WP image fetching and attaching to post

wp-image-import.php

	function process_image() {
		$response = '';
		$data[] = '';
		$error = 0;
		if (  isset( $_POST['ids'] ) )
			$ids = $_POST['ids'];

		$data['choose-tool'] = $_POST['args'];

			$post = get_post( $ids );
			$response .=  '<h3><a href="' . esc_url( admin_url( 'post.php?post=' . $post->ID . '&action=edit' ) ) . '" target="_blank">'.get_the_title( $post->ID ) . '</a></h3>';

			if ( 'import-media' == $data['choose-tool'] ) {
					$response .=  'Running import media tool<br>';
					$res =  $this->extract_multi( $post );
					$response .= $res['response'];
					$error = $error + (int)$res['error'];
				die( sprintf( $response . '<br>Media tool complete (Post ID %1$s) in %2$s seconds. %3$d errors', esc_html( $post->ID ), timer_stop(), $error = $error > 0 ? $error : 'no' ) );


			} elseif ( 'convert-import' == $data['choose-tool'] ) {
				 $response .=  'Running import and set featured image tool<br>';
				 $res =  $this->extract_multi( $post );
				 $response .= $res['response'];
				 $error = $error +  (int)$res['error'];

			}
			/** If the post already has an attached thumbnail continue with the loop  */
			if ( has_post_thumbnail( $post->ID ) ) {
				$response .=  'Featured image already set <br>';
				die( sprintf( $response . '<br>Media tool complete (Post ID %1$s) in %2$s seconds. %3$d errors', esc_html( $post->ID ), timer_stop(), $error = $error > 0 ? $error : 'no' ) );
			}
			/** @var $attachments array of attached images to the post */

			$attachments = $this->get_attach( $post->ID );

			if ( ! $attachments ) {
				$img = $this->extract_image( $post );
				if( empty( $img ) ) {
					$response .=  'No images found <br>';
					die( sprintf( $response . '<br>Media tool complete (Post ID %1$s) in %2$s seconds. %3$d errors', esc_html( $post->ID ), timer_stop(), $error = $error  > 0 ? $error : 'no' ) );

				}

				/** @var $file string or WP_Error of image attached to the post  */
				$file = media_sideload_image( $img, (int)$post->ID );
				if ( is_wp_error( $file ) ) {
					$response .= '<span style="color:red">Upload Error: Could not upload image. Check for malformed img src url</span><br>';
					$error++;
				} else {

					$atts = $this->get_attach( $post->ID );
					foreach ( $atts as $a ) {
						$img = set_post_thumbnail( $post->ID, $a['ID'] );
						if ( $img ) {
							$thumb = wp_get_attachment_thumb_url( $a['ID'] );
							$response .= '<img src="'.esc_url( $thumb ).'" /><br>';
							$response .= '<a href="' . wp_nonce_url( get_edit_post_link( $a['ID'], true ) ) . '" >' . get_the_title( $a['ID'] ) . '</a>  Set as Featured Image</p><br>';
						}
					}
					unset( $atts );
					unset( $a );
				}
			} else {

				foreach( $attachments as $a ) {
					$img = set_post_thumbnail( $post->ID, $a['ID'] );
					if ( $img ) {
						$thumb = wp_get_attachment_thumb_url( $a['ID'] );
						$response .= '<img src="' . esc_url( $thumb ) . '" /><br>';
						$response .=  '<a href="' . wp_nonce_url( get_edit_post_link( $a['ID'], true ) ) . '" >' . get_the_title( $a['ID'] ) . '</a>  Set as Featured Image</p><br>';
					}
				}
				unset( $attachments );
				unset( $a );
			}

		die( sprintf( $response.'<br>Media tool complete (Post ID %1$s) in %2$s seconds. %3$d errors', esc_html( $post->ID ), timer_stop(), $error = $error > 0 ? $error : 'no' ) );


	}



	/**
	 * 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_attach( $post_id ) {
		return get_children( array (
				'post_parent'    => $post_id,
				'post_type'      => 'attachment',
				'post_mime_type' => 'image',
				'posts_per_page'  => (int)1
			), ARRAY_A );
	}

	/**
	 * Extracts the first image in the post content
	 * @param object $post the post object
	 * @return bool|string false if no images or img src
	 */
	function extract_image( $post ) {
		$html = $post->post_content;
		if ( stripos( $html, '<img' ) !== false ) {
			$regex = '#<\s*img [^\>]*src\s*=\s*(["\'])(.*?)\1#im';
			preg_match( $regex, $html, $matches );
			unset( $regex );
			unset( $html );
			if ( is_array( $matches ) && ! empty( $matches ) ) {
				return  $matches[2];

