JezK
Edit File: crawler.cls.php
<?php /** * The crawler class. * * @package LiteSpeed * @since 1.1.0 */ namespace LiteSpeed; defined( 'WPINC' ) || exit(); /** * Handles sitemap crawling, blacklisting, and async operations. */ class Crawler extends Root { const LOG_TAG = '🕸️'; const TYPE_REFRESH_MAP = 'refresh_map'; const TYPE_EMPTY = 'empty'; const TYPE_BLACKLIST_EMPTY = 'blacklist_empty'; const TYPE_BLACKLIST_DEL = 'blacklist_del'; const TYPE_BLACKLIST_ADD = 'blacklist_add'; const TYPE_START = 'start'; const TYPE_RESET = 'reset'; const USER_AGENT = 'lscache_walker'; const FAST_USER_AGENT = 'lscache_runner'; const CHUNKS = 10000; const STATUS_WAIT = 'W'; const STATUS_HIT = 'H'; const STATUS_MISS = 'M'; const STATUS_BLACKLIST = 'B'; const STATUS_NOCACHE = 'N'; // Number of consecutive crawl failures before a URL is given up (dropped from the sitemap). const BLACKLIST_THRESHOLD = 3; /** * Sitemeta file slug. * * @var string */ private $_sitemeta = 'meta.data'; /** * Reset file full path. * * @var string */ private $_resetfile; /** * Reason that ended current run. * * @var string */ private $_end_reason; /** * Number of CPU cores. * * @var int */ private $_ncpu = 1; /** * Server IP set in settings. * * @var string|null */ private $_server_ip; /** * Crawler configuration. * * @var array */ private $_crawler_conf = [ 'cookies' => [], 'headers' => [], 'ua' => '', ]; /** * Built crawler variants. * * @var array<int,array> */ private $_crawlers = []; /** * Current allowed worker threads. * * @var int */ private $_cur_threads = -1; /** * Max timestamp to run until. * * @var int */ private $_max_run_time; /** * Last time threads were adjusted. * * @var int */ private $_cur_thread_time; /** * Map-status list to batch-save. * * @var array */ private $_map_status_list = [ 'H' => [], 'M' => [], 'B' => [], 'N' => [], ]; /** * Initialize crawler, assign sitemap path. * * @since 1.1.0 */ public function __construct() { if ( is_multisite() ) { $this->_sitemeta = 'meta' . get_current_blog_id() . '.data'; } $this->_resetfile = LITESPEED_STATIC_DIR . '/crawler/' . $this->_sitemeta . '.reset'; $this->_summary = self::get_summary(); $this->_ncpu = $this->_get_server_cpu(); $this->_server_ip = $this->conf( Base::O_SERVER_IP ); self::debug( 'Init w/ CPU cores=' . $this->_ncpu ); } /** * Try get server CPUs. * * @since 5.2 * @return int Number of cores detected. */ private function _get_server_cpu() { $cpuinfo_file = '/proc/cpuinfo'; $setting_open_dir = ini_get( 'open_basedir' ); if ( $setting_open_dir ) { return 1; // Server has limit. } try { // phpcs:ignore WordPress.PHP.NoSilencedErrors.Discouraged if (!@is_file($cpuinfo_file)) { return 1; } } catch ( \Exception $e ) { return 1; } // Local system read; no WP alternative. Suppress sniff. // phpcs:ignore WordPress.WP.AlternativeFunctions.file_get_contents_file_get_contents $cpuinfo = file_get_contents( $cpuinfo_file ); preg_match_all( '/^processor/m', $cpuinfo, $matches ); $cnt = isset( $matches[0] ) ? count( $matches[0] ) : 0; return $cnt ? $cnt : 1; } /** * Check whether the current crawler is active. * * @since 4.3 * @param int $curr Crawler index. * @return bool Active state. */ public function is_active( $curr ) { $bypass_list = self::get_option( 'bypass_list', [] ); return ! in_array( (int) $curr, $bypass_list, true ); } /** * Toggle the current crawler's active state and return the updated state. * * @since 4.3 * @param int $curr Crawler index. * @return bool True if turned on, false if turned off. */ public function toggle_activeness( $curr ) { $bypass_list = self::get_option( 'bypass_list', [] ); if ( in_array( (int) $curr, $bypass_list, true ) ) { // Remove it. $key = array_search( (int) $curr, $bypass_list, true ); if ( false !== $key ) { unset( $bypass_list[ $key ] ); $bypass_list = array_values( $bypass_list ); self::update_option( 'bypass_list', $bypass_list ); } return true; } // Add it. $bypass_list[] = (int) $curr; self::update_option( 'bypass_list', $bypass_list ); return false; } /** * Clear bypassed list. * * @since 4.3 * @access public * @return void */ public function clear_disabled_list() { self::update_option( 'bypass_list', [] ); $msg = __( 'Crawler disabled list is cleared! All crawlers are set to active! ', 'litespeed-cache' ); Admin_Display::note( $msg ); self::debug( 'All crawlers are set to active...... ' ); } /** * Overwrite get_summary to init elements. * * @since 3.0 * @access public * * @param string|false $field Field name to fetch or false to get all. * @return mixed Summary value/array or null if not found. */ public static function get_summary( $field = false ) { $_default = [ 'list_size' => 0, 'last_update_time' => 0, 'curr_crawler' => 0, 'curr_crawler_beginning_time' => 0, 'last_pos' => 0, 'last_count' => 0, 'last_crawled' => 0, 'last_start_time' => 0, 'last_status' => '', 'is_running' => 0, 'end_reason' => '', 'meta_save_time' => 0, 'pos_reset_check' => 0, 'done' => 0, 'this_full_beginning_time' => 0, 'last_full_time_cost' => 0, 'last_crawler_total_cost' => 0, 'crawler_stats' => [], // this will store all crawlers hit/miss crawl status. ]; wp_cache_delete( 'alloptions', 'options' ); // ensure the summary is current. $summary = parent::get_summary(); $summary = array_merge( $_default, $summary ); if ( false === $field ) { return $summary; } if ( array_key_exists( $field, $summary ) ) { return $summary[ $field ]; } return null; } /** * Overwrite save_summary. * * @since 3.0 * @access public * * @param array|false $data Data to save or false to save current. * @param bool $reload Whether to reload after saving. * @param