub/a/oreilly/ask_tim/2001/codepolicy.html  ##
##############################################################################


# Standard modules...
use strict;
use warnings;
use IO::Prompt;
use Carp;
use English qw( -no_match_vars );
use Data::Alias;
use Readonly;


# Build a regex that matches HTTP addresses...
Readonly my $HTTP => qr{
    (?:(?:http)://(?:(?:(?:(?:(?:(?:[a-zA-Z0-9][-a-zA-Z0-9]*)?[a-zA-Z0-9])[.])*
    (?:[a-zA-Z][-a-zA-Z0-9]*[a-zA-Z0-9]|[a-zA-Z])[.]?)|(?:[0-9]+[.][0-9]+[.]
    [0-9]+[.][0-9]+)))(?::(?:(?:[0-9]*)))?(?:/(?:(?:(?:(?:(?:(?:[a-zA-Z0-9
    \-_.!~*'():@&=+\$,]+|(?:%[a-fA-F0-9][a-fA-F0-9]))*)(?:;(?:(?:[a-zA-Z0-9
    \-_.!~*'():@&=+\$,]+|(?:%[a-fA-F0-9][a-fA-F0-9]))*))*)(?:/(?:(?:(?:
    [a-zA-Z0-9\-_.!~*'():@&=+\$,]+|(?:%[a-fA-F0-9][a-fA-F0-9]))*)(?:;(?:(?:
    [a-zA-Z0-9\-_.!~*'():@&=+\$,]+|(?:%[a-fA-F0-9][a-fA-F0-9]))*))*))*))(?:[?]
    (?:(?:(?:[;/?:@&=+\$,a-zA-Z0-9\-_.!~*'()]+|(?:%[a-fA-F0-9][a-fA-F0-9
    ]))*)))?))?)
}xms;
 
# Find webpages...
URI:
while (my $uri = <DATA>) {
    next URI if $uri !~ m/ $HTTP /xms;
    print $uri;
}


__DATA__
http://damian.conway.org
mailto:[e-mail]
http://perl.com