stemcell/app/code/Stemcell/Catalog/Console/Command/ProtocolsDocumentationPdfUpdate.php

<?php

namespace Stemcell\Catalog\Console\Command;

use Magento\Catalog\Model\Product;
use Magento\Catalog\Model\ProductRepository;
use Magento\Framework\App\Filesystem\DirectoryList;
use Magento\Framework\App\State;
use Magento\Framework\Exception\CouldNotSaveException;
use Magento\Framework\Exception\FileSystemException;
use Magento\Framework\Exception\InputException;
use Magento\Framework\Exception\StateException;
use Magento\Framework\UrlInterface;
use PhpOffice\PhpSpreadsheet\Cell\DataType;
use PhpOffice\PhpSpreadsheet\Spreadsheet;
use PhpOffice\PhpSpreadsheet\Writer\Exception;
use PhpOffice\PhpSpreadsheet\Writer\Xlsx;
use Symfony\Component\Console\Command\Command;
use Symfony\Component\Console\Input\InputInterface;
use Symfony\Component\Console\Output\OutputInterface;
use Magento\Catalog\Model\ResourceModel\Product\Collection as ProductCollection;

/**
 * 更新产品详情的产品说明书及文档中PDF的URL，如果PDF在服务器上存在，就用当前域名替换pdf的域名。
 */
class ProtocolsDocumentationPdfUpdate  extends Command
{
    private OutputInterface $output;
    private string $baseUrl;

    private array $notExistPdf = [];

    public function __construct(
        private ProductCollection $productCollection,
        private DirectoryList $directoryList,
        private UrlInterface $url,
        private ProductRepository $productRepository,
        private State $state,
        private \Magento\Store\Model\StoreManagerInterface $storeManager,
    ) {
        parent::__construct('protocols:documentation:update');
    }

    protected function updatePdfUrl(Product $product){

        $html = $product->getData('protocols_documentation');
        $html = preg_replace('/<\/?body[^>]*>/i', '', $html);

        $dom = new \DOMDocument();
        libxml_use_internal_errors(true); // 避免 HTML 解析警告
        $dom->loadHTML(mb_encode_numericentity($html, [0x80, 0x10FFFF, 0, ~0], 'UTF-8'));

        libxml_clear_errors();

        $links = $dom->getElementsByTagName('a');

        foreach ($links as $link) {
            $href = $link->getAttribute('href');

//            $output->writeln('old pdf href: ' . $href);
            
            if ($href && preg_match('/\.pdf$/i', $href)) {

                $pdfPath = parse_url($href, PHP_URL_PATH);

                $pdfPath = $this->directoryList->getPath(DirectoryList::PUB).'/'.$pdfPath;

                // 检查 PDF 是否存在
                if (file_exists($pdfPath)) {
                    $this->output->writeln(sprintf('product %s old pdf href: %s', $product->getSku(), $href));
                    $newUrl = preg_replace(
                        '#^https?://[^/]+/#i',
                        $this->baseUrl,
                        $href
                    );
                    $this->output->writeln(sprintf('<info>product %s updated pdf href: %s</info>', $product->getSku(), $newUrl));
                    // 更新 <a> 标签的 href
                    $link->setAttribute('href', $newUrl);
                } else {
                    $md5 = md5(strtolower($href));
                    if (!isset($this->notExistPdf[$md5])) {
                        $this->notExistPdf[$md5] = $href;
                    }

                }
            }
        }

        $body = $dom->getElementsByTagName("body")->item(0);

        return $dom->saveHTML($body);
    }

    /**
     * @throws Exception
     * @throws FileSystemException
     */
    protected function exportNotExistPdf()
    {
        $spreadsheet = new Spreadsheet();
        $sheet = $spreadsheet->getActiveSheet();

        $sheet->getStyle('A1:'  . 'B1')->getFont()->setBold(true);
        $sheet->setCellValue('A1', 'pdf  links');

        $rowIndex = 2;
        foreach ($this->notExistPdf as $link) {

//            $sheet->setCellValue('B' . $rowIndex, implode("\n", $links));
            $sheet->getStyle('A' . $rowIndex)->getAlignment()->setWrapText(true);
            $sheet->setCellValueExplicit('A' . $rowIndex, $link, DataType::TYPE_STRING);

            $sheet->getColumnDimension('A')->setWidth(100);
            $rowIndex++;
        }
        $writer = new Xlsx($spreadsheet);
        $pdfPath = $this->directoryList->getPath(DirectoryList::VAR_DIR).'/share/产品说明书及文档不存在的PDF-'.date('Ymd').'.xlsx';
        $writer->save($pdfPath);
    }
    public function execute(InputInterface $input, OutputInterface $output)
    {
        $this->state->setAreaCode(\Magento\Framework\App\Area::AREA_ADMINHTML);

        $this->output = $output;
        $this->baseUrl = $this->url->getBaseUrl();

        foreach ($this->storeManager->getStores(true) as $store) {
            $collection = $this->productCollection
                ->setStoreId($store->getId())
                ->addAttributeToFilter('protocols_documentation', ['neq' => 'NULL']);

            foreach ($collection as $product) {
//                if ($product->getSku()=='100-0237_C') {
//                    $output->writeln(preg_replace('/<\/?body[^>]*>/i', '', $product->getData('protocols_documentation')));
//                } else {
//                    continue;
//                }
                $output->writeln(sprintf('product: %s', $product->getSku()));
                $html = preg_replace('/<\/?body[^>]*>/i', '', $this->updatePdfUrl($product));
//                $output->writeln('updated html: ');
//                $output->writeln($html);
//                $output->writeln('');
                $product->setData('protocols_documentation', $html);
                try {
                    $product->setData('_edit_mode', true);
                    $product->setStoreId($store->getId());
                    $this->productRepository->save($product);
                } catch (\Exception $e) {
                    $this->output->writeln(sprintf('<error>product %s updated pdf fail, msg: %s</error>', $product->getSku(), $e->getMessage()));
                }
//                if ($product->getSku()=='100-0237_C') {
//                    break;
//                }
            }
        }

        $this->exportNotExistPdf();


        return Command::SUCCESS;
    }
}