PHP Requires Chilkat v11.7.0+

Clipped, Off-Page and White-on-White Text in PDF Extraction

See more PDF Text Extraction Examples

Demonstrates the "clippedText", "offPageText" and "obscuredText" filters. Text that a reader never sees - hidden by a clipping path, outside the crop box, or drawn in the same color as the box beneath it - is excluded by default, and the quality report notes what was skipped. Each kind can be included. Chilkat2 PHP

<?php

use Chilkat2\JsonObject;
use Chilkat2\Pdf;

// 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 hidden_text.pdf

$pdf = new Pdf();
try {
    $pdf->LoadFile('qa_data/pdf/hidden_text.pdf');

    $json = new JsonObject();
    $jsonOut = new JsonObject();

    // The page has a visible paragraph plus three hidden lines: one drawn outside its clipping
    // rectangle, one below the crop box, and one in white on a white box.
    $pdf->ExtractText('text', $json, $jsonOut);
} catch (\Chilkat2\Exception $e) {
    echo $e->getMessage(), "\n";
    exit;
}

echo "---- default ----\n";
echo $jsonOut->StringOf('text'), "\n";

// The quality report says what was left out.
$i = 0;
$count_i = $jsonOut->SizeOfArray('quality.pages[0].issues');
while ($i < $count_i) {
    $jsonOut->I = $i;
    echo 'issue: ', $jsonOut->StringOf('quality.pages[0].issues[i].code'), "\n";
    $i = $i + 1;
}

// Include everything.
$json->UpdateString('clippedText', 'include');
$json->UpdateString('offPageText', 'include');
$json->UpdateString('obscuredText', 'include');
try {
    $pdf->ExtractText('text', $json, $jsonOut);
} catch (\Chilkat2\Exception $e) {
    echo $e->getMessage(), "\n";
    exit;
}

echo "---- clippedText, offPageText, obscuredText: include ----\n";
echo $jsonOut->StringOf('text'), "\n";

// Sample output:

// ---- default ----
// Visible Text
//
// This paragraph is visible. The page also carries three kinds of text a reader never sees.
//
// End of the visible text.
// issue: obscuredTextSkipped
// issue: clippedTextSkipped
// ---- clippedText, offPageText, obscuredText: include ----
// Visible Text
//
// This paragraph is visible. The page also carries three kinds of text a reader never sees.
//
// CLIPPED: this line is drawn outside its clipping rectangle.
//
// OBSCURED: this line is white on a white box.
//
// End of the visible text.
//
// OFFPAGE: this line sits below the crop box.