php simple dom html 解析乱码

$html = '<p>你好</p><p><span>立即学习</span>“<a href="https://pan.quark.cn/s/7fc7563c4182" style="text-decoration: underline !important; color: blue; font-weight: bolder;" rel="nofollow" target="_blank">PHP免费学习笔记（深入）</a>”；</p>'; $dom = new DOMDocument(); @$dom->loadHTML($html); echo $dom->documentElement->nodeValue;

$html = '<p>你好</p><p><span>立即学习</span>“<a href="https://pan.quark.cn/s/7fc7563c4182" style="text-decoration: underline !important; color: blue; font-weight: bolder;" rel="nofollow" target="_blank">PHP免费学习笔记（深入）</a>”；</p>'; $dom = new DOMDocument(); @$dom->loadXML($html); echo $dom->documentElement->nodeValue;

$meta = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>'; @$dom->loadHTML($meta . $html);

function _pretty_html_node($node){ // 递归终止前提 // 1. XML_TEXT_NODE // 2. XML_ELEMENT_NODE // 3. 没有子节点 foreach($node->childNodes as $n){ $child_text .= _pretty_html_node($n); } // 然后对分歧的标签做不同的处置 switch($tag){ case 'a': $href = $node->getAttribute('href'); $text .= "<a href=\"$href\">$child_text</a>"; ... } return $text; }