#!/usr/bin/perl # use LWP::UserAgent; # create a new UserAgent instance my $ua = LWP::UserAgent->new; # set ua identity to Mozilla, otherwise the site won't recognize it my @ns_headers = ( 'User-Agent' => 'Mozilla/4.76 [en] (Win98; U)', ); # get last name as a command line argument my $cognome = $ARGV[0]; # the query is composed just by appending the last name to the following URL my $URL = "http://www.dei.polimi.it/people/index.php?p=$cognome"; # get the page or DIE my $res = $ua->get( $URL, @ns_headers ); die "Can't get $URL -- ", $res->status_line unless $res->is_success; my $content = $res->content; # if content contains the specified regexp, extract and print the section if ($content =~ /id_sezione=.&idlang=ita">([^<]*)</si){ print " Section : $1\n"; }