#!/usr/bin/perl

# urls.pl - extract the URLs from a file

# Eric Lease Morgan <eric_morgan@infomotions.com>
# September 13, 2011 - based on previous work at c4l11


# configure
use constant TWEETS => './urls.txt';

# require
use strict;

# initialize
my %urls = ();

# process the file
open INPUT, ' < ' . TWEETS or die "Can't open " . TWEETS . ": $!\n";
while ( <INPUT> ) {

	chop;
	/(http:\/\/.*)/;
	my ( $url, $cruft ) = split / /, $1;
	$url =~ s/\.$//;
	$url =~ s/\)$//;
	$url =~ s/,$//;
	$url =~ s/,$//;	
	$urls{ $url }++;
	
}

# clean up
close INPUT;

# output
foreach ( sort { $urls{ $b } <=> $urls{ $a } } keys %urls ) { print $urls{ $_ } . "\t$_\n" }

# done
exit;