# The script, in brief... use PDF::API2; use LWP; $ua = LWP::UserAgent->new; $ua->agent('PDFInspector/0.2 (email@host.com)'); binmode STDOUT, ":utf8"; @url_list = qw( http://www.gs.gov.nl.ca/ohs/pdf/ann-rep-whsi.pdf http://www.gs.gov.nl.ca/cca/cr/pdf/coop/coop21-art-dis.pdf http://www.gs.gov.nl.ca/misc/data/gazette/wk/2006-01-13.pdf ); # ann-rep-whsi.pdf contains wide characters # coop21-art-dis.pdf # 2006-01-13.pdf is encrypted foreach (@url_list) { ($pdf_doc, $pdf_status, undef, undef) = do_get ($pdf_url, "Accept-Language" => "en"); $pdf = PDF::API2->openScalar($pdf_doc); %pdf_info = $pdf->info(); print "URL: $pdf_url"; print "Title: $pdf_info{'Title'}"; print "Author: $pdf_info{'Author'}"; print "Subject: $pdf_info{'Subject'}"; print "Creator: $pdf_info{'Creator'}"; print "Producer: $pdf_info{'Producer'}"; } # Results look like... URL: http://offline.gs.gov.nl.ca/ohs/pdf/ann-rep-whsi.pdf Title: *Garbled* Author: *Garbled* Subject: Creator: *Garbled* Producer: Acrobat PDFWriter 4.0 for Windows URL: http://offline.gs.gov.nl.ca/cca/cr/pdf/coop/coop01-art-inc.pdf Title: The Co-Operatives Act (Form 1) Author: Commercial Registrations Subject: Articles of Incorporation (Section 8) Creator: Producer: Acrobat Distiller 4.05 for Windows URL: http://offline.gs.gov.nl.ca/misc/data/gazette/wk/2006-01-13.pdf Title: *Garbled* Author: *Garbled* Subject: Creator: *Garbled* Producer: *Garbled*