php正则取网页代码中的img图片

分类:php

 php正则取网页代码中的img图片,下载图片到本地,方便小巧实用!

 

<?php
set_time_limit(0);



$srt='<br tangram-key="module-split" style="display: none;"><table border="0" bordercolor="#cccccc" cellspacing="0" height="31" width="682"><tbody><tr><td height="31" width="105"><img data-ks-lazyloaded="true" src="http://img01.taobaocdn.com/imgextra/i1/676649324/T2cul3XoNcXXXXXXXX_!!676649324.jpg" height="39" width="104"></td><td height="31" width="565"><font face="simhei" size="5"><span style="line-height: 36.0px;"></span></font><br><br><span style="color: #ff0000;"></span></td></tr></tbody></table><table border="0" cellpadding="0" cellspacing="0" width="750"><tbody><tr><td><img data-ks-lazyloaded="true" src="http://img01.taobaocdn.com/imgextra/i1/1037043605/T2j58lXaxOXXXXXXXX_!!1037043605.jpg" height="556" width="750"></td></tr></tbody></table><table border="0" cellpadding="0" cellspacing="0" width="750"><tbody><tr></tr><tr><td height="664"><img data-ks-lazyloaded="true" src="http://img01.taobaocdn.com/imgextra/i1/1037043605/T2jSyfXexcXXXXXXXX_!!1037043605.jpg" height="664" width="750"></td></tr><tr><td height="916"><img data-ks-lazyloaded="true" src="http://img02.taobaocdn.com/imgextra/i2/676649324/T2Ly1gXbpcXXXXXXXX_!!676649324.jpg" height="916" width="750"></td></tr><tr><td height="742"><img data-ks-lazyloaded="true" src="http://img01.taobaocdn.com/imgextra/i1/676649324/T2e.pRXo4dXXXXXXXX_!!676649324.jpg" height="742" width="750"></td></tr><tr><td height="724"><img data-ks-lazyloaded="true" src="http://img03.taobaocdn.com/imgextra/i3/676649324/T28kC1XnlXXXXXXXXX_!!676649324.jpg" height="724" width="750"></td></tr><tr><td height="789"><img data-ks-lazyloaded="true" src="http://img03.taobaocdn.com/imgextra/i3/676649324/T2gXu0XnRaXXXXXXXX_!!676649324.jpg" height="789" width="750"></td></tr><tr><td height="834"><img data-ks-lazyloaded="true" src="http://img02.taobaocdn.com/imgextra/i2/676649324/T2aq11XgXaXXXXXXXX_!!676649324.jpg" height="834" width="750"></td></tr><tr><td height="1020"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img02.taobaocdn.com/imgextra/i2/676649324/T21OF_XgNcXXXXXXXX_!!676649324.jpg" height="1020" width="750"></td></tr><tr><td height="815"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img02.taobaocdn.com/imgextra/i2/676649324/T2Hbq1XilXXXXXXXXX_!!676649324.jpg" height="816" width="750"></td></tr><tr><td height="320"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img03.taobaocdn.com/imgextra/i3/676649324/T2I651XoxXXXXXXXXX_!!676649324.jpg" height="320" width="750"></td></tr><tr><td><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img03.taobaocdn.com/imgextra/i3/676649324/T2yB4hXcBOXXXXXXXX_!!676649324.jpg"><br><a href="http://www.taobao.com/webww/ww.php?spm=a220o.1000855.0.119.ADw66M&amp;ver=3&amp;touid=%E6%A2%B5%E5%B8%8C%E8%94%93%E5%85%B0%E5%86%A0%E4%B8%93%E5%8D%96%E5%BA%97&amp;siteid=cntaobao&amp;status=1&amp;charset=utf-8" target="_blank"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img02.taobaocdn.com/imgextra/i2/676649324/T2iEKnXadcXXXXXXXX_!!676649324.jpg" border="0"></a><br><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img04.taobaocdn.com/imgextra/i4/676649324/T2joG8XiJaXXXXXXXX_!!676649324.gif"><br><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img03.taobaocdn.com/imgextra/i3/676649324/T2LTy8XfFaXXXXXXXX_!!676649324.jpg"><br><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img02.taobaocdn.com/imgextra/i2/676649324/T2u_m9XclXXXXXXXXX_!!676649324.jpg"></td></tr><tr><td height="1028"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img04.taobaocdn.com/imgextra/i4/676649324/T24eWGXmpbXXXXXXXX_!!676649324.jpg" height="1028" width="750"></td></tr><tr><td height="0">&nbsp;</td></tr><tr><td height="821"><a href="http://detail.tmall.com/item.htm?spm=a220o.1000855.17.31.a2b9c5&amp;id=15662490028&amp;" target="_blank"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img01.taobaocdn.com/imgextra/i1/1037043605/T2w.X.XhXcXXXXXXXX_!!1037043605.jpg" border="0" height="821" width="750"></a></td></tr><tr><td height="0"><a href="http://detail.taobao.com/meal_detail.htm?spm=0.0.0.3.WnWbAk&amp;meal_id=24054196&amp;seller_id=676649324" target="_blank"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img01.taobaocdn.com/imgextra/i1/676649324/T2gGSqXa8cXXXXXXXX_!!676649324.jpg" border="0" height="456" width="750"></a></td></tr><tr><td height="0"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img03.taobaocdn.com/imgextra/i3/676649324/T2Dbp.XdVbXXXXXXXX_!!676649324.jpg"></td></tr><tr><td height="0"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img02.taobaocdn.com/imgextra/i2/676649324/T2vnJ8XjRcXXXXXXXX_!!676649324.jpg" height="827" width="750"></td></tr><tr><td height="1028"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img02.taobaocdn.com/imgextra/i2/676649324/T2Sfy1XfhaXXXXXXXX_!!676649324.jpg" height="1028" width="750"></td></tr><tr><td height="3562"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img04.taobaocdn.com/imgextra/i4/676649324/T2XXG2Xd0XXXXXXXXX_!!676649324.jpg" height="3562" width="750"></td></tr><tr><td height="3600"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img03.taobaocdn.com/imgextra/i3/676649324/T2QVa1XgVaXXXXXXXX_!!676649324.jpg" height="3600" width="750"></td></tr><tr><td height="3492"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img04.taobaocdn.com/imgextra/i4/676649324/T2vUm1XihXXXXXXXXX_!!676649324.jpg" height="3492" width="750"></td></tr><tr><td height="2400"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img04.taobaocdn.com/imgextra/i4/676649324/T24GXVXihdXXXXXXXX_!!676649324.jpg" height="2400" width="750"></td></tr><tr><td height="1399"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img02.taobaocdn.com/imgextra/i2/676649324/T2ZLBLXh0eXXXXXXXX_!!676649324.jpg" height="1399" width="750"></td></tr><tr><td height="3458"><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img01.taobaocdn.com/imgextra/i1/676649324/T2lZOCXbxcXXXXXXXX_!!676649324.jpg" height="3458" width="750"></td></tr></tbody></table><p><img src="http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="http://img03.taobaocdn.com/imgextra/i3/676649324/T2C6NEXhhNXXXXXXXX_!!676649324.gif" height="224" width="750"></p>';


