PHP多線程批量采集下載美女圖片的實(shí)現(xiàn)代碼
使用curl的多線程,另外curl可以設(shè)置請(qǐng)求時(shí)間,遇到很慢的url資源,可以果斷的放棄,這樣沒有阻塞,另外有多線程請(qǐng)求,效率應(yīng)該比較高
使用curl的多線程,另外curl可以設(shè)置請(qǐng)求時(shí)間,遇到很慢的url資源,可以果斷的放棄,這樣沒有阻塞,另外有多線程請(qǐng)求,效率應(yīng)該比較高
下面是代碼實(shí)現(xiàn):
- /**
- * curl 多線程
- * @author http://www.lai18.com
- * @param array $array 并行網(wǎng)址
- * @param int $timeout 超時(shí)時(shí)間
- * @return mix
- */
- public function Curl_http($array,$timeout='15'){
- $res = array();
- $mh = curl_multi_init();//創(chuàng)建多個(gè)curl語(yǔ)柄
- foreach($array as $k=>$url){
- $conn[$k]=curl_init($url);//初始化
- curl_setopt($conn[$k], CURLOPT_TIMEOUT, $timeout);//設(shè)置超時(shí)時(shí)間
- curl_setopt($conn[$k], CURLOPT_USERAGENT, 'Mozilla/5.0 (compatible; MSIE 5.01; Windows NT 5.0)');
- curl_setopt($conn[$k], CURLOPT_MAXREDIRS, 7);//HTTp定向級(jí)別 ,7最高
- curl_setopt($conn[$k], CURLOPT_HEADER, false);//這里不要header,加塊效率
- curl_setopt($conn[$k], CURLOPT_FOLLOWLOCATION, 1); // 302 redirect
- curl_setopt($conn[$k], CURLOPT_RETURNTRANSFER,1);//要求結(jié)果為字符串且輸出到屏幕上
- curl_setopt($conn[$k], CURLOPT_HTTPGET, true);
- curl_multi_add_handle ($mh,$conn[$k]);
- }
- //防止死循環(huán)耗死cpu 這段是根據(jù)網(wǎng)上的寫法
- do {
- $mrc = curl_multi_exec($mh,$active);//當(dāng)無(wú)數(shù)據(jù),active=true
- } while ($mrc == CURLM_CALL_MULTI_PERFORM);//當(dāng)正在接受數(shù)據(jù)時(shí)
- while ($active and $mrc == CURLM_OK) {//當(dāng)無(wú)數(shù)據(jù)時(shí)或請(qǐng)求暫停時(shí),active=true
- if (curl_multi_select($mh) != -1) {
- do {
- $mrc = curl_multi_exec($mh, $active);
- } while ($mrc == CURLM_CALL_MULTI_PERFORM);
- }
- }
- foreach ($array as $k => $url) {
- if(!curl_errno($conn[$k])){
- $data[$k]=curl_multi_getcontent($conn[$k]);//數(shù)據(jù)轉(zhuǎn)換為array
- $header[$k]=curl_getinfo($conn[$k]);//返回http頭信息
- curl_close($conn[$k]);//關(guān)閉語(yǔ)柄
- curl_multi_remove_handle($mh , $conn[$k]); //釋放資源
- }else{
- unset($k,$url);
- }
- }
- curl_multi_close($mh);
- return $data;
- }
- //參數(shù)接收
- $callback = $_GET['callback'];
- $hrefs = $_GET['hrefs'];
- $urlarray = explode(',',trim($hrefs,','));
- $date = date('Ymd',time());
- //實(shí)例化
- $img = new HttpImg();
- $stime = $img->getMicrotime();//開始時(shí)間
- $data = $img->Curl_http($urlarray,'20');//列表數(shù)據(jù)
- mkdir('./img/'.$date,0777);
- foreach ((array)$data as $k=>$v){
- preg_match_all("/(href|src)=(["|']?)([^ "'>]+.(jpg|png|PNG|JPG|gif))\2/i", $v, $matches[$k]);
- if(count($matches[$k][3])>0){
- $dataimg = $img->Curl_http($matches[$k][3],'20');//全部圖片數(shù)據(jù)二進(jìn)制
- $j = 0;
- foreach ((array)$dataimg as $kk=>$vv){
- if($vv !=''){
- $rand = rand(1000,9999);
- $basename = time()."_".$rand.".".jpg;//保存為jpg格式的文件
- $fname = './img/'.$date."/"."$basename";
- file_put_contents($fname, $vv);
- $j++;
- echo "創(chuàng)建第".$j."張圖片"."$fname"."<br/>";
- }else{
- unset($kk,$vv);
- }
- }
- }else{
- unset($matches);
- }
- }
- $etime = $img->getMicrotime();//結(jié)束時(shí)間
- echo "用時(shí)".($etime-$stime)."秒";
- exit;
責(zé)任編輯:王雪燕
來(lái)源:
hello_katty的專欄