name-gen/parse.pl

#!/usr/bin/perl

use strict;
use warnings;

# Scratch pad for parsing webpages for lists
# of different words/names, for the seed file

my @page = split("\n", `cat saints.html`);

foreach my $line ( @page ) {
	if ( $line =~ m/<td data-sort-value=.*<a\ href=.*title="(.*)"/ ) {
		my $line1 = $1;
		if ( $line1 =~ m/^([a-zA-z0-9\ ,-]{1,})/ ) {
			print "$1\n";
		}
	}
}