php匹配指定标签的内容

/*** 匹配任意id的html标签内容* */function getWebTag($tag_id,$tag='div',$data=false){             $charset_pos = stripos($data,'charset');        if($charset_pos) {            if(stripos($data,'utf-8',$charset_pos)) {                $data = iconv('utf-8','utf-8',$data);            }else if(stripos($data,'gb2312',$charset_pos)) {                $data = iconv('gb2312','utf-8',$data);            }else if(stripos($data,'gbk',$charset_pos)) {                $data = iconv('gbk','utf-8',$data);            }        }               preg_match_all('/<'.$tag.'/i',$data,$pre_matches,PREG_OFFSET_CAPTURE);    //获取所有div前缀        preg_match_all('/<\/'.$tag.'/i',$data,$suf_matches,PREG_OFFSET_CAPTURE); //获取所有div后缀        $hit = strpos($data,$tag_id);        if($hit == -1) return false;    //未命中        $divs = array();    //合并所有div        foreach($pre_matches[0] as $index=>$pre_div){            $divs[(int)$pre_div[1]] = 'p';            $divs[(int)$suf_matches[0][$index][1]] = 's';           }               //对div进行排序        $sort = array_keys($divs);        asort($sort);               $count = count($pre_matches[0]);        foreach($pre_matches[0] as $index=>$pre_div){            //';                break;            }        }        return $hitDivString;}

调用示例

$html=file_get_contents('http://www.baidu.com');

$divContent=getWebTag('id="content"','div',$html);