Perl Requires Chilkat v11.7.0+

Search a PDF with a Regular Expression

See more PDF Text Extraction Examples

Demonstrates searching a PDF with a regular expression (regex: true), limiting the number of results (maxResults), and matching whole words only (wholeWord). 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 is available at order_records.pdf

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

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

# Find every order number.  With regex set to true, the query is a regular expression.
$json->UpdateString('query', 'ORD-[0-9]{4}-[0-9]{4}');
$json->UpdateBool('regex', 1);
# We only want the matched text, so no context is needed.
$json->UpdateInt('context', 0);

$success = $pdf->ExtractText('search', $json, $jsonOut);
if (!$success) {
    print $pdf->LastErrorText, "\n";
    exit;
}

print 'Order numbers found: ', $jsonOut->IntOf('count'), "\n";
my $i = 0;
my $count_i = $jsonOut->SizeOfArray('matches');
while ($i < $count_i) {
    $jsonOut->I($i);
    print $jsonOut->StringOf('matches[i].text'), "\n";
    $i = $i + 1;
}

# Find the e-mail addresses, but stop after the first three.
$json->UpdateString('query', '[a-z0-9._]+@[a-z]+[.][a-z]+');
$json->UpdateInt('maxResults', 3);
$success = $pdf->ExtractText('search', $json, $jsonOut);
if (!$success) {
    print $pdf->LastErrorText, "\n";
    exit;
}

print "First three e-mail addresses:\n";
$i = 0;
$count_i = $jsonOut->SizeOfArray('matches');
while ($i < $count_i) {
    $jsonOut->I($i);
    print $jsonOut->StringOf('matches[i].text'), "\n";
    $i = $i + 1;
}

# wholeWord: true matches only whole words.  The word "cat" appears once in the PDF,
# but it is also inside "catalog" and "category".
$json->Delete('maxResults');
$json->UpdateBool('regex', 0);
$json->UpdateString('query', 'cat');
$success = $pdf->ExtractText('search', $json, $jsonOut);
if (!$success) {
    print $pdf->LastErrorText, "\n";
    exit;
}

print 'Occurrences of cat (any): ', $jsonOut->IntOf('count'), "\n";

$json->UpdateBool('wholeWord', 1);
$success = $pdf->ExtractText('search', $json, $jsonOut);
if (!$success) {
    print $pdf->LastErrorText, "\n";
    exit;
}

print 'Occurrences of cat (whole word): ', $jsonOut->IntOf('count'), "\n";

# Sample output:

# Order numbers found: 9
# ORD-2026-0301
# ORD-2026-0302
# ORD-2026-0303
# ORD-2026-0304
# ORD-2026-0305
# ORD-2026-0306
# ORD-2026-0307
# ORD-2026-0308
# ORD-2026-0307
# First three e-mail addresses:
# alice.moore@example.com
# bkumar@example.org
# carla@example.net
# Occurrences of cat (any): 3
# Occurrences of cat (whole word): 1