The Code

Save the following code to a file called hoocount.pl:

	#!/usr/bin/perl -w

	use strict;
	use Date::Manip;
	use LWP::Simple;
	use Getopt::Long;

	$ENV{TZ} = "GMT" if $^O eq "MSWin32";

	# the homepage for Yahoo!'s "What's New".
	my $new_url = "http://dir.yahoo.com/new/";
	
	# the major categories at Yahoo!. hash'd because
	# we'll use them to hold our counts string.
	my @categories = ("Arts & Humanities",		"Business & Economy",
				  "Computers & Internet",	"Education",
				  "Entertainment",				"Government",
				  "Health",				"News & Media",
				  "Recreation & Sports",	"Reference",
				  "Regional",					"Science",
				  "Social Science",				"Society & Culture");
	my %final_counts; # where we save our final readouts.

	# load in our options from the command line.
	my %opts; GetOptions(\%opts, "c|count=i");
	die unless $opts{c}; # count sites from past $i days.

	# if we've been told to count the number of new sites,
	# then we'll go through each of our main categories
	# for the last $i days and collate a result.

	# begin the header
	# for our import file.
	my $header = "Category";

	# from today, going backwards, get $i days.
	for (my $i=1; $i <= $opts{c}; $i++) {
	
		# create a Data::Manip time that will
		# be used to construct the last $i days	
		my $day; # query for Yahoo! retrieval.
		if ($i == 1) { $day = "yesterday"; }	
		else { $day = "$i days ago"; }
		my $date = UnixDate($day, "%Y%m%d");

		# and this date to
		# our import file.
		$header .= "\t$date";
		
		# and download the day.
		my $url = "$new_url$date.html";
		my $data = get($url) or die $!;
		
		# and loop through each of our categories.
		my $day_count; foreach my $category (sort @categories) {
			$data =~ /$category.*?(\d+)/; my $count = $1 || 0;
			$final_counts{$category} .= "\t$count"; # building our string.
		}
	}

	# with all our counts finished,
	# print out our final file.
	print $header . "\n";
	foreach my $category (@categories) {
		print $category, $final_counts{$category}, "\n";
	}