bool $overwrite Whether to overwrite completely. * @return void */ public static function save_summary( $data = false, $reload = false, $overwrite = false ) { $instance = self::cls(); $instance->_summary['meta_save_time'] = time(); if ( false === $data ) { $data = $instance->_summary; } parent::save_summary( $data, $reload, $overwrite ); File::save( LITESPEED_STATIC_DIR . '/crawler/' . $instance->_sitemeta, wp_json_encode( $data ), true ); } /** * Cron start async crawling. * * @since 5.5 * @return void */ public static function start_async_cron() { Task::async_call( 'crawler' ); } /** * Manually start async crawling. * * @since 5.5 * @return void */ public static function start_async() { Task::async_call( 'crawler_force' ); $msg = __( 'Started async crawling', 'litespeed-cache' ); Admin_Display::success( $msg ); } /** * Ajax crawl handler. * * @since 5.5 * @param bool $manually_run Whether manually triggered. * @return void */ public static function async_handler( $manually_run = false ) { self::debug( '------------async-------------start_async_handler' ); self::start( (bool) $manually_run ); } /** * Proceed crawling. * * @since 1.1.0 * @access public * * @param bool $manually_run Whether manually triggered. * @return bool|void */ public static function start( $manually_run = false ) { if ( ! Router::can_crawl() ) { self::debug( '......crawler is NOT allowed by the server admin......' ); return false; } if ( $manually_run ) { self::debug( '......crawler manually ran......' ); } self::cls()->_crawl_data( (bool) $manually_run ); } /** * Crawling start. * * @since 1.1.0 * @access private * * @param bool $manually_run Whether manually triggered. * @return void */ private function _crawl_data( $manually_run ) { if ( ! defined( 'LITESPEED_LANE_HASH' ) ) { define( 'LITESPEED_LANE_HASH', Str::rrand( 8 ) ); } if ( $this->_check_valid_lane() ) { $this->_take_over_lane(); } else { self::debug( '⚠️ lane in use' ); return; } self::debug( '......crawler started......' ); // for the first time running. if ( ! $this->_summary || ! Data::cls()->tb_exist( 'crawler' ) || ! Data::cls()->tb_exist( 'crawler_blacklist' ) ) { $this->cls( 'Crawler_Map' )->gen(); } // if finished last time, regenerate sitemap. if ( 'touchedEnd' === $this->_summary['done'] ) { // check whole crawling interval. $last_finished_at = (int) $this->_summary['last_full_time_cost'] + (int) $this->_summary['this_full_beginning_time']; if ( ! $manually_run && ( time() - $last_finished_at ) < $this->conf( Base::O_CRAWLER_CRAWL_INTERVAL ) ) { self::debug( 'Cron abort: cache warmed already.' ); $this->Release_lane(); return; } self::debug( 'TouchedEnd. regenerate sitemap....' ); $this->cls( 'Crawler_Map' )->gen(); } $crawlers = $this->list_crawlers(); $crawlers_count = count( $crawlers ); // Skip the crawlers that in bypassed list. while ( ! $this->is_active( $this->_summary['curr_crawler'] ) && $this->_summary['curr_crawler'] < $crawlers_count ) { self::debug( 'Skipped the Crawler #' . $this->_summary['curr_crawler'] . ' ......' ); $this->_summary['curr_crawler'] = (int) $this->_summary['curr_crawler'] + 1; } if ( $this->_summary['curr_crawler'] >= $crawlers_count ) { $this->_end_reason = 'end'; $this->_terminate_running(); $this->Release_lane(); return; } // In case crawlers are all done but not reload, reload it. if ( empty( $this->_summary['curr_crawler'] ) || empty( $this->_crawlers[ $this->_summary['curr_crawler'] ] ) ) { $this->_summary['curr_crawler'] = 0; $this->_summary['crawler_stats'][ $this->_summary['curr_crawler'] ] = []; } $res = $this->load_conf(); if ( ! $res ) { self::debug( 'Load conf failed' ); $this->_terminate_running(); $this->Release_lane(); return; } try { $this->_engine_start(); $this->Release_lane(); } catch ( \Exception $e ) { self::debug( '🛑 ' . $e->getMessage() ); } } /** * Load conf before running crawler. * * @since 3.0 * @access private * @return bool True on success. */ private function load_conf() { $this->_crawler_conf['base'] = site_url(); $current_crawler = $this->_crawlers[ $this->_summary['curr_crawler'] ]; // Cookies. foreach ( $current_crawler as $k => $v ) { if ( 0 !== strpos( $k, 'cookie:' ) ) { continue; } if ( '_null' === $v ) { continue; } $this->_crawler_conf['cookies'][ substr( $k, 7 ) ] = $v; } // WebP/AVIF simulation. if ( ! empty( $current_crawler['webp'] ) ) { $this->_crawler_conf['headers'][] = 'Accept: image/' . ( 2 === (int) $this->conf( Base::O_IMG_OPTM_WEBP ) ? 'avif' : 'webp' ) . ',*/*'; } // Mobile crawler. if ( ! empty( $current_crawler['mobile'] ) ) { $this->_crawler_conf['ua'] = 'Mobile iPhone'; } // Limit delay to use server setting. $this->_crawler_conf['run_delay'] = 500; // microseconds. if ( defined( 'LITESPEED_CRAWLER_USLEEP' ) && constant( 'LITESPEED_CRAWLER_USLEEP' ) > $this->_crawler_conf['run_delay'] ) { $this->_crawler_conf['run_delay'] = (int) constant( 'LITESPEED_CRAWLER_USLEEP' ); } if ( isset( $_SERVER[ Base::ENV_CRAWLER_USLEEP ] ) ) { $env_usleep = absint( wp_unslash( $_SERVER[ Base::ENV_CRAWLER_USLEEP ] ) ); if ( $env_usleep > (int) $this->_crawler_conf['run_delay'] ) { $this->_crawler_conf['run_delay'] = $env_usleep; } } $this->_crawler_conf['run_duration'] = $this->get_crawler_duration(); $this->_crawler_conf['load_limit'] = (int) $this->conf( Base::O_CRAWLER_LOAD_LIMIT ); if ( isset( $_SERVER[ Base::ENV_CRAWLER_LOAD_LIMIT_ENFORCE ] ) ) { $this->_crawler_conf['load_limit'] = absint( wp_unslash( $_SERVER[ Base::ENV_CRAWLER_LOAD_LIMIT_ENFORCE ] ) ); } elseif ( isset( $_SERVER[ Base::ENV_CRAWLER_LOAD_LIMIT ] ) ) { $env_limit = absint( wp_unslash( $_SERVER[ Base::ENV_CRAWLER_LOAD_LIMIT ] ) ); if ( $env_limit < (int) $this->_crawler_conf['load_limit'] ) { $this->_crawler_conf['load_limit'] = $env_limit; } } if ( 0 === (int) $this->_crawler_conf['load_limit'] ) { self::debug( '🛑 Terminated crawler due to load limit set to 0' ); return false; } // Role simulation. if ( ! empty( $current_crawler['uid'] ) ) { if ( empty( $this->_server_ip ) ) { self::debug( '🛑 Terminated crawler due to Server IP not set' ); return false; } $vary_name = $this->cls( 'Vary' )->get_vary_name(); $vary_val = $this->cls( 'Vary' )->finalize_default_vary( $current_crawler['uid'] ); $this->_crawler_conf['cookies'][ $vary_name ] = $vary_val; $this->_crawler_conf['cookies']['litespeed_hash'] = Router::cls()->get_hash( $current_crawler['uid'] ); } return true; } /** * Get crawler duration allowance. * * @since 7.0 * @return int Seconds. */ public function get_crawler_duration() { $run_duration = defined( 'LITESPEED_CRAWLER_DURATION' ) ? (int) constant( 'LITESPEED_CRAWLER_DURATION' ) : 900; if ( $run_duration > 900 ) { $run_duration = 900; // reset to default value if defined higher than 900 seconds. } return $run_duration; } /** * Start crawler. * * @since 1.1.0 * @access private * @return void */ private function _engine_start() { // check current load. $this->_adjust_current_threads(); if ( 0 === (int) $this->_cur_threads ) { $this->_end_reason = 'stopped_highload'; self::debug( 'Stopped due to heavy load.' ); return; } // log started time. self::save_summary( [ 'last_start_time' => time() ] ); // set time limit. $max_time = (int) ini_get( 'max_execution_time' ); self::debug( 'ini_get max_execution_time=' . $max_time ); if ( 0 === $max_time ) { $max_time = 300; // hardlimit. } else { $max_time -= 5; } if ( $max_time >= (int) $this->_crawler_conf['run_duration'] ) { $max_time = (int) $this->_crawler_conf['run_duration']; self::debug( 'Use run_duration setting as max_execution_time=' . $max_time ); // phpcs:ignore WordPress.PHP.IniSet.max_execution_time_Disallowed -- Required for crawler functionality. } elseif ( ini_set( 'max_execution_time', $this->_crawler_conf['run_duration'] + 15 ) !== false ) { $max_time = $this->_crawler_conf['run_duration']; self::debug( 'ini_set max_execution_time=' . $max_time ); } self::debug( 'final max_execution_time=' . $max_time ); $this->_max_run_time = $max_time + time(); // mark running. $this->_prepare_running(); // run crawler. $this->_do_running(); $this->_terminate_running(); } /** * Get server load. * * @since 5.5 * @return int Load or -1 if unsupported. */ public function get_server_load() { if ( ! function_exists( 'sys_getloadavg' ) ) { return -1; } $curload = sys_getloadavg(); $curload = (float) $curload[0]; self::debug( 'Server load: ' . $curload ); return $curload; } /** * Adjust threads dynamically. * * @since 1.1.0 * @access private * @return void */ private function _adjust_current_threads() { $curload = $this->get_server_load(); if ( -1 === (int) $curload ) { self::debug( 'set threads=0 due to func sys_getloadavg not exist!' ); $this->_cur_threads = 0; return; } $curload /= (float) $this->_ncpu; $crawler_threads = defined( 'LITESPEED_CRAWLER_THREADS' ) ? (int) constant( 'LITESPEED_CRAWLER_THREADS' ) : 3; $load_limit = (float) $this->_crawler_conf['load_limit']; $current_threads = (int) $this->_cur_threads; if ( -1 === $current_threads ) { // init. if ( $curload > $load_limit ) { $curthreads = 0; } elseif ( $curload >= ( $load_limit - 1 ) ) { $curthreads = 1; } else { $curthreads = (int) ( $load_limit - $curload ); if ( $curthreads > $crawler_threads ) { $curthreads = $crawler_threads; } } } else { // adjust. $curthreads = $current_threads; if ( $curload >= ( $load_limit + 1 ) ) { sleep( 5 ); // sleep 5 secs. if ( $curthreads >= 1 ) { --$curthreads; } } elseif ( $curload >= $load_limit ) { --$curthreads; } elseif ( ( $curload + 1 ) < $load_limit ) { if ( $curthreads < $crawler_threads ) { ++$curthreads; } } } $this->_cur_threads = (int) $curthreads; $this->_cur_thread_time = time(); } /** * Mark running status. * * @since 1.1.0 * @access private * @return void */ private function _prepare_running() { $this->_summary['is_running'] = time(); $this->_summary['done'] = 0; // reset done status. $this->_summary['last_status'] = 'prepare running'; $this->_summary['last_crawled'] = 0; // Current crawler starttime mark. if ( 0 === (int) $this->_summary['last_pos'] ) { $this->_summary['curr_crawler_beginning_time'] = time(); } if ( 0 === (int) $this->_summary['curr_crawler'] && 0 === (int) $this->_summary['last_pos'] ) { $this->_summary['this_full_beginning_time'] = time(); $this->_summary['list_size'] = $this->cls( 'Crawler_Map' )->count_map(); } if ( 'end' === $this->_summary['end_reason'] && 0 === (int) $this->_summary['last_pos'] ) { $this->_summary['crawler_stats'][ $this->_summary['curr_crawler'] ] = []; } self::save_summary(); } /** * Take over lane. * * @since 6.1 * @return void */ private function _take_over_lane() { self::debug( 'Take over lane as lane is free: ' . $this->json_local_path() . '.pid' ); File::save( $this->json_local_path() . '.pid', LITESPEED_LANE_HASH ); } /** * Update lane file mtime. * * @since 6.1 * @return void */ private function _touch_lane() { // phpcs:ignore WordPress.WP.AlternativeFunctions.file_system_operations_touch touch( $this->json_local_path() . '.pid' ); } /** * Release lane file. * * @since 6.1 * @return void */ public function Release_lane() { $lane_file = $this->json_local_path() . '.pid'; if ( ! file_exists( $lane_file ) ) { return; } self::debug( 'Release lane' ); // phpcs:ignore WordPress.WP.AlternativeFunctions.unlink_unlink unlink( $lane_file ); } /** * Check if lane is used by other crawlers. * * @since 6.1 * @param bool $strict_mode Strict check that file must exist. * @return bool True if valid lane. */ private function _check_valid_lane( $strict_mode = false ) { $lane_file = $this->json_local_path() . '.pid'; if ( $strict_mode ) { if ( ! file_exists( $lane_file ) ) { self::debug( 'lane file not existed, strict mode is false [file] ' . $lane_file ); return false; } } $pid = File::read( $lane_file ); if ( $pid && LITESPEED_LANE_HASH !