PHP kód:
<?php
function getMetaFromHTML($html){
$finalMetas = [];
preg_match_all('~<meta\s*([^>]+)\s*\*>~i', $html, $metas, PREG_SET_ORDER);
foreach($metas as $meta){
preg_match_all('~([a-z0-9:_\-]+)=(?:"([^"]*?)"|\'([^\']*?)\')~i', $meta[1], $attributes, PREG_SET_ORDER);
$currentMeta = [];
foreach($attributes as $attribute){
$currentMeta[$attribute[1]] = $attribute[2]?:$attribute[3];
}
$finalMetas[] = $currentMeta;
}
return $finalMetas;
}
var_dump(getMetaFromHTML('
<meta name="referrer" content="unsafe-url"/>
<meta content="WebTrh, byznys, podnikání" name="keywords" />
<meta data-something="1" name="news_keywords" content="web,trh">
<META value=\'@WashingtonPost\' data-something="1" name="twitter:site"/>
<meta name=\'twitter:card\' content="summary_large_image" data-something="1">
<title>Washington Post</title>
<meta data-something1="1" content=\'type1\' data-something2="2" property="og:type" />
'));
/*
array(6) {
[0]=>
array(2) {
["name"]=>
string(8) "referrer"
["content"]=>
string(10) "unsafe-url"
}
[1]=>
array(2) {
["content"]=>
string(27) "WebTrh, byznys, podnikání"
["name"]=>
string(8) "keywords"
}
[2]=>
array(3) {
["data-something"]=>
string(1) "1"
["name"]=>
string(13) "news_keywords"
["content"]=>
string(7) "web,trh"
}
[3]=>
array(3) {
["value"]=>
string(15) "@WashingtonPost"
["data-something"]=>
string(1) "1"
["name"]=>
string(12) "twitter:site"
}
[4]=>
array(3) {
["name"]=>
string(12) "twitter:card"
["content"]=>
string(19) "summary_large_image"
["data-something"]=>
string(1) "1"
}
[5]=>
array(4) {
["data-something1"]=>
string(1) "1"
["content"]=>
string(5) "type1"
["data-something2"]=>
string(1) "2"
["property"]=>
string(7) "og:type"
}
}*/
