Perl Requires Chilkat v11.7.0+

Get Every Occurrence of a Label in a PDF

See more PDF Text Extraction Examples

Demonstrates the "labelOccurrence" option. When the same label appears more than once (for example "Total:" on each of several receipts), "first" (the default) uses the first occurrence, "all" returns every occurrence with its page, and a number selects one occurrence. Chilkat2 Perl

use strict;
use warnings;
use Chilkat2;

# This example requires the Chilkat API to have been previously unlocked.
# See Global Unlock Sample for sample code.

# The PDF used in this example (three receipts, one per page) is available at three_receipts.pdf

my $pdf = Chilkat2::Pdf->new;
my $success = $pdf->LoadFile('qa_data/pdf/three_receipts.pdf');
if (!$success) {
    print $pdf->LastErrorText, "\n";
    exit;
}

my $json = Chilkat2::JsonObject->new;
my $jsonOut = Chilkat2::JsonObject->new;

# Each of the three pages is a receipt with a "Total:" line.
$json->UpdateString('label', 'Total');
$json->UpdateString('labelValue', 'right');

# By default only the first occurrence (in reading order) is used.
$success = $pdf->ExtractText('text', $json, $jsonOut);
if (!$success) {
    print $pdf->LastErrorText, "\n";
    exit;
}

print 'First total: ', $jsonOut->StringOf('text'), "\n";

# labelOccurrence "all" returns every occurrence.  The "text" member holds the values joined
# by line breaks, and labelMatches has one entry per occurrence with its page.
$json->UpdateString('labelOccurrence', 'all');
$success = $pdf->ExtractText('text', $json, $jsonOut);
if (!$success) {
    print $pdf->LastErrorText, "\n";
    exit;
}

my $i = 0;
my $count_i = $jsonOut->SizeOfArray('labelMatches');
while ($i < $count_i) {
    $jsonOut->I($i);
    print 'Page ', $jsonOut->IntOf('labelMatches[i].page'), ' total: ', $jsonOut->StringOf('labelMatches[i].text'), "\n";
    $i = $i + 1;
}

# A number selects one occurrence: 2 is the second.
$json->UpdateInt('labelOccurrence', 2);
$success = $pdf->ExtractText('text', $json, $jsonOut);
if (!$success) {
    print $pdf->LastErrorText, "\n";
    exit;
}

print 'Second total: ', $jsonOut->StringOf('text'), "\n";

# The occurrences are counted over the selected pages, so combining "pages" with the label
# is another way to pick one receipt:
$json->UpdateString('labelOccurrence', 'first');
$json->UpdateString('pages', '3');
$json->UpdateString('label', 'Receipt No.');
$success = $pdf->ExtractText('text', $json, $jsonOut);
if (!$success) {
    print $pdf->LastErrorText, "\n";
    exit;
}

print 'Receipt number on page 3: ', $jsonOut->StringOf('text'), "\n";

# Sample output:

# First total: $19.86
# Page 1 total: $19.86
# Page 2 total: $17.34
# Page 3 total: $23.62
# Second total: $17.34
# Receipt number on page 3: 1003