Advanced Search

Update PDF metadata from BibTeX data file

/ Published in: Perl
Save to your folder(s)

Expand | Embed | Plain Text

Copy this code and paste it in your HTML 
  1. #!/usr/bin/env perl
  2. # updatepdf.pl
  3. # parses a bibtex file and updates linked pdf file's metadata with bibtex data
  4.  
  5. use strict;
  6. use warnings;
  7.  
  8. use Getopt::Std;
  9. use Text::BibTeX;
  10. use PDF::API2;
  11.  
  12. # option -x forces overwriting existing metadata
  13. # option -f provides the field name which contains the linked PDF file's path
  14. # default PDF file field name to "local-url"
  15. my %options;
  16. getopts('xf:', \%options);
  17. my $field = $options{'f'} || 'local-url';
  18.  
  19. # get input bibtex file's name from cl argument or read stdin 
  20. my $in_file = shift || "<&STDIN";
  21. my $bib = Text::BibTeX::File->new($in_file); 
  22.  
  23. # loops thorugh bibtex entries
  24. while (my  $entry = new Text::BibTeX::Entry $bib) {
  25. 	# skip non-regular entries
  26.  	next unless $entry->parse_ok && $entry->metatype == BTE_REGULAR;
  27. 	# read local file field from the bibtex entry
  28. 	if ( $entry->exists($field) ) {
  29. 		my $pdf_file = $entry->get($field);
  30. 		# skip file if doesn't exist or not a .pdf
  31. 		if ($pdf_file !~ m{\.pdf$}i || ! -e $pdf_file) {
  32. 			warn "Skipping $pdf_file\n";
  33. 			next;
  34. 		}
  35. 		# get PDF's info
  36. 		my $pdf = PDF::API2->open($pdf_file);
  37. 		my %info = $pdf->info();
  38. 		# set authour and title fields
  39. 		$info{'Author'} = $entry->get('author') 
  40. 			if $entry->exists('author') && ( $options{'x'} || !defined $info{'Author'} ) ;
  41. 		$info{'Title'} = $entry->get('title') 
  42. 			if $entry->exists('title') and ( $options{'x'} || !defined $info{'Title'} );
  43. 		# write
  44. 		$pdf->info(%info);
  45. 		$pdf->update();
  46. 	} 
  47. }

Report this snippet


Comments

RSS Icon Subscribe to comments

You need to login to post a comment.