PHP code example of fivefilters / readability.php

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

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

    

fivefilters / readability.php example snippets

ivefilters\Readability\Readability;
use fivefilters\Readability\ParseException;

$readability = new Readability();

$html = file_get_contents('https://your.favorite.newspaper/article.html');

try {
    $article = $readability->parse($html);
    if ($article->hasContent()) {
        echo $article->content;
    } else {
        // no article content found — title and metadata are still available
        echo sprintf('No content found in "%s"', $article->title);
    }
} catch (ParseException $e) {
    echo sprintf('Error processing text: %s', $e->getMessage());
}

$article->title;         // string – article title
$article->content;       // string – processed article HTML
$article->textContent;   // string – article text with all HTML removed
$article->length;        // int    – length of textContent in characters
$article->excerpt;       // ?string – description or short excerpt
$article->byline;        // ?string – author metadata
$article->siteName;      // ?string – name of the site
$article->dir;           // ?string – content direction (ltr/rtl)
$article->lang;          // ?string – content language
$article->publishedTime; // ?string – published time
$article->image;         // ?string – lead image URL (og:image/twitter:image/link)
$article->images;        // string[] – lead image + all content images, de-duplicated
$article->contentElement; // \Dom\Element – content as a DOM element
echo $article;           // same as $article->content

<h1><?= $article->title 

foreach ($article->contentElement->querySelectorAll('img[src]') as $img) {
    $images[] = $img->getAttribute('src');
}

use fivefilters\Readability\Readerable;

// Only run the full parse if we suspect it will produce a meaningful result.
if (Readerable::isProbablyReaderable($html)) {
    $article = new Readability()->parse($html);
}

Readerable::isProbablyReaderable($html, minScore: 0, minContentLength: 120);

$readability = new Readability(
    fixRelativeURLs: true,
    originalURL: 'https://my.newspaper.url/article/something-interesting-to-read.html',
);

use fivefilters\Readability\Configuration;

$configuration = new Configuration(fixRelativeURLs: true, originalURL: 'https://...');
$readability = new Readability($configuration);

bash
cd test/tools && npm install
node cross-check.mjs
php cross-check.php