$re = '/(.*?)((((aa|ab|af|ak|am|an|ar|as|av|ay|az|ba|be|bg|bh|bi|bm|bn|bo|br|bs|ca|ce|ch|co|cr|cs|cv|cy|da|de|dv|dz|ee|el|es|et|eu|fa|ff|fi|fj|fo|fr|fy|ga|gd|gl|gn|gu|gv|ha|he|hi|ho|hr|ht|hu|hy|hz|id|ig|ii|ik|io|is|it|iu|ja|jv|ka|kg|ki|kj|kk|kl|km|kn|ko|kr|ks|ku|kv|kw|ky|lb|lg|li|ln|lo|lt|lu|lv|mg|mh|mi|mk|ml|mn|mr|ms|mt|my|na|nb|nd|ne|ng|nl|nn|no|nr|nv|ny|oc|oj|om|or|os|pa|pl|ps|pt|qu|rm|rn|ro|ru|rw|sa|sc|sd|se|sg|si|sk|sl|sm|sn|so|sq|sr|ss|st|su|sv|sw|ta|te|tg|th|ti|tk|tl|tn|to|tr|ts|tt|tw|ty|ug|uk|ur|uz|ve|vi|wa|wo|xh|yi|yo|za|zh|zu)\.(wikipedia|wikisource|wikiversity|wikibooks|wikinews|wiktionary|wikivoyage|wikiquote)\.org))|(web\.archive\.org)|(\.(ac|ad|ae|af|ag|ai|al|am|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|bq|br|bs|bt|bw|by|bz|ca|cd|cf|cg|ch|ci|ck|cl|cm|cn|cr|cu|cv|cw|cx|cy|cz|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tr|tt|tv|tw|tz|ua|ug|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|za|zm|zw)([\.\/]|$))).*?$/m';
$str = 'https://en.wikipedia.org/wiki/Main_Page
https://tl.wikipedia.org/wiki/Unang_Pahina
https://web.archive.org/123123
whatever.pl/asd';
preg_match_all($re, $str, $matches, PREG_SET_ORDER, 0);
// Print the entire match result
var_dump($matches);
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for PHP, please visit: http://php.net/manual/en/ref.pcre.php