== $pid ) { // If lane file is older than 1h, ignore. if ( ( time() - filemtime( $lane_file ) ) > 3600 ) { self::debug( 'Lane file is older than 1h, releasing lane' ); $this->Release_lane(); return true; } return false; } return true; } /** * Test port for simulator. * * @since 7.0 * @access private * @return bool true if success and can continue crawling, false otherwise. */ private function _test_port() { if ( empty( $this->_server_ip ) ) { if ( empty( $this->_crawlers[ $this->_summary['curr_crawler'] ]['uid'] ) ) { self::debug( 'Bypass test port as Server IP is not set' ); return true; } self::debug( '❌ Server IP not set' ); return false; } if ( defined( 'LITESPEED_CRAWLER_LOCAL_PORT' ) ) { self::debug( '✅ LITESPEED_CRAWLER_LOCAL_PORT already defined' ); return true; } // Don't repeat testing in 120s. if ( ! empty( $this->_summary['test_port_tts'] ) && ( time() - (int) $this->_summary['test_port_tts'] ) < 120 ) { if ( ! empty( $this->_summary['test_port'] ) ) { self::debug( '✅ Use tested local port: ' . $this->_summary['test_port'] ); define( 'LITESPEED_CRAWLER_LOCAL_PORT', (int) $this->_summary['test_port'] ); return true; } return false; } $this->_summary['test_port_tts'] = time(); self::save_summary(); $options = $this->_get_curl_options(); $home = home_url(); File::save( LITESPEED_STATIC_DIR . '/crawler/test_port.html', $home, true ); $url = LITESPEED_STATIC_URL . '/crawler/test_port.html'; $parsed_url = wp_parse_url( $url ); if ( empty( $parsed_url['host'] ) ) { self::debug( '❌ Test port failed, invalid URL: ' . $url ); return false; } $resolved = $parsed_url['host'] . ':443:' . $this->_server_ip; $options[ CURLOPT_RESOLVE ] = [ $resolved ]; $options[ CURLOPT_DNS_USE_GLOBAL_CACHE ] = false; $options[ CURLOPT_HEADER ] = false; self::debug( 'Test local 443 port for ' . $resolved ); // cURL is intentionally used for speed; suppress sniffs in this method. // phpcs:disable WordPress.WP.AlternativeFunctions $ch = curl_init(); curl_setopt_array( $ch, $options ); curl_setopt( $ch, CURLOPT_URL, $url ); $result = curl_exec( $ch ); $test_result = false; if ( curl_errno( $ch ) || $result !== $home ) { if ( curl_errno( $ch ) ) { self::debug( '❌ Test port curl error: [errNo] ' . curl_errno( $ch ) . ' [err] ' . curl_error( $ch ) ); } elseif ( $result !== $home ) { self::debug( '❌ Test port response is wrong: ' . $result ); } self::debug( '❌ Test local 443 port failed, try port 80' ); // Try port 80. $resolved = $parsed_url['host'] . ':80:' . $this->_server_ip; $options[ CURLOPT_RESOLVE ] = [ $resolved ]; $url = str_replace( 'https://', 'http://', $url ); if ( empty( $options[ CURLOPT_HTTPHEADER ] ) || ! in_array( 'X-Forwarded-Proto: https', $options[ CURLOPT_HTTPHEADER ], true ) ) { $options[ CURLOPT_HTTPHEADER ][] = 'X-Forwarded-Proto: https'; } $ch = curl_init(); curl_setopt_array( $ch, $options ); curl_setopt( $ch, CURLOPT_URL, $url ); $result = curl_exec( $ch ); if ( curl_errno( $ch ) ) { self::debug( '❌ Test port curl error: [errNo] ' . curl_errno( $ch ) . ' [err] ' . curl_error( $ch ) ); } elseif ( $result !== $home ) { self::debug( '❌ Test port response is wrong: ' . $result ); } else { self::debug( '✅ Test local 80 port successfully' ); define( 'LITESPEED_CRAWLER_LOCAL_PORT', 80 ); $this->_summary['test_port'] = 80; $test_result = true; } } else { self::debug( '✅ Tested local 443 port successfully' ); define( 'LITESPEED_CRAWLER_LOCAL_PORT', 443 ); $this->_summary['test_port'] = 443; $test_result = true; } self::save_summary(); unset( $ch ); // phpcs:enable return $test_result; } /** * Run crawler. * * @since 1.1.0 * @access private * @return void * @throws \Exception When lane becomes invalid during run. */ private function _do_running() { $options = $this->_get_curl_options( true ); // If is role simulator and not defined local port, check port once. $test_result = $this->_test_port(); if ( ! $test_result ) { $this->_end_reason = 'port_test_failed'; self::debug( '❌ Test port failed, crawler stopped.' ); return; } while ( true ) { $url_chunks = $this->cls( 'Crawler_Map' )->list_map( self::CHUNKS, $this->_summary['last_pos'] ); if ( empty( $url_chunks ) ) { break; } $url_chunks = array_chunk( $url_chunks, (int) $this->_cur_threads ); foreach ( $url_chunks as $rows ) { if ( ! $this->_check_valid_lane( true ) ) { $this->_end_reason = 'lane_invalid'; self::debug( '🛑 The crawler lane is used by newer crawler.' ); throw new \Exception( 'invalid crawler lane' ); } // Update time. $this->_touch_lane(); // multi curl. $rets = $this->_multi_request( $rows, $options ); // check result headers. foreach ( $rows as $row ) { if ( empty( $rets[ $row['id'] ] ) ) { continue; } if ( 428 === (int) $rets[ $row['id'] ]['code'] ) { // HTTP/1.1 428 Precondition Required (need to test) $this->_end_reason = 'crawler_disabled'; self::debug( 'crawler_disabled' ); return; } $status = $this->_status_parse( $rets[ $row['id'] ]['header'], $rets[ $row['id'] ]['code'], $row['url'] ); // B or H or M or N(nocache). self::debug( '[status] ' . $this->_status2title( $status ) . "\t\t [url] " . $row['url'] ); $this->_map_status_list[ $status ][ $row['id'] ] = [ 'url' => $row['url'], 'code' => (int) $rets[ $row['id'] ]['code'], // 201 or 200 or 404. ]; if ( empty( $this->_summary['crawler_stats'][ $this->_summary['curr_crawler'] ][ $status ] ) ) { $this->_summary['crawler_stats'][ $this->_summary['curr_crawler'] ][ $status ] = 0; } ++$this->_summary['crawler_stats'][ $this->_summary['curr_crawler'] ][ $status ]; } // update offset position. $_time = time(); $this->_summary['last_count'] = count( $rows ); $this->_summary['last_pos'] += $this->_summary['last_count']; $this->_summary['last_crawled'] += $this->_summary['last_count']; $this->_summary['last_update_time'] = $_time; $this->_summary['last_status'] = 'updated position'; // check duration. if ( $this->_summary['last_update_time'] > $this->_max_run_time ) { $this->_end_reason = 'stopped_maxtime'; self::debug( 'Terminated due to maxtime' ); return; } // make sure at least each 10s save meta & map status once. if ( $_time - $this->_summary['meta_save_time'] > 10 ) { $this->_map_status_list = $this->cls( 'Crawler_Map' )->save_map_status( $this->_map_status_list, $this->_summary['curr_crawler'] ); self::save_summary(); } // check if need to reset pos each 5s. if ( $_time > $this->_summary['pos_reset_check'] ) { $this->_summary['pos_reset_check'] = $_time + 5; if ( file_exists( $this->_resetfile ) && unlink( $this->_resetfile ) ) { // phpcs:ignore WordPress.WP.AlternativeFunctions.unlink_unlink self::debug( 'Terminated due to reset file' ); $this->_summary['last_pos'] = 0; $this->_summary['curr_crawler'] = 0; $this->_summary['crawler_stats'][ $this->_summary['curr_crawler'] ] = []; // reset done status. $this->_summary['done'] = 0; $this->_summary['this_full_beginning_time'] = 0; $this->_end_reason = 'stopped_reset'; return; } } // check loads. if ( ( $this->_summary['last_update_time'] - $this->_cur_thread_time ) > 60 ) { $this->_adjust_current_threads(); if ( 0 === (int) $this->_cur_threads ) { $this->_end_reason = 'stopped_highload'; self::debug( '🛑 Terminated due to highload' ); return; } } $this->_summary['last_status'] = 'sleeping ' . (int) $this->_crawler_conf['run_delay'] . 'ms'; usleep( (int) $this->_crawler_conf['run_delay'] ); } } // All URLs are done for current crawler. $this->_end_reason = 'end'; $this->_summary['crawler_stats'][ $this->_summary['curr_crawler'] ]['W'] = 0; self::debug( 'Crawler #' . $this->_summary['curr_crawler'] . ' touched end' ); } /** * If need to resolve DNS or not. * * @since 7.3.0.1 * @return bool */ private function _should_force_resolve_dns() { if ( ! empty( $this->_server_ip ) ) { return true; } if ( ! empty( $this->_crawler_conf['cookies'] ) && ! empty( $this->_crawler_conf['cookies']['litespeed_hash'] ) ) { return true; } return false; } /** * Send multi curl requests. * If res=B/N, bypass request and won't return. * * @since 1.1.0 * @access private * * @param array<int,array<string,mixed>> $rows Rows to crawl. * @param array $options cURL options. * @return array<int,array{header:string,code:int}> */ private function _multi_request( $rows, $options ) { if ( ! function_exists( 'curl_multi_init' ) ) { exit( 'curl_multi_init disabled' ); } // phpcs:disable WordPress.WP.AlternativeFunctions $mh = curl_multi_init(); $crawler_drop_domain = defined( 'LITESPEED_CRAWLER_DROP_DOMAIN' ) ? (bool) constant( 'LITESPEED_CRAWLER_DROP_DOMAIN' ) : false; $curls = []; foreach ( $rows as $row ) { if ( self::STATUS_BLACKLIST === substr( $row['res'], $this->_summary['curr_crawler'], 1 ) ) { continue; } if ( self::STATUS_NOCACHE === substr( $row['res'], $this->_summary['curr_crawler'], 1 ) ) { continue; } if (!function_exists('curl_init')) { exit('curl_init disabled'); } $curls[$row['id']] = curl_init(); // Append URL. $url = $row['url']; if ( $crawler_drop_domain ) { $url = $this->_crawler_conf['base'] . $row['url']; } // IP resolve. if ( $this->_should_force_resolve_dns() ) { $parsed_url = wp_parse_url( $url ); if ( ! empty( $parsed_url['host'] ) ) { $dom = $parsed_url['host']; $port = defined( 'LITESPEED_CRAWLER_LOCAL_PORT' ) ? (int) LITESPEED_CRAWLER_LOCAL_PORT : 443; $resolved = $dom . ':' . $port . ':' . $this->_server_ip; $options[ CURLOPT_RESOLVE ] = [ $resolved ]; $options[ CURLOPT_DNS_USE_GLOBAL_CACHE ] = false; if ( 80 === $port ) { $url = str_replace( 'https://', 'http://', $url ); if ( empty( $options[ CURLOPT_HTTPHEADER ] ) || ! in_array( 'X-Forwarded-Proto: https', $options[ CURLOPT_HTTPHEADER ], true ) ) { $options[ CURLOPT_HTTPHEADER ][] = 'X-Forwarded-Proto: https'; } } self::debug( 'Resolved DNS for ' . $resolved ); } } curl_setopt( $curls[ $row['id'] ], CURLOPT_URL, $url ); self::debug( 'Crawling [url] ' . $url . ( $url === $row['url'] ? '' : ' [ori] ' . $row['url'] ) ); curl_setopt_array( $curls[ $row['id'] ], $options ); curl_multi_add_handle( $mh, $curls[ $row['id'] ] ); } // execute curl. if ( $curls ) { do { $status = curl_multi_exec( $mh, $active ); if ( $active ) { curl_multi_select( $mh ); } } while ( $active && CURLM_OK === $status ); } // curl done. $ret = []; foreach ( $rows as $row ) { if ( self::STATUS_BLACKLIST === substr( $row['res'], $this->_summary['curr_crawler'], 1 ) ) { continue; } if ( self::STATUS_NOCACHE === substr( $row['res'], $this->_summary['curr_crawler'], 1 ) ) { continue; } $ch = $curls[ $row['id'] ]; // Parse header. $header_size = curl_getinfo( $ch, CURLINFO_HEADER_SIZE ); $content = curl_multi_getcontent( $ch ); $header = substr( $content, 0, $header_size ); $ret[ $row['id'] ] = [ 'header' => $header, 