I want to put hyperlinks on some strings that are in a complex PDF page. I don't have access to the source document for the PDF file.

How can I search for text strings on a page from the existing pdf file? I also need the position of the textlabels to place the hyperlink. Please see code below.

Is there a method to extract all text from a single pdf page, and iterate through it? Or should I use the Data::Dumper structure? I know by greeping though Data::Dumper output that it contains what I need, but the structure is too complex. There must be a better way.

#!/usr/bin/perl -w
use CAM::PDF;
use Getopt::Long;
use Pod::Usage;
use English qw(-no_match_vars);
use PDF::API2;
use Data::Dumper;
use strict;

our $VERSION = '0.02';

my %opts = (
            infile     => undef,
            pagenum    => undef,
            verbose    => 0,
            help       => 0,
            version    => 0,
            );

Getopt::Long::Configure('bundling');
GetOptions('i|infile=s'   => \$opts{infile},
           'p|pagenum=s'  => \$opts{pagenum},
           'v|verbose'    => \$opts{verbose},
           'h|help'       => \$opts{help},
           'V|version'    => \$opts{version},
           ) or pod2usage(1);
if ($opts{help})
{
   pod2usage(-exitstatus => 0, -verbose => 2);
}
if ($opts{version})
{
   print "v$VERSION\n";
   exit 0;
}

unless ($opts{infile} ){
print "Missing option -i (infile) \n";
die;
}
$opts{pagenum} ||= 1;


# get contents of e.g. page #27 
# parse strings:
my $infile = $opts{infile};

my $campdf=CAM::PDF->new($infile) or die "Can't open infile: $!\n";
my $numpages = $campdf->numPages();
print "Document $infile has $numpages pages.\n";
#rangeToArray ($pkg_or_doc, $min, $max, @range_parts) = @_;
my @range = CAM::PDF->rangeToArray(1, $numpages, "$opts{pagenum}");
my $range = join ", " , @range;
print "Checking page(s) " . $range . ".\n";
## done with campdf


# for each string $s matching something:.../, 
    # find coordinates of bounding box
    # add a link at that position, consisting of: http://my.org/$s
my $pdfa2 = PDF::API2->open($infile);
foreach my $pagenum (@range){
    my ($x, $y);
    $x = 40;
    $y = 680;
    my $pdfpage = $pdfa2->openpage($pagenum);

    my $str = $pdfpage->text();
## HERE I NEED TO parse all text strings on the page
## but I don't know how to do that

## continuing with hard-wired example...
    $pdfpage->gfx->textlabel(
    $x, 
    $y, 
    $pdfa2->corefont('Arial',-encode => 'latin1'),
    10,
    "Link",
    );
    my $url = qq{ http://my.org/something};
    draw_url($pdfa2, $pagenum, [$x, $y, $x + 50, $y + 10], $url); 
    $pdfpage->update();
    print "page $pagenum\n";

}
# save the page to a new file.



$pdfa2->saveas("doc/new.pdf");
$pdfa2->end;


sub draw_url
{
     my ($pdf, $page_num, $dims, $url) = @_;

     my $page = $pdf->openpage($page_num);
     my $an = $page->annotation;
     $an->url($url, (-rect => $dims), (-border => [1, 1, 1]));
     $page->update;

}
[download]