[php-dom] php-dom使用注意事项

/*
注意事项：
　　1. 在loadHTML之前，应该将内容转义为UTF-8编码的，这样子避免出现entity等等的报错；
　　2. 已经使用了php函数htmlspecialchars()转换的html实体，再经过DOM解析转换后，会被直接还原为标签，如：<br/> 在dom解析之后，直接被还原为 "<br/>";

*/

$doc = new DOMDocument('1.0' , 'UTF-8');
//var_dump($doc);
libXml_use_internal_errors(true);
$doc->loadHTML(mb_convert_encoding($content , 'HTML-ENTITIES', 'UTF-8'));

$node = $doc->getElementsByTagName('div');
$arr_return = array();

// 只发了一条动态的情况还没有考虑清楚
for($c = 0; $c<$node->length; $c++){
$arr_return[$c]['time'] = $node->item($c)->getAttribute('hnb-time');
$arr_return[$c]['ftime'] = date('H:i' , $arr_return[$c]['time']);
$arr_return[$c]['nation'] = $node->item($c)->getAttribute('hnb-nation');
$arr_return[$c]['nation_info'] = Hnb_Model_Tag::getInstance()->getCndNationalInfoByID($node->item($c)->getAttribute('hnb-nation'));
$p_nodes = $node->item($c)->getElementsByTagName('p');
//$doc->encoding = 'UTF-8';
//echo iconv("UTF-8", "GB18030//TRANSLIT", $dom->saveXML($n) );
//$arr_return[$c]['content'] = iconv("UTF-8", "UTF-8", $doc->saveXML($p_nodes->item(0)));
//var_dump($p_nodes->item(0));
// 默认将第一个p节点作为内容来处理
$arr_return[$c]['content'] = $doc->saveXML($p_nodes->item(0));
$arr_return[$c]['raw_content'] = $p_nodes->item(0)->textContent;
$arr_img_list = [];
for($p = 1; $p<$p_nodes->length; $p++){
$img = $doc->saveXML($p_nodes->item($p));
if(preg_match('/jpg|png|gif|jpeg/i' , $img))
{
$arr_img_list[] = $img;
}
}
$arr_return[$c]['img_list'] = $arr_img_list;
}
return $arr_return;