'code' => (int) curl_getinfo( $ch, CURLINFO_HTTP_CODE ), ]; curl_multi_remove_handle( $mh, $ch ); unset( $ch ); } curl_multi_close( $mh ); // phpcs:enable return $ret; } /** * Translate the status to title. * * @since 6.0 * @param string $status Status char. * @return string Human title. */ private function _status2title( $status ) { if ( self::STATUS_HIT === $status ) { return '✅ Hit'; } if ( self::STATUS_MISS === $status ) { return '😊 Miss'; } if ( self::STATUS_BLACKLIST === $status ) { return '😅 Blacklisted'; } if ( self::STATUS_NOCACHE === $status ) { return '😅 Blacklisted'; } return '🛸 Unknown'; } /** * Check returned curl header to find if cached or not. * * @since 2.0 * @access private * * @param string $header Response header. * @param int $code HTTP code. * @param string $url URL. * @return string One of status chars. */ private function _status_parse( $header, $code, $url ) { if ( 201 === (int) $code ) { return self::STATUS_HIT; } if ( false !== stripos( $header, 'X-Litespeed-Cache-Control: no-cache' ) ) { // If is from DIVI, taken as miss. if ( defined( 'LITESPEED_CRAWLER_IGNORE_NONCACHEABLE' ) && constant( 'LITESPEED_CRAWLER_IGNORE_NONCACHEABLE' ) ) { return self::STATUS_MISS; } // If blacklist is disabled. if ( ( defined( 'LITESPEED_CRAWLER_DISABLE_BLOCKLIST' ) && constant( 'LITESPEED_CRAWLER_DISABLE_BLOCKLIST' ) ) || apply_filters( 'litespeed_crawler_disable_blocklist', false, $url ) ) { return self::STATUS_MISS; } return self::STATUS_NOCACHE; // Blacklist. } $_cache_headers = [ 'x-litespeed-cache', 'x-qc-cache', 'x-lsadc-cache' ]; foreach ( $_cache_headers as $_header ) { if ( false !== stripos( $header, $_header ) ) { if ( false !== stripos( $header, $_header . ': bkn' ) ) { return self::STATUS_HIT; // Hit. } if ( false !== stripos( $header, $_header . ': miss' ) ) { return self::STATUS_MISS; // Miss. } return self::STATUS_HIT; // Hit. } } // If blacklist is disabled. if ( ( defined( 'LITESPEED_CRAWLER_DISABLE_BLOCKLIST' ) && constant( 'LITESPEED_CRAWLER_DISABLE_BLOCKLIST' ) ) || apply_filters( 'litespeed_crawler_disable_blocklist', false, $url ) ) { return self::STATUS_MISS; } return self::STATUS_BLACKLIST; // Blacklist. } /** * Get curl options. * * @since 1.1.0 * @access private * * @param bool $crawler_only Whether crawler-only UA. * @return array */ private function _get_curl_options( $crawler_only = false ) { $crawler_timeout = defined( 'LITESPEED_CRAWLER_TIMEOUT' ) ? (int) constant( 'LITESPEED_CRAWLER_TIMEOUT' ) : 30; $options = [ CURLOPT_RETURNTRANSFER => true, CURLOPT_HEADER => true, CURLOPT_CUSTOMREQUEST => 'GET', CURLOPT_FOLLOWLOCATION => false, CURLOPT_ENCODING => 'gzip', CURLOPT_CONNECTTIMEOUT => 10, CURLOPT_TIMEOUT => $crawler_timeout, // Larger timeout to avoid incorrect blacklist addition #900171. CURLOPT_SSL_VERIFYHOST => 0, CURLOPT_SSL_VERIFYPEER => false, CURLOPT_NOBODY => false, CURLOPT_HTTPHEADER => $this->_crawler_conf['headers'], ]; $options[ CURLOPT_HTTPHEADER ][] = 'Cache-Control: max-age=0'; $options[ CURLOPT_HTTP_VERSION ] = CURL_HTTP_VERSION_1_1; // if is walker // $options[ CURLOPT_FRESH_CONNECT ] = true; // Referer. if ( isset( $_SERVER['HTTP_HOST'], $_SERVER['REQUEST_URI'] ) ) { $host = sanitize_text_field( wp_unslash( $_SERVER['HTTP_HOST'] ) ); $uri = sanitize_text_field( wp_unslash( $_SERVER['REQUEST_URI'] ) ); $options[ CURLOPT_REFERER ] = 'http://' . $host . $uri; } // User Agent. if ( $crawler_only ) { if ( 0 !== strpos( (string) $this->_crawler_conf['ua'], self::FAST_USER_AGENT ) ) { $this->_crawler_conf['ua'] = self::FAST_USER_AGENT . ' ' . (string) $this->_crawler_conf['ua']; } } $options[ CURLOPT_USERAGENT ] = (string) $this->_crawler_conf['ua']; // Cookies. $cookies = []; foreach ( $this->_crawler_conf['cookies'] as $k => $v ) { if ( ! $v ) { continue; } $cookies[] = $k . '=' . rawurlencode( $v ); } if ( $cookies ) { $options[ CURLOPT_COOKIE ] = implode( '; ', $cookies ); } return $options; } /** * Terminate crawling. * * @since 1.1.0 * @access private * @return void */ private function _terminate_running() { $this->_map_status_list = $this->cls( 'Crawler_Map' )->save_map_status( $this->_map_status_list, $this->_summary['curr_crawler'] ); if ( 'end' === $this->_end_reason ) { $this->_summary['curr_crawler'] = (int) $this->_summary['curr_crawler'] + 1; // Jump to next crawler. $this->_summary['last_pos'] = 0; // reset last position. $this->_summary['last_crawler_total_cost'] = time() - (int) $this->_summary['curr_crawler_beginning_time']; $count_crawlers = count( $this->list_crawlers() ); if ( $this->_summary['curr_crawler'] >= $count_crawlers ) { self::debug( '_terminate_running Touched end, whole crawled. Reload crawler!' ); $this->_summary['curr_crawler'] = 0; $this->_summary['done'] = 'touchedEnd'; // log done status. $this->_summary['last_full_time_cost'] = time() - (int) $this->_summary['this_full_beginning_time']; } } $this->_summary['last_status'] = 'stopped'; $this->_summary['is_running'] = 0; $this->_summary['end_reason'] = $this->_end_reason; self::save_summary(); } /** * List all crawlers ( tagA => [ valueA => titleA, ... ] ... ). * * @since 1.9.1 * @access public * @return array<int,array<string,mixed>> */ public function list_crawlers() { if ( $this->_crawlers ) { return $this->_crawlers; } $crawler_factors = []; // Add default Guest crawler. $crawler_factors['uid'] = [ 0 => __( 'Guest', 'litespeed-cache' ) ]; // WebP on/off. if ( $this->conf( Base::O_IMG_OPTM_WEBP ) ) { $crawler_factors['webp'] = [ 1 => $this->cls( 'Media' )->next_gen_image_title() ]; if ( apply_filters( 'litespeed_crawler_webp', false ) ) { $crawler_factors['webp'][0] = ''; } } // Guest