$str2="";
$zz="/data-ks-lazyload="(.*)jpg"/i";
//preg_match_all("/<img.*?data-ks-lazyloaded="true".*?src="(.*?)".*?height=(.*)"></td>/i",$srt,$a);

//preg_match_all("/<img.*?(.*)>/i",$srt,$a);


//preg_match_all("/<img.*?data-ks-lazyloaded="true".*?src="(.*?.jpg)"/i",$srt,$a);

preg_match_all("/<img.*?(http://img.*?.jpg)"/i",$srt,$a);

//$a=str_repleace('http://l.tbcdn.cn/kissy/1.0.0/build/imglazyload/spaceball.gif" data-ks-lazyload="',"",$a);
//print_r($a);
//echo $a[1];
$filepath="/test/getimg/d";
$num=count($a[1]);
echo $num;
$dir="d";
foreach ($a[1] as $key=>$value){
   
    echo $value."<br/><br/><br/>";
	 	//for($i=1;$i<=56;$i++){
		$i=$key+1;
		if($i<10){
			
			$u=$value;
	
			copy($u,"$dir/taobao0$i.jpg");

		}else{
			
			$u=$value;
		
			copy($u,"$dir/taobao$i.jpg");
		
		}
		
		
		
	
	

	
	//echo '<img src="'.$value.'">';
	//grabImage($value);
	//file_put_contents(basename($value), file_get_contents($value));
	//downloadImage($value, $filepath);
	/*preg_match_all("/<img.*?src=['| "](.*?(?:[.gif|.jpg]))['|"].*?[/]?>/",$value,$getPicPath);
	foreach ($$getPicPath[1] as $key=>$value){
		echo $value."<br/>22<br/>22<br/>";
    }*/

}

/*preg_match_all("/<img.*?src=['| "](.*?(?:[.gif|.jpg]))['|"].*?[/]?>/",$srt,$getPicPath);
*/
//print_r($getPicPath);


function grabImage($url, $filename = '') {
    if($url == '') {
        return false; //如果 $url 为空则返回 false;
    }
    $ext_name = strrchr($url, '.'); //获取图片的扩展名
    if($ext_name != '.gif' && $ext_name != '.jpg' && $ext_name != '.bmp' && $ext_name != '.png') {
        return false; //格式不在允许的范围
    }
    if($filename == '') {
        $filename = time().$ext_name; //以时间戳另起名
    }
    //开始捕获
    ob_start();
    readfile($url);
    $img_data = ob_get_contents();
    ob_end_clean();
    $size = strlen($img_data);
    $local_file = fopen($filename , 'a');
    fwrite($local_file, $img_data);
    fclose($local_file);
    return $filename;
}


/**
     * 下载远程图片
     * @param string $url 图片的绝对url
     * @param string $filepath 文件的完整路径(包括目录,不包括后缀名,例如/www/images/test) ,此函数会自动根据图片url和http头信息确定图片的后缀名
     * @return mixed 下载成功返回一个描述图片信息的数组,下载失败则返回false
     */
    function downloadImage($url, $filepath) {
        //服务器返回的头信息
        $responseHeaders = array();
        //原始图片名
        $originalfilename = '';
        //图片的后缀名
        $ext = '';
        $ch = curl_init($url);
        //设置curl_exec返回的值包含Http头
        curl_setopt($ch, CURLOPT_HEADER, 1);
        //设置curl_exec返回的值包含Http内容
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);       
        //设置抓取跳转(http 301,302)后的页面
        curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
        //设置最多的HTTP重定向的数量
        curl_setopt($ch, CURLOPT_MAXREDIRS, 2);
 
        //服务器返回的数据(包括http头信息和内容)
        $html = curl_exec($ch);
        //获取此次抓取的相关信息
        $httpinfo = curl_getinfo($ch);
        curl_close($ch);
        if ($html !== false) {
            //分离response的header和body,由于服务器可能使用了302跳转,所以此处需要将字符串分离为 2+跳转次数 个子串
            $httpArr = explode("rnrn", $html, 2 + $httpinfo['redirect_count']);
            //倒数第二段是服务器最后一次response的http头
            $header = $httpArr[count($httpArr) - 2];
            //倒数第一段是服务器最后一次response的内容
            $body = $httpArr[count($httpArr) - 1];
            $header.="rn";
 
            //获取最后一次response的header信息
            preg_match_all('/([a-z0-9-_]+):s*([^rn]+)rn/i', $header, $matches);
            if (!empty($matches) && count($matches) == 3 && !empty($matches[1]) && !empty($matches[1])) {
                for ($i = 0; $i < count($matches[1]); $i++) {
                    if (array_key_exists($i, $matches[2])) {
                        $responseHeaders[$matches[1][$i]] = $matches[2][$i];
                    }
                }
            }
            //获取图片后缀名
            if (0 < preg_match('{(?:[^/\]+).(jpg|jpeg|gif|png|bmp)$}i', $url, $matches)) {
                $originalfilename = $matches[0];
                $ext = $matches[1];
            } else {
                if (array_key_exists('Content-Type', $responseHeaders)) {
                    if (0 < preg_match('{image/(w+)}i', $responseHeaders['Content-Type'], $extmatches)) {
                        $ext = $extmatches[1];
                    }
                }
            }
            //保存文件
            if (!empty($ext)) {
                $filepath .= ".$ext";
                //如果目录不存在,则先要创建目录
                CFiles::createDirectory(dirname($filepath));
                $local_file = fopen($filepath, 'w');
                if (false !== $local_file) {
                    if (false !== fwrite($local_file, $body)) {
                        fclose($local_file);
                        $sizeinfo = getimagesize($filepath);
                        return array('filepath' => realpath($filepath), 'width' => $sizeinfo[0], 'height' => $sizeinfo[1], 'orginalfilename' => $originalfilename, 'filename' => pathinfo($filepath, PATHINFO_BASENAME));
                    }
                }
            }
        }
        return false;
    }




?>

 

本文链接: php正则取网页代码中的img图片
版权所有:布士收藏夹在网络收集,如有侵犯你的权利, 请联系QQ:641868752。

评论

发表评论

*

* (显示gravatar头像)

Ctrl+Enter快捷回复

© 2014 布士收藏夹 all rights reserved.