Coastpress Migration Script

gistfile1.txt

<?php

function post_exists_by_title($title) {
    global $wpdb;
    $query = $wpdb->prepare("SELECT ID FROM $wpdb->posts WHERE post_title = %s AND post_type = 'post' AND post_status = 'publish' LIMIT 1", $title);
    return $wpdb->get_var($query);
}

function set_featured_image($post_id, $image_url) {
    if (empty($image_url)) return;

    $upload_dir = wp_upload_dir(); // WordPress upload directory
    $image_data = file_get_contents($image_url);
    $filename = urldecode(basename($image_url));
    $file_path = $upload_dir['path'] . '/' . $filename;
    
    $new_file = !file_exists($file_path);
    
    // Save the new file if it doesn't exist
    file_put_contents($file_path, $image_data);

    if ($new_file) {
        $wp_filetype = wp_check_filetype($filename, null);
        $attachment = array(
            'post_mime_type' => $wp_filetype['type'],
            'post_title'     => sanitize_file_name($filename),
            'post_content'   => '',
            'post_status'    => 'inherit'
        );
        
        $attach_id = wp_insert_attachment($attachment, $file_path, $post_id);
        // Normally you would generate metadata and use wp_update_attachment_metadata() here
    } else {
        // File exists, find the attachment ID
        $attach_id = attachment_url_to_postid($upload_dir['url'] . '/' . $filename);
    }

    // Set the found or new attachment as the featured image
    set_post_thumbnail($post_id, $attach_id);
}

function fetch_full_post_content($url) {
    if (!$url) return 'No content found';
    
    // Initialize cURL session
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
    curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (compatible; MyScraperBot/1.0; +http://example.com/bot)');

    // Execute cURL session and close it
    $html = curl_exec($ch);
    curl_close($ch);
    
    $doc = new DOMDocument();
    libxml_use_internal_errors(true);
    $doc->loadHTML($html);
    libxml_clear_errors();
    
    $xpath = new DOMXPath($doc);
    $contentNode = $xpath->query("//div[contains(@class, 'post-body')]");
    return $contentNode->item(0) ? $contentNode->item(0)->C14N() : 'No content found';
}

function fetch_posts($url) {
    // Initialize cURL session
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
    curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (compatible; MyScraperBot/1.0; +http://example.com/bot)');

    // Execute cURL session and close it
    $html = curl_exec($ch);
    curl_close($ch);

    $doc = new DOMDocument();
    libxml_use_internal_errors(true); // Suppress libXML errors
    $doc->loadHTML($html);
    libxml_clear_errors();

    $xpath = new DOMXPath($doc);
    $postsQuery = "//div[contains(@class, 'post-outer')]";
    $nextPageQuery = "//a[@title='More posts']";

    foreach ($xpath->query($postsQuery) as $post) {
        $titleNode = $xpath->query(".//h3[contains(@class, 'post-title')]/a", $post);
        $title = $titleNode->item(0) ? $titleNode->item(0)->nodeValue : 'No title found';
        $postUrl = $titleNode->item(0) ? $titleNode->item(0)->getAttribute('href') : null;

        // Fetch full post content from the post's page
        $fullPostContent = fetch_full_post_content($postUrl);

// Extract excerpt from snippet-item
        $excerptNode = $xpath->query(".//div[contains(@class, 'snippet-item')]", $post);
        $excerpt = $excerptNode->item(0) ? $excerptNode->item(0)->nodeValue : '';
        
        $dateNode = $xpath->query(".//time[@class='published']", $post);
        $date = $dateNode->item(0) ? $dateNode->item(0)->getAttribute('datetime') : date('Y-m-d H:i:s');

        $post_data = array(
            'post_title'    => sanitize_text_field($title),
            'post_content'  => wp_kses_post($fullPostContent),  // Use the full content
            'post_status'   => 'publish',
            'post_author'   => 1,
            'post_date'     => date('Y-m-d H:i:s', strtotime($date)),
            'post_category' => array(1),
            'post_excerpt'  => sanitize_text_field($excerpt) 
        );
        
        $existing_post_id = post_exists_by_title($post_data['post_title']);

    if ($existing_post_id) {
        // Post exists, update it
        $post_data['ID'] = $existing_post_id; // Set the ID to update the existing post
        $post_id = wp_update_post($post_data);
        echo "Updated existing post: " . $post_data['post_title'] . " (ID: $post_id)<br>";
    } else {
        // Post does not exist, insert it
        $post_id = wp_insert_post($post_data);
        echo "Inserted new post: " . $post_data['post_title'] . " (ID: $post_id)<br>";
    }
    
    // Extract image URL from JSON-LD script
        $scriptNodes = $xpath->query(".//script[@type='application/ld+json']", $post);
        $imageURL = '';
        foreach ($scriptNodes as $scriptNode) {
            $jsonData = json_decode($scriptNode->nodeValue, true);
            if (isset($jsonData['image']['url'])) {
                $imageURL = $jsonData['image']['url'];
                break;
            }
        }

        // Set featured image
        set_featured_image($post_id, $imageURL);

    }
    
    // Check for the next page
    $nextPage = $xpath->query($nextPageQuery)->item(0);
    if ($nextPage) {
        $nextPageURL = $nextPage->getAttribute('href');
        fetch_posts($nextPageURL);  // Recursively call fetch_posts with the new URL
    }
}

// Start fetching from the first page
fetch_posts('https://coastregionpressclub.blogspot.com/');