(.*?)<(?:\s+)?/(?:\s+)?a(?:\s+)?>)%sm', $html, $match, PREG_PATTERN_ORDER);
for ($i = 0; $i < count($match[1]); $i++) {
if(!preg_match("/$whitelist/", $match[1][$i])){
$spamsite = $match[3][$i];
$html = preg_replace("%" . preg_quote($match[1][$i]) . "%", " (SPAM) ", $html);
}
}
preg_match_all('/(\b(?:(?:(?:https?|ftp|file):\/\/|www\.|ftp\.)[A-Z0-9+&@#\/%?=~_|$!:,.;-]*[A-Z0-9+&@#\/%=~_|$-]|((?:mailto:)?[A-Z0-9._%+-]+@[A-Z0-9._%-]+\.[A-Z]{2,6})\b)|"(?:(?:https?|ftp|file):\/\/|www\.|ftp\.)[^"\r\n]+"|\'(?:(?:https?|ftp|file):\/\/|www\.|ftp\.)[^\'\r\n]+\')/i', $html, $match2, PREG_PATTERN_ORDER);
for ($i = 0; $i < count($match2[1]); $i++) {
if(!preg_match("/$whitelist/", $match2[1][$i])){
$spamsite = $match2[1][$i];
$html = preg_replace("%" . preg_quote($spamsite) . "%", " (SPAM) ", $html);
}
}
return $html;
}
$html = <<< LOB
Hello world, thanks to http://mywebsite/about I learned a lot. I found
you on http://w...content-available-to-author-only...g.com, https://google.com/search and on some www.spamwebsite.com/refid=spammer2< /a >. www.spamme.com, http://m...content-available-to-author-only...m.com/?aff=122, http://c...content-available-to-author-only...r.com/?money=22 and spam@email.com, file://spamfile.com/file.txt ftp://s...content-available-to-author-only...p.com/file.exe
LOB;
//USAGE
$whitelist = "(google\.com|yahoo\.com|bing\.com|nicesite\.com|mywebsite\.com)";
$noSpam = killSpam($html, $whitelist);
echo $noSpam;