01.$html = '<html>
02. <body>
03. <!--a comment-->
04. <div>some content</div><br>
05. Hello.
06. <p>Hello in paragraph.</p>
07. <p>Lorem Ipsum paragraph.</p>
08. <!--another comment-->
09. <!--------------another comment with wrong dashes------------>
10. </body>
11.</html>';
12.
13.
14.$dom = new DOMDocument();
15.$dom->preserveWhiteSpace = false;
16.$dom->formatOutput = false;
17.$dom->loadHTML($html, LIBXML_HTML_NODEFDTD);
18.
19.$xpath = new DOMXPath($dom);
20.
21.foreach ($xpath->query('//comment()') as $comment) {
22. $comment->parentNode->removeChild($comment);
23.}
24.
25.$body = $xpath->query('//body')->item(0);
26.$newHtml = $body instanceof DOMNode ? $dom->saveHTML() : 'something failed';
27.
28.
29.$htmlExp = explode("\n", str_replace(["\r\n", "\r", "\n"], "\n", $newHtml));
30.foreach ($htmlExp as $key => $htmlLine) {
31. if (trim($htmlLine) === '') {
32. unset($htmlExp[$key]);
33. }
34.}
35.$newHtml = implode("\n", $htmlExp);
36.
37.
38.var_dump($newHtml);
