Detect encoding and make everything UTF-8

Question

I\'m reading out lots of texts from various RSS feeds and inserting them into my database.

Of course, there are several different character encodings used in the fee

Answer 1

Get encoding from headers and convert it to utf-8.

$post_url='http://website.domain';

/// Get headers ////////////////////////////////////////////////////////////
function get_headers_curl($url) 
{ 
    $ch = curl_init(); 

    curl_setopt($ch, CURLOPT_URL,            $url); 
    curl_setopt($ch, CURLOPT_HEADER,         true); 
    curl_setopt($ch, CURLOPT_NOBODY,         true); 
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); 
    curl_setopt($ch, CURLOPT_TIMEOUT,        15); 

    $r = curl_exec($ch); 
    return $r; 
}
$the_header = get_headers_curl($post_url);
/// check for redirect /////////////////////////////////////////////////
if (preg_match("/Location:/i", $the_header)) {
    $arr = explode('Location:', $the_header);
    $location = $arr[1];

    $location=explode(chr(10), $location);
    $location = $location[0];

$the_header = get_headers_curl(trim($location));
}
/// Get charset /////////////////////////////////////////////////////////////////////
if (preg_match("/charset=/i", $the_header)) {
    $arr = explode('charset=', $the_header);
    $charset = $arr[1];

    $charset=explode(chr(10), $charset);
    $charset = $charset[0];
    }
///////////////////////////////////////////////////////////////////////////////
// echo $charset;

if($charset && $charset!='UTF-8') { $html = iconv($charset, "UTF-8", $html); }