在正则表达式中选择几个项目

你不应该使用正则表达式来解析 html，这里有一个简单的函数，它使用 domDocument 加 curl 作为它的速度更快。

示例抓取：

查找具有onmouseout属性的所有链接a 值为 return nd(); ：

<?php 
$link = 'http://www.bandliste.de/Bandliste/';
$data=curl_get($link, $link);
$info = DOMParse($data,'a','onmouseout','return nd();');
print_r($info);
/*
Array
(
    [0] => Array
        (
            [tag] => a
            [onmouseout] => return nd();
            [text] => Martin und Kiehm
        )
    [1] => Array
        (
            [tag] => a
            [onmouseout] => return nd();
            [text] => Blues For Three
        )
    [2] => Array
        (
            [tag] => a
            [onmouseout] => return nd();
            [text] => Phrase Applauders
        )
 ...
 ...
*/
?>

或者第二个示例查找具有名为 bandinfo 的 class 属性的div：

<?php
$link = 'Bands/Falling_For_Beautiful/14469/';
$link='http://www.bandliste.de/'.$link;
$data=curl_get($link, $link);
$info = DOMParse($data,'div','class','bandinfo');
/*
Array
(
[0] => Array
(
[tag] => div
[class] => bandinfo
[text] => What? We are Falling For Beautiful and we make music. And basically  thats it. Sound? Rock. Indie. Alternative. Pop. Who? Adrianne (Vocals/Guitar) Nina (Guitar/Special Effects) Bianca (Bass) Marisa (Drums) When? Some of us started having a band in 2003  we played tons of gigs, covered tons of songs, started writing our own songs. In 2008 we decided to forget about that and founded FFB. So we started to write songs and arranged them. We made them sound simple and catchy focusing on lyrics. Our songs are about life.  Booking: Bianca Untertrifallerhttp://www.fallingforbeautiful.com
)
)
*/
?>

或者在某些javascript中包含的onclick中包含的图像：

获取所有带有onclicks img标签

<?php
$img = DOMParse($data,'img','onclick');
//Then find the image we are looking for
function parse_img($array){
    foreach($array as $value){
        if(strstr($value['onclick'],"Band Foto")){
            preg_match('#window.open'(''(.*?)'', ''Band Foto''#',$value['onclick'],$match);
            return $match[1];
        }
    }
}
//echo parse_img($img); //bandfoto-14469.jpg
?>

实际的 dom 函数：

<?php
function DOMParse($source,$tags,$attribute=null,$attributeValue=null){
    header('Content-Type: text/html; charset=utf-8');
    $return = array();
    $dom = new DOMDocument("1.0","UTF-8");
    @$dom->loadHTML($source);
    $dom->preserveWhiteSpace = false;
    foreach($dom->getElementsByTagName($tags) as $ret) {
        //No attribute to look for so return only nodeValue
        if($attribute==null){
            if(trim($ret->nodeValue)==''){continue;}
            $return[] = array('tag'=>$tags,'text'=>preg_replace('/'s+/', ' ',$ret->nodeValue));
        }else{
            //Attribute not null look for eg: src, href, class ect
            if(trim($ret->nodeValue)=='' && $ret->getAttribute($attribute)==''){continue;}
            //If we looking for specific value from an attribute containg an attibute value
            if($attributeValue!=null){
                if($ret->getAttribute($attribute)==$attributeValue){
                    $return[] = array('tag'=>$tags,$attribute=>$ret->getAttribute($attribute),'text'=>preg_replace('/'s+/', ' ',$ret->nodeValue));
                }
            }else{
                $return[] = array('tag'=>$tags,$attribute=>$ret->getAttribute($attribute),'text'=>preg_replace('/'s+/', ' ',$ret->nodeValue));
            }
        }
    }
    return $return;
}
?>

和卷曲功能：

<?php
function curl_get($url, $referer){
    //check curl is installed or revert back to file_get_contents
    $return = (function_exists('curl_init')) ? '' : false;
    if($return==false){return file_get_contents($url);}
    $curl = curl_init();
    $header[0] = "Accept: text/xml,application/xml,application/json,application/xhtml+xml,";
    $header[0] .= "text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5";
    $header[] = "Cache-Control: max-age=0";
    $header[] = "Connection: keep-alive";
    $header[] = "Keep-Alive: 300";
    $header[] = "Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7";
    $header[] = "Accept-Language: en-us,en;q=0.5";
    $header[] = "Pragma: ";
    curl_setopt($curl, CURLOPT_URL, $url);
    curl_setopt($curl, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows NT 5.1; rv:5.0) Gecko/20100101 Firefox/5.0 Firefox/5.0');
    curl_setopt($curl, CURLOPT_HTTPHEADER, $header);
    curl_setopt($curl, CURLOPT_HEADER, 0);
    curl_setopt($curl, CURLOPT_REFERER, $referer);
    curl_setopt($curl, CURLOPT_ENCODING, 'gzip,deflate');
    curl_setopt($curl, CURLOPT_AUTOREFERER, true);
    curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
    curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true);
    curl_setopt($curl, CURLOPT_TIMEOUT, 30);
    curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false);
    $html = curl_exec($curl);
    curl_close($curl);
    return $html;
}
?>

希望对您有所帮助。

$match2[1]只包含一个匹配项。尝试使用$match2

foreach($match2 as $info) echo $info."<br/>";