我使用
DOMDocument
来处理HTML和PHP 7。问题是,页面上的文本(西里尔字母)看起来很好,但当我查看“查看HTML页面源代码”时,它不好。它显示如下:Здесь осн
可能有什么问题?<meta>
charset是utf-8。我的代码:$dom = new DOMDocument();
if (@$dom->loadHTML(mb_convert_encoding("<div>$body</div>", 'HTML-ENTITIES', 'UTF-8'), LIBXML_HTML_NOIMPLIED | LIBXML_HTML_NODEFDTD)) {
// https://dev59.com/7F0b5IYBdhLWcg3wMutw
$container = $dom->getElementsByTagName('div')->item(0);
$container = $container->parentNode->removeChild($container);
while ($dom->firstChild)
$dom->removeChild($doc->firstChild);
while ($container->firstChild )
$dom->appendChild($container->firstChild);
$xpath = new DOMXPath($dom);
$headlines = $xpath->query("//h2");
// some code..
return $dom->saveHTML();
}