Online PHP editor | refs for kXlLb

<?php $html=<<<HTML <a href="bla">123 "this" is asd</a> <a href="bla">this should not be captured</a> <a href="bla">no quotes in anchor text here</a> <a href="bla">"445 is in quotes"</a> <a href="bla">asd "blabla" sometimes</a> <a href="bla">Je commence à avoir mal à la tête</a> <a href="bla">something with quotes like “blabla” is bad</a> HTML; $dom = new DOMDocument; $html=mb_convert_encoding($html,'HTML-ENTITIES',"UTF-8"); $dom->loadHTML($html,LIBXML_HTML_NODEFDTD); // 2nd params to remove DOCTYPE); foreach($dom->getElementsByTagName('a') as $a){ //echo $a->nodeValue,"\n"; if(preg_match('~["“”]~u',$a->nodeValue)){ $remove[]=$a; } } foreach($remove as $bad_a){ $bad_a->parentNode->removeChild($bad_a); } $result=mb_convert_encoding($dom->saveHTML(),"UTF-8",'HTML-ENTITIES'); echo preg_replace(['~^<html><body>|</body></html>$~','~\R+~'],['',"\n"],$result);