#!/usr/bin/perl -w 
# find the title and size of a webdocument, adapted from the Perl cookbook
# usage:  titlebytes.pl http://www.cnn.com

use LWP::UserAgent; 
use HTTP::Request; 
use HTTP::Response; 
use URI::Heuristic;

my $raw_url = shift or die "usage: $0 url\n"; 
my $url = URI::Heuristic::uf_urlstr($raw_url);

$| = 1;                                                                      # flush next line 
printf "%s =>\n\t", $url;
my $ua = LWP::UserAgent->new(); 
$ua->agent("Mozilla/v9.14 Platinum");                                        # give it time, it'll get there
my $req = HTTP::Request->new(GET => $url); 
$req->referer("http://how.are.you");                                         # perplex the log analysers

my $response = $ua->request($req);
if ($response->is_error()) {
     printf " %s\n", $response->status_line;
 } else {
     my $count;
     my $bytes;
     my $content = $response->content();                                     # the html document
     $bytes = length $content;                                               # length of the document
     $count = ($content =~ tr/\n/\n/);                                       # number of lines
     printf "%s (%d lines, %d bytes)\n", $response->title(), $count, $bytes; 
}