extract-code.php

gistfile1.txt

<?php

error_reporting(E_ALL);
ini_set('display_errors', 1);
set_time_limit(0);

$chapters = glob('./chapters/*.html');

$dom = new DOMDocument;

foreach ($chapters as $chapter) {

    // Extract this chapter name, without path and suffix info
    $name = basename($chapter, '.html');

    // Silence invalid HTML format warnings
    // https://stackoverflow.com/a/17559716
    libxml_use_internal_errors(true);
    $dom->loadHTMLFile($chapter);
    libxml_clear_errors();

    // Get all <pre> elements
    $codes = $dom->getElementsByTagName('pre');

    // Set counter for this chapter's codes
    $counter = 0;

    // Loop through each chapter code and extract it into its own file
    foreach ($codes as $code) {
        $counter++;
        file_put_contents(
            './chapters-codes/' . $name . '_' . $counter . '.php',
            $code->nodeValue
        );
    }
}