Remove Duplicate product Images in Magento 2

Question

I have created a script file to delete all the duplicate product images.

Here is the code I used.

<?php
 error_reporting(E_ALL);
 use \Magento\Framework\App\Bootstrap;
 require __DIR__ . '/app/bootstrap.php';
 $bootstrap = Bootstrap::create(BP, $_SERVER);
 $obj = $bootstrap->getObjectManager(); 
 $app_state = $obj->get('\Magento\Framework\App\State');
 $app_state->setAreaCode('global');
 ini_set('memory_limit','10240M');
 ini_set('max_execution_time', 0); 
 set_time_limit(0); 


 $mediaApi = $obj->create('\Magento\Catalog\Model\Product\Gallery\Processor');
 $storeManager = $obj->get('\Magento\Store\Model\StoreManagerInterface');
 $mediaUrl = $storeManager->getStore()->getBaseUrl(\Magento\Framework\UrlInterface::URL_TYPE_MEDIA);
 $directoryList=$obj->get('\Magento\Framework\App\Filesystem\DirectoryList');
 $path = $directoryList->getPath('media'); 
$productCollection=$obj->create('Magento\Catalog\Model\ResourceModel\Product\Collection');
$_products = $productCollection->addAttributeToSelect('*')->load();
$i =0;
$total = count($_products);
$count = 0;
foreach($_products as $_prod)
{
    $_product = $obj->create('Magento\Catalog\Model\Product')->load($_prod->getId());
$_md5_values = array();

$base_image = $_product->getImage();

if($base_image != 'no_selection')
{
    $mediaUrl = $storeManager->getStore()->getBaseUrl(\Magento\Framework\UrlInterface::URL_TYPE_MEDIA);
    $filepath = $path.'/catalog/product' . $base_image ;
    if(file_exists($filepath))
        $_md5_values[] = md5(file_get_contents($filepath));
}
$i ++;
 // echo "\r\n processing product $i of $total ";

 // Loop through product images
 $_images = $_product->getMediaGalleryImages();

 if($_images)
   {
    foreach($_images as $_image)
    {
        //protected base image
        if($_image->getFile() == $base_image)
            continue;
        $filepath = $path.'/catalog/product' .$_image->getFile();
        if(file_exists($filepath))
            $md5 = md5(file_get_contents($filepath));
        else
            continue;

        if( in_array( $md5, $_md5_values ))
        {
            $mediaApi->removeImage($_product, $_image->getFile());

            echo "\r\n removed duplicate image from ".$_product->getSku();
            $count++;
        }
        else 
        {
            $_md5_values[] = $md5;
        }
    }
  }
  $_product->save();
}

Above script removes if same image file exist for a product, then only it will remove it,

In my case if same image imported multiple times for a product, that is created as image.jpg and image_1.jpg.

I need to remove all duplicate images(which are _1,_2 etc) for all the products.

Please correct me in the above script, to remove duplicate image for the product. Thanks

Answer 1

Make sure you are working on the admin store view:

        $this->storeManager->setCurrentStore(0);
        $product->setStoreId(0);

Use the Media Gallery 'Entries' instead:

    $gallery = $product->getMediaGalleryEntries();

Iterate with:

    foreach ($gallery as $key => $galleryImage) {

You can access the files with:

        $galleryImage->getFile()

Then when you have a duplicate:

                unset($gallery[$key]);

Then set the gallery to your revised one:

        $product->setMediaGalleryEntries($gallery);

Then save the product using the product repository:

        $this->productRepository->save($product);

Answer 2

You can Buy Extension available on MP that can clean your unused Catalog Images as well as Duplicate entries You can Clean theme manually or using CRON

Answer 3

If anyone needs a full script to remove duplicate product images, here it is. This will not remove the image with any image type (small image, thumbnail image, etc.) tagged with the image.

<?php
error_reporting(E_ALL);
use \Magento\Framework\App\Bootstrap;
require __DIR__ . '/app/bootstrap.php';
$bootstrap = Bootstrap::create(BP, $_SERVER);
$obj = $bootstrap->getObjectManager(); 
$app_state = $obj->get('\Magento\Framework\App\State');
$app_state->setAreaCode('global');
ini_set('memory_limit','10240M');
ini_set('max_execution_time', 0); 
set_time_limit(0);

$mediaApi = $obj->create('\Magento\Catalog\Model\Product\Gallery\Processor');
$storeManager = $obj->get('\Magento\Store\Model\StoreManagerInterface');
$storeManager->setCurrentStore(0);
$mediaUrl = $storeManager->getStore()->getBaseUrl(\Magento\Framework\UrlInterface::URL_TYPE_MEDIA);
$directoryList=$obj->get('\Magento\Framework\App\Filesystem\DirectoryList');
$path = $directoryList->getPath('media'); 
$productCollection=$obj->create('Magento\Catalog\Model\ResourceModel\Product\Collection');
$_products = $productCollection->addAttributeToSelect('*')->load();

$productRepository = $obj->get('\Magento\Catalog\Model\ProductRepository');
$i =0;
$total = count($_products);
$count = 0;
$productCount = array();
foreach($_products as $_prod) {
    $_product = $productRepository->getById($_prod->getId());
    $_product->setStoreId(0);
    $_md5_values = array();
    $base_image = $_product->getImage();
    
    if($base_image != 'no_selection') {
        $mediaUrl = $storeManager->getStore()->getBaseUrl(\Magento\Framework\UrlInterface::URL_TYPE_MEDIA);
        $filepath = $path.'/catalog/product' . $base_image ;
        if (file_exists($filepath)) {
            $_md5_values[] = md5(file_get_contents($filepath));            
        }
        $i++;

        echo "\r\n processing product $i of $total ";
        // Loop through product images
        $gallery = $_product->getMediaGalleryEntries();
        if ($gallery) {
            foreach ($gallery as $key => $galleryImage) {
                //protected base image
                if($galleryImage->getFile() == $base_image) {
                    continue;
                }
                $filepath = $path.'/catalog/product' .$galleryImage->getFile();

                if(file_exists($filepath)) {
                    $md5 = md5(file_get_contents($filepath));
                } else {
                    continue;
                }

                if( in_array( $md5, $_md5_values )) {
                    if (count($galleryImage->getTypes()) > 0) {
                        continue;
                    }
                    unset($gallery[$key]);
                    echo "\r\n removed duplicate image from ".$_product->getSku();
                    $count++;
                } else {
                    $_md5_values[] = $md5;
                }
            }
            
            $_product->setMediaGalleryEntries($gallery);
            $productRepository->save($_product);            
        }
        //$_product->save();
    }
}
die("Script Completed");