			} else {
				return false;
			}
		} else {
			return false;
		}
	}

	/**
	 * Extracts all images in content adds to media library if external and updates content with new url
	 * @param object $post The post object
	 * @return array|bool Post id and images converted on success false if no images found in source
	 */
	function extract_multi( $post ) {
		$html = $post->post_content;
		$path = wp_upload_dir();
		$path = $path['baseurl'];
		$error = 0;
		$response = '';
		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 ) {
						$response .= 'Img already in media library<br>';
						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 );
						$thumb = wp_get_attachment_thumb_url( $id );
						array_push( $new, $url );
						array_push( $old, $img );

						$response .= '<p><a href="'. wp_nonce_url( get_edit_post_link( $id, true ) ).'" title="edit-image"><img src="'.esc_url( $thumb ).'" style="max-width:100px;" /></a><br>';
						$response .= '<a href="'. wp_nonce_url( get_edit_post_link( $id, true ) ).'" >'.get_the_title( $id ). '</a>  Imported and attached</p>';
					} else {
						$response .= '<span style="color:red">Upload Error: Could not upload image. Check for malformed img src url</span><br>';
						$error ++;
					}
				}
				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 );
						if ( isset( $post_id ) )
							$response .= 'Post Content updated for Post: '.esc_html( $post->post_title).'<br>';
						return array( 'error' => $error, 'response' => $response );
				} else
					 $response .= 'No external images found for ' . esc_html( $post->post_title ) . '<br>';
					return array ( 'error' => $error, 'response' => $response );

			} else {
				 $response .= 'Error processing images for '. esc_html( $post->post_title ) .'<br>';
				return array ( 'error' => $error, 'response' => $response );
			  }
		} else {
			 $response .= 'No images found for ' . esc_html( $post->post_title) . '<br>';
			return array ( 'error' => $error, 'response' => $response );
		  }
	}

	/**
	 * Queries the posts based on the form field data
	 * The database MySql queries were <del>inspired</del> jacked from the WordPress Export tool
	 *
	 * @param array $args The ajax form array formatted for the query
	 * @return array $post_ids an array of post ids from the query result
	 */
	function query( $args = array() ) {
		global $wpdb, $post;

		$defaults = array( 'content' => 'all', 'author' => false, 'category' => false,
		'start_date' => false, 'end_date' => false, 'status' => false, );
		$args = wp_parse_args( $args, $defaults );

		if ( 'all' != $args['content'] && post_type_exists( $args['content'] ) ) {
			$ptype = get_post_type_object( $args['content'] );
			if ( ! $ptype->can_export )
				$args['content'] = 'post';

			$where = $wpdb->prepare( "{$wpdb->posts}.post_type = %s", $args['content'] );
		} else {
			$post_types = get_post_types();
			$post_types = array_diff( $post_types, array( 'attachment', 'revision', 'nav_menu_item' ) );
			$esses = array_fill( 0, count($post_types), '%s' );
			$where = $wpdb->prepare( "{$wpdb->posts}.post_type IN (" . implode( ',', $esses ) . ')', $post_types );
		}

		if ( $args['status'] && ( 'post' == $args['content'] || 'page' == $args['content'] ) )
			$where .= $wpdb->prepare( " AND {$wpdb->posts}.post_status = %s", $args['status'] );
		else
			$where .= " AND {$wpdb->posts}.post_status != 'auto-draft'";

		$join = '';
		if ( $args['category'] && 'post' == $args['content'] ) {
			if ( $term = term_exists( $args['category'], 'category' ) ) {
				$join = "INNER JOIN {$wpdb->term_relationships} ON ({$wpdb->posts}.ID = {$wpdb->term_relationships}.object_id)";
				$where .= $wpdb->prepare( " AND {$wpdb->term_relationships}.term_taxonomy_id = %d", $term['term_taxonomy_id'] );
			}
		}

		if ( 'post' == $args['content'] || 'page' == $args['content'] ) {
			if ( $args['author'] )
				$where .= $wpdb->prepare( " AND {$wpdb->posts}.post_author = %d", $args['author'] );

			if ( $args['start_date'] )
				$where .= $wpdb->prepare( " AND {$wpdb->posts}.post_date >= %s", date( 'Y-m-d', strtotime($args['start_date']) ) );

			if ( $args['end_date'] )
				$where .= $wpdb->prepare( " AND {$wpdb->posts}.post_date < %s", date( 'Y-m-d', strtotime('+1 month', strtotime($args['end_date'])) ) );
		}

		$post_ids = $wpdb->get_col( "SELECT ID FROM {$wpdb->posts} $join WHERE $where ORDER BY ID ASC" );

			return $post_ids;
	}