Mode on/off. if ( $this->conf( Base::O_GUEST ) ) { $vary_name = $this->cls( 'Vary' )->get_vary_name(); $vary_val = 'guest_mode:1'; if ( ! defined( 'LSCWP_LOG' ) ) { $vary_val = md5( $this->conf( Base::HASH ) . $vary_val ); } $crawler_factors[ 'cookie:' . $vary_name ] = [ $vary_val => '', '_null' => '<font data-balloon-pos="up" aria-label="Guest Mode">👒</font>', ]; } // Mobile crawler. if ( $this->conf( Base::O_CACHE_MOBILE ) ) { $crawler_factors['mobile'] = [ 1 => '<font data-balloon-pos="up" aria-label="Mobile">📱</font>', 0 => '', ]; } // Get roles set. foreach ( $this->conf( Base::O_CRAWLER_ROLES ) as $v ) { $role_title = ''; $udata = get_userdata( $v ); if ( isset( $udata->roles ) && is_array( $udata->roles ) ) { $tmp = array_values( $udata->roles ); $role_title = array_shift( $tmp ); } if ( ! $role_title ) { continue; } $crawler_factors['uid'][ $v ] = ucfirst( $role_title ); } // Cookie crawler. Filter lets 3rd-party integrations inject crawler-scoped cookie rows (e.g. WCML _lscache_vary per-currency) $cookie_list = apply_filters( 'litespeed_crawler_cookies', $this->conf( Base::O_CRAWLER_COOKIES ) ); if ( ! is_array( $cookie_list ) ) { $cookie_list = []; } foreach ( $cookie_list as $v ) { if ( empty( $v['name'] ) ) { continue; } $this_cookie_key = 'cookie:' . $v['name']; // Preserves Guest Mode preset when same-name cookie row arrives. if ( ! isset( $crawler_factors[ $this_cookie_key ] ) ) { $crawler_factors[ $this_cookie_key ] = []; } foreach ( $v['vals'] as $v2 ) { // Preserve existing labels (e.g. Guest Mode 👒 marker on `_null`) — skip if value already mapped. if ( isset( $crawler_factors[ $this_cookie_key ][ $v2 ] ) ) { continue; } $crawler_factors[ $this_cookie_key ][ $v2 ] = ( '_null' === $v2 ? '' : '<font data-balloon-pos="up" aria-label="Cookie">🍪</font>' . esc_html( $v['name'] ) . '=' . esc_html( $v2 ) ); } } // Crossing generate the crawler list. $this->_crawlers = $this->_recursive_build_crawler( $crawler_factors ); return $this->_crawlers; } /** * Build a crawler list recursively. * * @since 2.8 * @access private * * @param array<string,array> $crawler_factors Factors. * @param array $group Current group. * @param int $i Factor index. * @return array<int,array> */ private function _recursive_build_crawler( $crawler_factors, $group = [], $i = 0 ) { $current_factor_keys = array_keys( $crawler_factors ); $current_factor = $current_factor_keys[ $i ]; $if_touch_end = ( $i + 1 ) >= count( $crawler_factors ); $final_list = []; foreach ( $crawler_factors[ $current_factor ] as $k => $v ) { $item = $group; // Don't alter $group bcos of loop usage. $item['title'] = ! empty( $group['title'] ) ? $group['title'] : ''; if ( $v ) { if ( $item['title'] ) { $item['title'] .= ' - '; } $item['title'] .= $v; } $item[ $current_factor ] = $k; if ( $if_touch_end ) { $final_list[] = $item; } else { // Inception: next layer. $final_list = array_merge( $final_list, $this->_recursive_build_crawler( $crawler_factors, $item, $i + 1 ) ); } } return $final_list; } /** * Return crawler meta file local path. * * @since 6.1 * @access public * @return string */ public function json_local_path() { return LITESPEED_STATIC_DIR . '/crawler/' . $this->_sitemeta; } /** * Return crawler meta file URL. * * @since 1.1.0 * @access public * @return string|false */ public function json_path() { if ( ! file_exists( LITESPEED_STATIC_DIR . '/crawler/' . $this->_sitemeta ) ) { return false; } return LITESPEED_STATIC_URL . '/crawler/' . $this->_sitemeta; } /** * Create reset pos file. * * @since 1.1.0 * @access public * @return void */ public function reset_pos() { File::save( $this->_resetfile, time(), true ); self::save_summary( [ 'is_running' => 0 ] ); } /** * Display status based by matching crawlers order. * * @since 3.0 * @access public * * @param string $status_row Status string. * @param string $reason_set Comma separated reasons. * @return string HTML dots. */ public function display_status( $status_row, $reason_set ) { if ( ! $status_row ) { return ''; } $_status_list = [ '-' => 'default', self::STATUS_MISS => 'primary', self::STATUS_HIT => 'success', self::STATUS_BLACKLIST => 'danger', self::STATUS_NOCACHE => 'warning', ]; $reason_set = explode( ',', $reason_set ); $status = ''; foreach ( str_split( $status_row ) as $k => $v ) { $reason = isset( $reason_set[ $k ] ) ? $reason_set[ $k ] : ''; if ( 'Man' === $reason ) { $reason = __( 'Manually added to blocklist', 'litespeed-cache' ); } if ( 'Existed' === $reason ) { $reason = __( 'Previously existed in blocklist', 'litespeed-cache' ); } if ( ctype_digit( (string) $v ) ) { // Counting marker: failed N time(s), still retrying. $class = 'warning'; $reason = $reason ? sprintf( __( 'Failed %1$s time(s) (HTTP %2$s), still retrying', 'litespeed-cache' ), $v, $reason ) : sprintf( __( 'Failed %s time(s), still retrying', 'litespeed-cache' ), $v ); } else { $class = isset( $_status_list[ $v ] ) ? $_status_list[ $v ] : 'default'; } $reason_attr = $reason ? 'data-balloon-pos="up" aria-label="' . esc_attr( $reason ) . '"' : ''; $status .