Friday, December 31, 2010

Get pagenumber in pdf file

#How to Use Perl to Search a PDF Doc
#!/usr/bin/perl

use CAM::PDF;

my $file = shift;
my $search = shift;

my $doc = CAM::PDF->new($file);

foreach my $p ((1 .. $doc->numPages())) {
   #print "$p\n";
   my $str = $doc->getPageText($p);
   @lines = split(/\n/, $str);
}
my $i = 0;
foreach $line (@lines) {
   ++$i;
   if($line =~ /$search/) {
     print "\"$search\" found in line $i of page $p\n";
     print "$line\n\n"
   }
}

No comments: