php 正则表达式抓取网页内容

<?php$url="http://m.youku.com/wap/";//$reg1="/^<a\s*href=\"(.*?)version=2\">$/i";$reg1="/<a\s*href=\"(.*?)version=2\"(.*?)>(.*?)<\/a>/i";//获取视频链接$reg2="/<img ([^ alt="php 正则表达式抓取网页内容" >]*)\s*class=\"imgdetail\"\s*src=('|\")([^'\"]+)('|\")/i";$reg3="<a\s*href=\"(.*?)&format=3gphd\"\s*id=\"click_play\"\s*>";$reg4= "/<p\s*class=\"videotitle\".*?>.*?<\/p>/i";//获取视频标题$content=file_get_contents($url);preg_match_all($reg1, $content,$matches);$video=$matches[0];//首页视频的链接$resultArray=array();//装载所有数据的数组//$subArray=array();//子数组foreach ($video as $key){		//处理url，得到视频的点击网址	$position=strpos($key, "href");	$substring=substr($key, $position+11);	$pos=strpos($substring, ">");	$link=substr($substring, 0,$pos-1);	$nextUrl=$url.$link;	$nextContent=file_get_contents($nextUrl);	//获取视频图片	preg_match_all($reg2, $nextContent,$img);	$img_arr=$img[0];	foreach ($img_arr as $arr)	{		$position=strpos($arr, "src");		$sub=substr($arr, $position+5);		$last=substr($sub, 0,$pos);	}		//获取视频高清点播地址	preg_match_all($reg3, $nextContent,$vids);	$video_arr=$vids[0];	$vid=$video_arr[0];	$position=strpos($vid, "href");	$v_string=substr($vid, $position+11);	$pos=strpos($v_string, "\"");	$add=substr($v_string, 0,$pos);	$video_url=$url.$add;	//获取视频的标题	preg_match_all($reg4, $nextContent,$match);	$title=$match[0];	$r=serialize($title);	$position=mb_strpos($r, "</p>");	$sub=substr($r, 0,$position);	$pos=mb_strrpos($sub, ">");	$til=substr($sub, $pos+1);	$subArray=array('image'=>$last,'video'=>$video_url,'title'=>$til);	array_push($resultArray, $subArray);}$resultJson=json_encode($resultArray);file_put_contents('web.txt', print_r($resultJson,true));