正则表达式，用于从HTML页面中提取第二个表

我认为过早接受，如果你想使用DOMDocument做它，那么这里有一个通用的DOM废弃类，我之前建立的，它非常基本。如果你想要更多的功能，也有简单的HTML DOM，但底线是不要使用正则表达式来解析HTML!

<?php 
$site = 'http://www.grossiste-informatique.com/grossiste/detail_article_popup.php?code_article=POA/F200CA-KX019H';
$scraper = new DOMScraper();
//Set site and get source
$scraper->setSite($site)
        ->setSource();

echo '<table cellspacing="0" cellpadding="3" border="0" width="100%">',
        //match and return only tables inner content with cellpadding="3"
        $scraper->getInnerHTML('table', 'cellpadding=3'), 
     '</table>';
/**
 * Generic DOM scapper using DOMDocument and cURL
 */
Class DOMScraper extends DOMDocument{
    public $site;
    private $source;
    private $dom;
    function __construct(){
        libxml_use_internal_errors(true);
        $this->preserveWhiteSpace = false;
        $this->strictErrorChecking = false;
        $this->formatOutput = true;
    }
    function setSite($site){
        $this->site = $site;
        return $this;
    }
    function setSource(){
        if(empty($this->site))return 'Error: Missing $this->site, use setSite() first';
        $this->source = $this->get_data($this->site);
        return $this;
    }
    function getInnerHTML($tag, $id=null, $nodeValue = false){
        if(empty($this->site))return 'Error: Missing $this->source, use setSource() first';
        $this->loadHTML($this->source);
        $tmp = $this->getElementsByTagName($tag);
        $ret = null;
        foreach ($tmp as $v){
            if($id !== null){
                $attr = explode('=',$id);
                if($v->getAttribute($attr[0])==$attr[1]){
                    if($nodeValue == true){
                        $ret .= trim($v->nodeValue);
                    }else{
                        $ret .= $this->innerHTML($v);
                    }
                }
            }else{
                if($nodeValue == true){
                    $ret .= trim($v->nodeValue);
                }else{
                    $ret .= $this->innerHTML($v);
                }
            }
        }
        return $ret;
    }
    function innerHTML($dom){
        $ret = "";
        $nodes = $dom->childNodes;
        foreach($nodes as $v){
            $tmp = new DOMDocument();
            $tmp->appendChild($tmp->importNode($v, true));
            $ret .= trim($tmp->saveHTML());
        }
        return $ret;
    }
    function get_data($url){
        if(function_exists('curl_init')){
            $ch = curl_init();
            curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
            curl_setopt($ch, CURLOPT_TIMEOUT, 5);
            curl_setopt($ch, CURLOPT_URL, $url);
            curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
            $data = curl_exec($ch);
            curl_close($ch);
            return $data;
        }else{
            return file_get_contents($url);
        }
    }
}
?>

我会第一时间把你链接到相关文章

用DOMDocument代替。

同样，如果你真的想要(你真的不应该想要)，你可以试试这个regex(未经测试):

preg_match('/<table[^>]+>.*?<table[^>]+>(.*?)<'/table>/is', $returnCurl, $features);