流方式实现多线程采集问题,请高手分析下
采集内容速度慢,我一直很头大,最近在研究多线程采集,下面贴出比较代码,有两个问题,一是获取的结果长度有点不一致;二是效率是不是还不够高?大伙帮忙分析,测试!
<?php$timeStart = microtimeFloat();function microtimeFloat() { list($usec, $sec) = explode(" ", microtime()); return ((float)$usec + (float)$sec);}$data = '';$urls = array('http://www.tzksgs.com/news/2012-09/article-217.html', 'http://www.tzksgs.com/news/2012-09/article-219.html', 'http://www.tzksgs.com/news/2012-09/article-222.html');foreach($urls as $url){ echo strlen(file_get_contents($url)),'<br>';}$timeEnd = microtimeFloat();echo sprintf("Spend time: %s second(s)\n", $timeEnd - $timeStart),'<br>';$timeStart = microtimeFloat();$timeout = 30;$status = array();$retdata = array();$sockets = array();$userAgent = $_SERVER['HTTP_USER_AGENT'];foreach($urls as $id => $url) { $tmp = parse_url($url); $host = $tmp['host']; $path = isset($tmp['path'])?$tmp['path']:'/'; empty($tmp['query']) or $path .= '?' . $tmp['query']; if (empty($tmp['port'])) { $port = $tmp['scheme'] == 'https' ? 443 : 80; } else $port = $tmp['port']; $fp = stream_socket_client("$host:$port", $errno, $errstr, 30); if (!$fp) { $status[$id] = "failed, $errno $errstr"; } else { $status[$id] = "in progress"; $retdata[$id] = ''; $sockets[$id] = $fp; fwrite($fp, "GET $path HTTP/1.1\r\nHost: $host\r\nUser-Agent: $userAgent\r\nConnection: Close\r\n\r\n"); }}// Now, wait for the results to come back inwhile (count($sockets)) { $read = $write = $sockets; //This is the magic function - explained below if (stream_select($read, $write = null, $e = null, $timeout)) { //readable sockets either have data for us, or are failed connection attempts foreach ($read as $r) { $id = array_search($r, $sockets); $data = fread($r, 8192); if (strlen($data) == 0) { if ($status[$id] == "in progress") { $status[$id] = "failed to connect"; } fclose($r); unset($sockets[$id]); } else { $retdata[$id] .= $data; } } }}foreach($retdata as $data){ $data = trim(substr($data, strpos($data, "\r\n\r\n") + 4)); echo strlen($data),'<br>';}$timeEnd = microtimeFloat();echo sprintf("Spend time: %s second(s)\n", $timeEnd - $timeStart);?>