PHP Luminova: Website Sitemap & Broken Link Generator

-u,  --url              # Specify the starting URL to scan (default: value of `env(dev.app.start.url)`).
-f,  --basename         # Set the output filename (default: `sitemap.xml` or `broken.sitemap.json`).
-b,  --broken           # Scan and generate a JSON report of broken links instead of a sitemap. 
-t,  --link-tree        # Generate a TXT report of website links instead of an XML sitemap or JSON broken links.
--format                # Custom output format for link tree, e.g., "{url} | {title} | {status} | {lastmod}". Default: "{url} {title} ({status})"
-l,  --limit            # Limit the number of URLs to scan (0 = no limit).   
-d,  --delay            # Delay in seconds between scans (minimum: 1).
-e,  --max-execution    # Maximum script execution time in seconds (0 = unlimited).
-p,  --prefix           # Restrict scan to URLs matching a specific prefix.
-c,  --change           # Set the expected change frequency (always, daily, weekly, etc.).
-s,  --html             # Include static `.html` versions of URLs in the sitemap. 
-v,  --verbose          # Control output verbosity (use `-v` multiple times for more detail). 
-n,  --dry-run          # Perform a full scan without writing any output files.
-a,  --ignore-assets    # Ignore URLs pointing to assets directories such as `/assets/` or `/public/assets/`.
-h,  --help             # Show help information for this command.

php novakit sitemap --help

/app/Config/Sitemap.php

php novakit sitemap

# Run sitemap generation every 2 days at 5:00 AM
0 5 */2 * * flock -n /tmp/task.lock /usr/bin/php /path/to/project/novakit sitemap

// app/Tasks/TaskQueue.php
namespace App\Tasks;

use Luminova\Base\Queue;

class TaskQueue extends Queue 
{
    public function tasks(): ?array
    {
        return [
            [
                'handler'   => 'Luminova\Component\Seo\Sitemap::generate', // Method to execute
                'arguments' => [APP_URL],                        // Base URL of your site
                'priority'  => 5,                                // Lower = higher priority
                'forever'   => 2880                              // Run once every 2 days (in minutes)
            ]
        ];
    }
}

php novakit task:run

* * * * * /usr/bin/php /path/to/project/novakit task:run --flock-worker

// app/Console/SitemapCommand.php
namespace App\Console;

use Luminova\Base\Console as BaseConsole;
use Luminova\Component\Seo\Sitemap;
use Throwable;

class SitemapCommand extends BaseConsole
{
    protected string $name = 'Sitemap';

    // Avoid conflicts with Luminova's built-in sitemap command
    protected string $group = 'app-sitemap'; 

    protected function onCreate(): void
    {
        // Ensures CLI errors are not suppressed
        setenv('throw.cli.exceptions', 'true');
    }

    public function run(?array $options = []): int
    {
        $this->term->parse($options);
        $url = $this->term->getAnyOption('url', 'u', APP_URL);
        $command = trim($this->term->getCommand());

        if ($command !== 'generator') {
            return $this->term->oops($command);
        }

        try {
            if (Sitemap::generate($url, basename: 'sitemap.xml')) {
                $this->term->success('Sitemap was successfully generated.');
                return STATUS_SUCCESS; 
            }
            $this->term->error('Failed to generate sitemap.');
        } catch (Throwable $e) {
            $this->term->error('Error generating sitemap: ' . $e->getMessage());
        }

        return STATUS_ERROR;
    }
}

// bin/.novakit-console.php
use Luminova\Command\Novakit;
use App\Console\SitemapCommand;

Novakit::command('app-sitemap', SitemapCommand::class);

php novakit app-sitemap generator --url=https://example.com

// /app/Controllers/Cli/SitemapCommand.php

namespace App\Controllers\Cli;

use Luminova\Base\Command;
use Luminova\Component\Seo\Sitemap;
use Luminova\Attributes\Group;
use Luminova\Attributes\Route;
use Throwable;

#[Group('sitemap')]
class SitemapCommand extends Command
{
    /** @var string $group Group name */
    protected string $group = 'sitemap';

    protected function onCreate(): void
    {
        // Ensure CLI exceptions are thrown
        setenv('throw.cli.exceptions', 'true'); 
    }

    /**
     * Generates the sitemap for the website.
     *
     * @return int Status code: STATUS_SUCCESS or STATUS_ERROR
     */
    #[Route('generator', group: 'sitemap')]
    public function generator(): int 
    {
        try {
            $url = $this->getAnyOption('url', 'u', APP_URL);

            if (Sitemap::generate($url, basename: 'sitemap.xml')) {
                $this->success('Sitemap was successfully generated.');
                return STATUS_SUCCESS; 
            }

            $this->error('Failed to generate sitemap.');
        } catch (Throwable $e) {
            $this->error('Error generating sitemap: ' . $e->getMessage());
        }

        return STATUS_ERROR;
    }
}

php index.php sitemap --url=https://example.com

public static generate(
    ?string $url = null, 
    Terminal|LazyObjectInterface|null $term = null, 
    string $basename = 'sitemap.xml',
    ?App\Config\Sitemap<Luminova\Base\Configuration> $config = null,
    array<string,mixed> $options = []
): bool

bool isBroken       // Generate broken-link report instead of sitemap. Default false.
int  verbose        // Output verbosity level (0-3). Default 3.
bool isDryRun       // Simulate run without writing output. Default false.
bool ignoreAssets   // Skip assets like images, CSS, and JS. Default true.

use Luminova\Component\Seo\Sitemap;
use Luminova\Command\Terminal;
Sitemap::generate(
    url: 'https://example.com',
    term: new Terminal(),
    basename: 'sitemap.xml'
);

use Luminova\Component\Seo\Sitemap;
use Luminova\Command\Terminal;

Sitemap::generate(
    url: 'https://example.com',
    term: new Terminal(),
    basename: 'broken.sitemap.json',
    options: ['isBroken' => true]
);