twitter has bad characters in twitter messages that will make your MySQL fail, so this cleans it up for an insert.

gistfile1.php

<?php

//Test string that will blow up MySQL insert: UlQgQFJabm9ydGg6IEhhcHB5IEJpcnRoZGF5IEBkdWNpZG5pIHlvdXIgbXVzaWMgcmVtaW5kcyBtZSBvZiBteSBiZXN0IG1lbW9yaWVzICNORlNNb3ZpZSAjc2F0ZWxsaXRlZmxpZ2h0IPCfjrbwn5KZ8J+agA==

if ( ! defined('BASEPATH')) exit('No direct script access allowed');

function remove_non_utf8($string) {
	//reject overly long 2 byte sequences, as well as characters above U+10000 and replace with ?
	$string = preg_replace('/[\x00-\x08\x10\x0B\x0C\x0E-\x19\x7F]'.
	 '|[\x00-\x7F][\x80-\xBF]+'.
	 '|([\xC0\xC1]|[\xF0-\xFF])[\x80-\xBF]*'.
	 '|[\xC2-\xDF]((?![\x80-\xBF])|[\x80-\xBF]{2,})'.
	 '|[\xE0-\xEF](([\x80-\xBF](?![\x80-\xBF]))|(?![\x80-\xBF]{2})|[\x80-\xBF]{3,})/S',
	 '', $string );
	 
	//reject overly long 3 byte sequences and UTF-16 surrogates and replace with ?
	$string = preg_replace('/\xE0[\x80-\x9F][\x80-\xBF]'.
	 '|\xED[\xA0-\xBF][\x80-\xBF]/S','', $string );

	return $string;
}