PHP code example of jcfrane / pdf-text-extractor

1. Go to this page and download the library: Download jcfrane/pdf-text-extractor 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/ */

jcfrane / pdf-text-extractor example snippets


use JCFrane\PdfTextExtractor\PdfTextExtractor;

class ParseResumeAction
{
    public function __invoke(PdfTextExtractor $extractor, string $path): string
    {
        $result = $extractor->extract($path);

        if (! $result->isSuccessful()) {
            return '';
        }

        return $result->getText();
    }
}


use JCFrane\PdfTextExtractor\Facades\PdfTextExtractor;

$result = PdfTextExtractor::extract(storage_path('app/resumes/candidate.pdf'));

if ($result->isSuccessful()) {
    $text = $result->getText();
    $strategyUsed = $result->getStrategy(); // pdf_parser, xobject, textract, tesseract
}


'min_text_length' => env('PDF_EXTRACTOR_MIN_TEXT_LENGTH', 20),


'strategies' => [
    JCFrane\PdfTextExtractor\Strategies\PdfParserStrategy::class,
    JCFrane\PdfTextExtractor\Strategies\XObjectStrategy::class,
    // JCFrane\PdfTextExtractor\Strategies\TextractStrategy::class,
    // JCFrane\PdfTextExtractor\Strategies\TesseractStrategy::class,
],


'strategies' => [
    JCFrane\PdfTextExtractor\Strategies\PdfParserStrategy::class,
    JCFrane\PdfTextExtractor\Strategies\XObjectStrategy::class,
    JCFrane\PdfTextExtractor\Strategies\TextractStrategy::class,
    JCFrane\PdfTextExtractor\Strategies\TesseractStrategy::class,
],


'textract' => [
    'region'  => env('PDF_EXTRACTOR_AWS_REGION', 'us-east-1'),
    'key'     => env('PDF_EXTRACTOR_AWS_KEY'),
    'secret'  => env('PDF_EXTRACTOR_AWS_SECRET'),
    'version' => env('PDF_EXTRACTOR_AWS_VERSION', 'latest'),

    // Required for multi-page PDFs (async API uploads the PDF to S3)
    's3_bucket' => env('PDF_EXTRACTOR_AWS_S3_BUCKET'),
    's3_prefix' => env('PDF_EXTRACTOR_AWS_S3_PREFIX', 'pdf-text-extractor'),

    // Async job polling
    'async_poll_interval_ms'  => (int) env('PDF_EXTRACTOR_AWS_ASYNC_POLL_INTERVAL_MS', 1000),
    'async_max_attempts'      => (int) env('PDF_EXTRACTOR_AWS_ASYNC_MAX_ATTEMPTS', 20),
    'async_delete_uploaded'   => (bool) env('PDF_EXTRACTOR_AWS_ASYNC_DELETE_UPLOADED', true),
],


'tesseract' => [
    'binary'              => env('PDF_EXTRACTOR_TESSERACT_BINARY', 'tesseract'),
    'ghostscript_binary'  => env('PDF_EXTRACTOR_GHOSTSCRIPT_BINARY', 'gs'),
    'language'            => env('PDF_EXTRACTOR_TESSERACT_LANGUAGE', 'eng'),
    'dpi'                 => (int) env('PDF_EXTRACTOR_TESSERACT_DPI', 300),
],

bash
php artisan vendor:publish --tag=pdf-text-extractor-config

bash
php artisan vendor:publish --tag=pdf-text-extractor-config