PHP code example of xxxwer / pdftohtml-poppler

    
        
<?php
require_once('vendor/autoload.php');

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

    

xxxwer / pdftohtml-poppler example snippets

// if you are using composer, just use this
'test.pdf', [
    'pdftohtml_path' => '/usr/bin/pdftohtml',
    'pdfinfo_path' => '/usr/bin/pdfinfo'
]);

// example for windows
// $pdf = new \TonchikTm\PdfToHtml\Pdf('test.pdf', [
//     'pdftohtml_path' => '/path/to/poppler/bin/pdftohtml.exe',
//     'pdfinfo_path' => '/path/to/poppler/bin/pdfinfo.exe'
// ]);

// get pdf info
$pdfInfo = $pdf->getInfo();

// get count pages
$countPages = $pdf->countPages();

// get content from one page
$contentFirstPage = $pdf->getHtml()->getPage(1);

// get content from all pages and loop for they
foreach ($pdf->getHtml()->getAllPages() as $page) {
    echo $page . '<br/>';
}

$full_settings = [
    'pdftohtml_path' => '/usr/bin/pdftohtml', // path to pdftohtml
    'pdfinfo_path' => '/usr/bin/pdfinfo', // path to pdfinfo

    'generate' => [ // settings for generating html
        'singlePage' => false, // we want separate pages
        'imageJpeg' => false, // we want png image
        'ignoreImages' => false, // we need images
        'zoom' => 1.5, // scale pdf
        'noFrames' => false, // we want separate pages
    ],

    'clearAfter' => true, // auto clear output dir (if removeOutputDir==false then output dir will remain)
    'removeOutputDir' => true, // remove output dir
    'outputDir' => '/tmp/'.uniqid(), // output dir

    'html' => [ // settings for processing html
        'inlineCss' => true, // replaces css classes to inline css rules
        'inlineImages' => true, // looks for images in html and replaces the src attribute to base64 hash
        'onlyContent' => true, // takes from html body content only
    ]
]