I am trying to extract data from credit card statements and enter them in a spreadsheet for tax purposes. What I have done so far involves a few steps, but I'm relatively new to Perl and working on what I know. Here are two separate scripts that I have written so far ... one reads all the data from pdf and writes to a text file, the other analyzes the text (imperfectly) and writes it to another text file. Then I would like to create a csv file to import into a spreadsheet or write directly to a spreadsheet. I would like to do this in one script, but two or three are enough.
script first:
use CAM::PDF;
my $file = "/home/cd/Documents/Jan14.pdf";
my $pdf = CAM::PDF->new($file);
my $doc="";
my $filename = 'report.txt';
open(my $fh, '>', $filename) or die "Could not open file '$filename' $!";
for ($i=1; $i <= $pdf->numPages(); $i++) {
$doc = $doc.$pdf->getPageText($i);
}
print $fh " $doc\n";
close $fh;
print "done\n";
Second script:
use strict;
use warnings;
undef $/;
open (FILE, '<', 'report.txt') or die "Could not open report.txt: $!";
my $file = <FILE>;
my ($stuff_that_interests_me) =
($file =~ m/.*?(Date of Transaction.*?CONTINUED).*/s);
print "$stuff_that_interests_me\n";
my $filename = 'data.txt';
open(my $fh, '>>', $filename) or die "Could not open file '$filename' $!";
print $fh " $stuff_that_interests_me\n";
close $fh;
print "done\n";
close (FILE) or die "Could not close report.txt: $!";
open (FILE2, '<', 'report.txt') or die "Could not open report.txt: $!";
my $file2 = <FILE2>;
my ($other_stuff_that_interests_me) =
($file2 =~ m/.*?(Page 2 .*?TRANSACTIONS THIS CYCLE).*/s);
print "$other_stuff_that_interests_me\n";
$filename = 'data.txt';
open($fh, '>>', $filename) or die "Could not open file '$filename' $!";
print $fh " $other_stuff_that_interests_me\n";
close $fh;
print "done\n";
close (FILE2) or die "Could not close report.txt: $!";
:
(CAM: PDF) CPAN, , ... , . , , .txt ... ?
package main;
use warnings;
use strict;
use CAM::PDF;
use Getopt::Long;
use Pod::Usage;
use English qw(-no_match_vars);
our $VERSION = '1.60';
my %opts = (
density => undef,
xdensity => undef,
ydensity => undef,
check => 0,
renderer => 'CAM::PDF::Renderer::Dump',
verbose => 0,
help => 0,
version => 0,
);
Getopt::Long::Configure('bundling');
GetOptions('r|renderer=s' => \$opts{renderer},
'd|density=f' => \$opts{density},
'x|xdensity=f' => \$opts{xdensity},
'y|ydensity=f' => \$opts{ydensity},
'c|check' => \$opts{check},
'v|verbose' => \$opts{verbose},
'h|help' => \$opts{help},
'V|version' => \$opts{version},
) or pod2usage(1);
if ($opts{help})
{
pod2usage(-exitstatus => 0, -verbose => 2);
}
if ($opts{version})
{
print "CAM::PDF v$CAM::PDF::VERSION\n";
exit 0;
}
if (defined $opts{density})
{
$opts{xdensity} = $opts{ydensity} = $opts{density};
}
if (defined $opts{xdensity} || defined $opts{ydensity})
{
if (!eval "require $opts{renderer}")
{
die $EVAL_ERROR;
}
if (defined $opts{xdensity})
{
no strict 'refs';
my $varname = $opts{renderer}.'::xdensity';
${$varname} = $opts{xdensity};
}
if (defined $opts{ydensity})
{
no strict 'refs';
my $varname = $opts{renderer}.'::ydensity';
${$varname} = $opts{ydensity};
}
}
if (@ARGV < 1)
{
pod2usage(1);
}
my $file = shift;
my $pagelist = shift;
my $doc = CAM::PDF->new($file) || die "$CAM::PDF::errstr\n";
foreach my $p ($doc->rangeToArray(1, $doc->numPages(), $pagelist))
{
my $tree = $doc->getPageContentTree($p, $opts{verbose});
if ($opts{check})
{
print "Checking page $p\n";
if (!$tree->validate())
{
print " Failed\n";
}
}
$tree->render($opts{renderer});
}