#!/usr/bin/perl require LWP::UserAgent; require HTTP::Request; require HTTP::Response; my $url = "http://news.bbc.co.uk/rss/newsonline_uk_edition/front_page/rss091.xml"; my %options = ( agent => 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0)' ); my $ua = LWP::UserAgent -> new(%options); my $request = new HTTP::Request 'GET', $url; my $response = $ua->request($request); if (!($response->is_success)) { die "Could not fetch!\n"; } my $content = $response->content; my %words; while ($content =~ s/.*\n.*(.+)<\/title>.*\n.*<description>(.+)<\/description>//) { my $title = $1; my $descr = $2; $title =~ s/[^\w\d\s]+//g; $descr =~ s/[^\w\d\s]+//g; while ($title =~ s/([\w\d]+)\s+//) { $words{$1 . " "} = 1; } while ($descr =~ s/([\w\d]+)\s+//) { $words{$1 . " "} = 1; } } print sort keys %words;