PHP code example of xatham / text-extraction

1. Go to this page and download the library: Download xatham/text-extraction library. Choose the download type require.

2. Extract the ZIP file and open the index.php.

3. Add this code to the index.php. 
    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

xatham / text-extraction example snippets



/**
 * Extracting only pdf files, without ocr capturing
 */
$textExtractor = (new TextExtractionBuilder())->buildTextExtractor(
    [
        'withOcr' => false,
        'validMimeTypes' =>  ['application/pdf'],
    ],
);

$target = dirname(__DIR__) . '/examples/sample.pdf';
$plainTextDocument = $textExtractor->extractByFilePath($target);
if ($plainTextDocument === null) {
    exit('Could not extract any data');
}
$texts = $plainTextDocument->getTextItems();

foreach ($texts as $text) {
    var_dump($text);
}