= '<i class="litespeed-dot litespeed-bg-' . esc_attr( $class ) . '" ' . $reason_attr . '>' . ( $k + 1 ) . '</i>'; } return $status; } /** * Handle all request actions from main cls. * * @since 3.0 * @access public * @return void */ public function handler() { $type = Router::verify_type(); switch ( $type ) { case self::TYPE_REFRESH_MAP: $this->cls( 'Crawler_Map' )->gen( true ); break; case self::TYPE_EMPTY: $this->cls( 'Crawler_Map' )->empty_map(); break; case self::TYPE_BLACKLIST_EMPTY: $this->cls( 'Crawler_Map' )->blacklist_empty(); break; case self::TYPE_BLACKLIST_DEL: // phpcs:ignore WordPress.Security.NonceVerification.Recommended, WordPress.Security.ValidatedSanitizedInput.MissingUnslash, WordPress.Security.ValidatedSanitizedInput.InputNotSanitized if (!empty($_GET['id'])) { // phpcs:ignore WordPress.Security.NonceVerification.Recommended $id = absint( wp_unslash( $_GET['id'] ) ); $this->cls( 'Crawler_Map' )->blacklist_del( $id ); } break; case self::TYPE_BLACKLIST_ADD: // phpcs:ignore WordPress.Security.NonceVerification.Recommended, WordPress.Security.ValidatedSanitizedInput.MissingUnslash, WordPress.Security.ValidatedSanitizedInput.InputNotSanitized if (!empty($_GET['id'])) { // phpcs:ignore WordPress.Security.NonceVerification.Recommended $id = absint( wp_unslash( $_GET['id'] ) ); $this->cls( 'Crawler_Map' )->blacklist_add( $id ); } break; case self::TYPE_START: // Handle the ajax request to proceed crawler manually by admin. self::start_async(); break; case self::TYPE_RESET: $this->reset_pos(); break; default: break; } Admin::redirect(); } }
BanaBridge News
https://validator.w3.org/feed/docs/rss2.html
Court Orders Ex-Weah Protocol Chief Jailed on US$8 Million Bail, Sends 15 Jurors to Prison Over Misconduct
Women Renew Call for War and Economic Crimes Court at Liberia’s Historic Peace Prayer Site
Finance Minister Ngafuan Urges Transparency, Accountability as Liberia Advances ARREST Agenda at UN Retreat
PPCC Donates ICT Equipment to 50 Government Institutions to Expand Electronic Procurement System
Liberia Commissions €100,000 Elemental Analyzer to Strengthen Environmental Research and Food Security
EPA Ends 16 Years of Renting with Purchase of Permanent Headquarters
West African Tax Bodies Deepen Partnership to Boost Revenue Mobilization, Launch Carbon Tax Study
Liberia Hosts Sierra Leone Procurement Delegation for E-GP Reform Study Tour
World Bank Praises Liberia’s Central Bank for Economic Stability and Private Sector Progress
Liberians See Slight Improvement in Corruption Fight, But Graft Still Viewed as Widespread, CENTAL Report Finds
Canada Afrique Care Foundation Set for Official Launch, Expanding Free Mental Health Access Across Canada and Africa
Weah Claims Liberia Has Become a “Narco State” as Opposition Rallies Behind Calls for Independent Probe into US$19 Million Cocaine Bust
EPA Boss Calls for Stronger Student Engagement, Unveils Push for Academic Partnership at UL Climate Symposium
Education Minister Urges Students to Embrace Tax Responsibility at National Student Tax Day
CDC Secretary General Urges U.S. Government to Review Support to Liberia National Police
Liberia Partners with CACFO to Expand Mental Health Services Ahead of Global Launch
Wreh-Toe Appointed Board Chair of CACFO as Foundation Strengthens Mental Health Push
GIABA Opens New Information Center Headquarters in Abidjan
Liberia Wins Fresh Backing as World Bank Group Executive Praises Progress, Pushes Faster Project Delivery
LRA Honors Liberia’s Top Taxpayers as Revenue Collections Hit Historic High
Root Cause in Question as Border Tensions Persist After Conakry Peace Deal
From Enforcement to Innovation: EPA Marks 2025 as a Defining Year for Liberia’s Environment
Weah Declares ‘Road to 2029 Begins Today’ as CDC Marks 22nd Anniversary in Zwedru
500 Documented Governance Failures: Activist Publishes Sweeping End-of-Year Indictment of Boakai Administration
CDC Calls for Probe into Border Crisis, Cites Alleged Mining Activities
Liberia Moves to Strengthen Small Businesses with $672,000 Packaging Solution Initiative
Former Public Works Minister Ruth Coker Collins Defends Zwedru Corridor Strategy, Calls for “Facts Over Rhetoric” in Infrastructure Debate
Power Shake-Up in CDC Diaspora: NEC Dissolves CDC-USA Interim Leadership, Appoints Rev. Muin to Lead U.S. Chapter
Tweah Reemerges, Sparks Fierce National Debate Over Governance and Liberia’s Future
Koijee Slams Tribal Politics and Political Manipulation in Lofa, Accuses Boakai Government
Mali and Burkina Faso Impose Reciprocal Travel Ban on U.S. Citizens
Guinea Election: A Turn Toward Continuity Amid Questions of Democratic Credibility
Liberia’s Revenue Grows Stronger as LRA Exceeds National Target for Second Year
Liberia’s Gender Legal Landscape: Laws in Place, Systems Lag Far Behind
Liberia’s Economy Gains Momentum as CBL Governor Highlights Progress at ECOWAS Meeting
Liberia Positions Itself for Eco Currency Entry as Economy Expands by 5.1%
From Overcrowded Classrooms to Renewal: NPA Mobilizes $1 Million to Transform UL
Ex-Public Works Minister Ruth Coker Collins Slams Ministry’s “Lack of Capacity,” Defends Her Infrastructure Record
CDC Expels Three Senior Members, Citing Alleged Alignment With Government and Undermining Party Ideology
UL to Celebrate 75 Years of Excellence
Saudi Fund Advances Liberia’s Push for Major Infrastructure Development
West African Financial Leaders Convene in Monrovia for ECOWAS Statutory Meetings
Unlocking Liberia’s Potential: Government Launches Major Revenue and Transparency Reforms
Incremental Gains, Enduring Impunity: Liberia’s CPI Improvement Fails the Test of Reform
Boakai’s Call for Unity Faces Scrutiny as Opposition, Citizens Question Actions Behind the Words
REMAPSEN Liberia Set to Strengthen Health and Environmental Reporting
Energy Sector Women Step Into the Spotlight at Liberia’s International Women’s Day Celebration
FeJAL Concludes Three-Day Retreat, Honors Outstanding Women Journalists
Dr. Rasha Kelej Named Among Africa’s 100 Most Influential Leaders
LAVA Honored for Strengthening Liberia–U.S. Ties at 2025 Military Ball