A Drupal service class that can extract base64 encoded files from HTML content.

Base64FileManagerService.php

<?php

namespace Drupal\mymodule;

use Drupal\Core\File\Exception\FileNotExistsException;
use Drupal\Core\File\FileSystemInterface;
use Drupal\file\FileRepositoryInterface;
use Drupal\Core\Logger\LoggerChannelFactoryInterface;
use Drupal\Core\Logger\LoggerChannelInterface;

/**
 * Extract base64 encoded files from HTML content.
 *
 * @see https://www.hashbangcode.com/article/drupal-9-removing-base64-encoded-files-content
 */
class Base64FileManagerService {

  /**
   * The file repository service.
   *
   * @var \Drupal\file\FileRepositoryInterface
   */
  protected $fileRepository;

  /**
   * The file system service.
   *
   * @var \Drupal\Core\File\FileSystemInterface
   */
  protected $fileSystem;

  /**
   * The logger interface.
   *
   * @var \Drupal\Core\Logger\LoggerChannelInterface
   */
  protected $logger;

  /**
   * Constructs a FileManager object.
   *
   * @param \Drupal\file\FileRepositoryInterface $file_repository
   *   The file repository service.
   * @param \Drupal\Core\File\FileSystemInterface $file_system
   *   The file system service.
   * @param \Drupal\Core\Logger\LoggerChannelFactoryInterface $logger_factory
   *   The logging channel factory.
   */
  public function __construct(FileRepositoryInterface $file_repository, FileSystemInterface $file_system, LoggerChannelFactoryInterface $logger_factory) {
    $this->fileRepository = $file_repository;
    $this->fileSystem = $file_system;
    $this->logger = $logger_factory->get('mymodule.base64_file_manager_service');
  }

  /**
   * {@inheritDoc}
   */
  public function extractBase64FilesFromHtml($content, $id, $directory):string {
    // Load the HTML from the content and find all of the img elements.
    $dom = new \DOMDocument('1.0', 'UTF-8');
    $dom->loadHTML('<?xml version="1.0" encoding="UTF-8"?>' . $content, LIBXML_NOERROR);
    $dom->encoding = 'UTF-8';
    $dom->substituteEntities = TRUE;

    $images = $dom->getElementsByTagName('img');

    // If we found img tags
    if (count($images) == 0) {
      // No images found.
      return $content;
    }

    // Create internal count to allow multiple files to be named differently.
    $count = 0;

    foreach ($images as $image) {
      $count++;

      // Search for base64 encoded data within the img tag.
      $verify = preg_match('/(data|image\/png):?([^;]*);base64,(.*)/', $image->getAttribute('src'), $match);
      if (!$verify) {
        // Skip if this isn't a base64 encoded file.
        continue;
      }

      // Extract data for the file.
      $dataRaw = explode(',', $image->getAttribute('src'));
      $fileData = base64_decode($dataRaw[1]);

      // Extract the mime type for the file so that we can save it in the right
      // format.
      $finfo = finfo_open();
      $mimeType = finfo_buffer($finfo, $fileData, FILEINFO_MIME_TYPE);

      // We need to make sure the encoding of the base64 data is actually an image
      $verifyMime = preg_match('/image\/(png|jpg|jpeg|gif)/', $mimeType, $mime_match);

      if (!$verifyMime) {
        // Skip this file since it's not an image.
        \Drupal::logger('mymodule.base64')->info();
        $this->logger->info('File of type @mime not decoded when processing content', ['@mime' => $mimeType]);
        continue;
      }

      $fileName = $directory . '/' . $id . '-' . $count . '.' . $mime_match[1];

      /** @var \Drupal\file\FileInterface $file */
      $file = $this->fileRepository->writeData($fileData, $fileName, FileSystemInterface::EXISTS_REPLACE);

      if (!$file) {
        throw new FileNotExistsException('Could not create the file ' . $fileName);
      }

      // Update the img src and add needed attributes.
      $image->setAttribute('src', $file->createFileUrl());
      $image->setAttribute('data-entity-uuid', $file->uuid());
      $image->setAttribute('data-entity-type', 'file');
    }

    // The DOM document currently contains the doctype, head and body tags.
    // To remove these we create a mock document and copy the children
    // of the body tag into it.
    $mock = new \DOMDocument('1.0', 'UTF-8');
    $mock->encoding = 'UTF-8';
    $mock->substituteEntities = TRUE;

    $body = $dom->getElementsByTagName('body')->item(0);
    foreach ($body->childNodes as $child){
      $mock->appendChild($mock->importNode($child, true));
    }

    // Convert mock HTML document back into HTML.
    $content = trim($mock->saveHTML());
    return $content;
  }

}