PHP code example of iprodev / sitemap-generator-pro

    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

    

iprodev / sitemap-generator-pro example snippets

use IProDev\Sitemap\Scheduler\CronScheduler;

$scheduler = new CronScheduler();
$scheduler->addSchedule('daily-crawl', [
    'url' => 'https://example.com',
    'schedule' => 'daily',  // or cron: '0 2 * * *'
    'out' => './sitemaps',
    'db_enabled' => true
]);

// Add to crontab:
// * * * * * php bin/scheduler

use IProDev\Sitemap\Fetcher;
use IProDev\Sitemap\Crawler;
use IProDev\Sitemap\SitemapWriter;
use IProDev\Sitemap\RobotsTxt;

$fetcher = new Fetcher(['concurrency' => 20]);
$robots = RobotsTxt::fromUrl('https://example.com', $fetcher);
$crawler = new Crawler($fetcher, $robots);

$pages = $crawler->crawl('https://example.com', 10000, 5);
$files = SitemapWriter::write($pages, './sitemaps');

use IProDev\Sitemap\Database\Database;
use IProDev\Sitemap\ChangeDetector;

// Initialize database
$db = new Database('sqlite:./sitemap.db');
$db->createTables();

// Start crawl
$domain = 'example.com';
$crawlId = $db->startCrawl($domain, 'https://example.com', []);

// Crawl and save
foreach ($pages as $page) {
    $db->saveUrl($crawlId, $page);
}

// Detect changes
$prevCrawl = $db->getPreviousCrawl($domain, $crawlId);
if ($prevCrawl) {
    $detector = new ChangeDetector($db);
    $changes = $detector->detectChanges($prevCrawl['id'], $crawlId);
    
    print_r($changes);
}

use IProDev\Sitemap\Analyzer\SeoAnalyzer;

$analyzer = new SeoAnalyzer();

foreach ($pages as $page) {
    $analysis = $analyzer->analyze(
        $page['url'], 
        $page['html'], 
        $page['status_code']
    );
    
    echo "Score: {$analysis['score']}/100\n";
    echo "Issues: " . count($analysis['issues']) . "\n";
}

use IProDev\Sitemap\Cache\FileCache;
use IProDev\Sitemap\Cache\RedisCache;

// File cache
$cache = new FileCache('./cache', 3600);

// Redis cache
$cache = new RedisCache('127.0.0.1', 6379);

// Use in fetcher
$fetcher = new Fetcher(['cache' => $cache]);

return [
    'url' => 'https://example.com',
    'out' => './sitemaps',
    'concurrency' => 20,
    'max_pages' => 10000,
    'max_depth' => 5,
    'cache_enabled' => true,
    'db_enabled' => true,
    'seo_analysis' => true,
    'exclude' => ['/admin/*', '/test/*'],
    'priority_rules' => [
        'homepage' => 1.0,
        '/products/*' => 0.8,
        '/blog/*' => 0.6
    ]
];

use IProDev\Sitemap\Fetcher;
use IProDev\Sitemap\Crawler;
use IProDev\Sitemap\SitemapWriter;
use IProDev\Sitemap\RobotsTxt;

$fetcher = new Fetcher(['concurrency' => 10]);
$robots = RobotsTxt::fromUrl('https://example.com', $fetcher);
$crawler = new Crawler($fetcher, $robots);

$pages = $crawler->crawl('https://example.com', 1000, 3);
SitemapWriter::write($pages, './output');

// In code, configure Guzzle to skip verification (not recommended for production)
$fetcher = new Fetcher(['verify' => false]);

bash
php bin/sitemap --url=https://www.example.com

bash
php bin/sitemap --interactive

bash
php bin/sitemap \
  --url=https://example.com \
  --webhook-url=https://example.com/webhook \
  --notify-on-complete \
  --notify-on-error

bash
# Single proxy
php bin/sitemap \
  --url=https://example.com \
  --proxy=http://proxy.example.com:8080

# Proxy file with rotation
php bin/sitemap \
  --url=https://example.com \
  --proxy-file=./proxies.txt \
  --rotate-proxies

bash
php bin/sitemap \
  --url=https://example.com \
  --exclude="/admin/*,/test/*,*.pdf" \
  --

bash
php bin/sitemap --config=sitemap.config.php

bash
php examples/comprehensive.php

bash
# Increase PHP memory limit
php -d memory_limit=512M bin/sitemap --url=https://example.com

bash
# Reduce concurrency
php bin/sitemap --url=https://example.com --concurrency=5

bash
# Enable rate limiting
php bin/sitemap --url=https://example.com --rate-limit=30 --delay=1000

bash
php bin/sitemap --url=https://example.com --verbose