Replace all of post’s image URLs with upload directory URLs

I have a plugin that does this manually in batch processes via ajax and I’ve been getting a lot of request for a way to make it automated.

This is the function that loads the post, downloads the images into the uploads directory and attaches them to the post. Then it does a search and replace for the old img urls and replaces them with the new ones. Attach this to all the publish actions and you should be good to go.

/**
 * Extracts all images in content adds to media library
 * if external and updates content with new url
 *
 * @param object $post The post object
 *
 */
function prefix_extract_external_images( $post ) {
  if ( ! is_object( $post ) ) {
    $post = get_post( $post );
  }
  $html = $post->post_content;
  $path = wp_upload_dir();
  $path = $path['baseurl'];

  if ( stripos( $html, '<img' ) !== false ) {

    $regex = '#<\s*img [^\>]*src\s*=\s*(["\'])(.*?)\1#im';
    preg_match_all( $regex, $html, $matches );

    if ( is_array( $matches ) && ! empty( $matches ) ) {
      $new = array();
      $old = array();
      foreach ( $matches[2] as $img ) {

        // Compare image source against upload directory
        // to prevent adding same attachment multiple times
        if ( stripos( $img, $path ) !== false ) {
          continue;
        }

        $tmp = download_url( $img );

        preg_match(
          '/[^\?]+\.(jpg|JPG|jpe|JPE|jpeg|JPEG|gif|GIF|png|PNG)/', $img, $matches
        );
        $file_array['name'] = basename( $matches[0] );
        $file_array['tmp_name'] = $tmp;
        // If error storing temporarily, unlink
        if ( is_wp_error( $tmp ) ) {
          @unlink( $file_array['tmp_name'] );
          $file_array['tmp_name'] = '';
          continue;
        }

        $id = media_handle_sideload( $file_array, $post->ID );

        if ( ! is_wp_error( $id ) ) {
          $url = wp_get_attachment_url( $id );
          array_push( $new, $url );
          array_push( $old, $img );
        }
      } // end foreach
      if ( ! empty( $new ) ) {
        $content = str_ireplace( $old, $new, $html );
        $post_args = array( 'ID' => $post->ID, 'post_content' => $content, );
        if ( ! empty( $content ) ) {
          $post_id = wp_update_post( $post_args );
        }       
      }
    } // end if ( is_array( $matches ) && ! empty( $matches ) )
  } // end if ( stripos( $html, '<img' ) !== false )
  return $post;
} // end function

$action_arrays = array( 'new_to_publish', 'pending_to_publish', 'draft_to_publish' );

foreach ( $action_array as $action ) {
  add_action( $action, 'prefix_extract_external_images' );
}

Bonus: Set the first image found as the featured image.

Add this right before the return $post in the function above.

$atts = get_first_attachment( $post->ID );

foreach ( $atts as $a ) {
  $img = set_post_thumbnail( $post->ID, $a['ID'] );
}

This function will also be needed by the above code.

/**
 * Queries for attached images
 * @param int $post_id The post id to check if attachments exist
 * @return array|bool The 1st attached on success false if no attachments
 */
 function get_first_attachment( $post_id ) {
   return get_children( array (
     'post_parent'    => $post_id,
     'post_type'      => 'attachment',
     'post_mime_type' => 'image',
     'posts_per_page'  => (int)1
   ), ARRAY_A );
 }