PHP code example of bitandblack / document-crawler

1. Go to this page and download the library: Download bitandblack/document-crawler 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/ */

    

bitandblack / document-crawler example snippets




use BitAndBlack\DocumentCrawler\ContentCrawler\TitleCrawler;
use Symfony\Component\DomCrawler\Crawler;

$document = <<<HTML
<!doctype html>
<html lang="en">
    <head>
        <title>Test</title>
    </head>
    <body>
        <h1>Hello world</h1>
    </body>
</html>
HTML;

$crawler = new Crawler($document);

$titleCrawler = new TitleCrawler($crawler);
$titleCrawler->crawlContent();

// This will output `Test`.
echo $titleCrawler->getTitle();



use BitAndBlack\DocumentCrawler\HolisticDocumentCrawler;

$document = <<<HTML
<!doctype html>
<html lang="en">
    <head>
        <title>Test</title>
    </head>
    <body>
        <h1>Hello world</h1>
    </body>
</html>
HTML;

$holisticDocumentCrawler = new HolisticDocumentCrawler($document);

// Get all anchors:
$anchors = $holisticDocumentCrawler->getAnchors();

// Get all icons:
$icons = $holisticDocumentCrawler->getIcons();

// Get all images:
$images = $holisticDocumentCrawler->getImages();

// Get the language code:
$languageCode = $holisticDocumentCrawler->getLanguageCode();

// Get all meta tags:
$metaTags = $holisticDocumentCrawler->getMetaTags();

// Get the title:
$title = $holisticDocumentCrawler->getTitle();



use BitAndBlack\DocumentCrawler\HolisticDocumentCrawler;

$holisticDocumentCrawler = HolisticDocumentCrawler::createFromUrl('https://www.bitandblack.com');