I have to get the content of a persian page and show a part of that page to some users. The problem is after I filter the page content I cannot show the content with the proper encoding. The webpage is located at sena.ir and here is the screen shot of the original webpage part I want to show:
And here is what I got:
Here is the function I use to get the page content:
function getPage($url, $referer="", $timeout="", $header=""){
if(!isset($timeout))
$timeout=30;
$curl = curl_init();
if(strstr($referer,"://")){
curl_setopt ($curl, CURLOPT_REFERER, $referer);
}
$headers [] = 'Accept: image/gif, image/x-bitmap, image/jpeg, image/pjpeg';
$headers [] = 'Connection: Keep-Alive';
$headers [] = 'Content-type: application/x-www-form-urlencoded;charset=utf-8 '; // I Tried iso-..... as well but no chance
$user_agent = 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 1.0.3705; .NET CLR 1.1.4322; Media Center PC 4.0)';
$compression = "gzip";
curl_setopt ($curl, CURLOPT_HTTPHEADER, $headers );
curl_setopt ($curl, CURLOPT_HEADER, 0 );
curl_setopt ($curl, CURLOPT_USERAGENT, $user_agent );
curl_setopt ($curl, CURLOPT_RETURNTRANSFER, 1 );
curl_setopt ($curl, CURLOPT_FOLLOWLOCATION, 1 );
curl_setopt ($curl, CURLOPT_POST, 0 );
curl_setopt ($curl, CURLOPT_ENCODING, $compression );
curl_setopt ($curl, CURLOPT_TIMEOUT, 300 );
curl_setopt ($curl, CURLOPT_SSL_VERIFYHOST, 0 );
curl_setopt ($curl, CURLOPT_SSL_VERIFYPEER, 0 );
curl_setopt ($curl, CURLOPT_URL, $url);
$html = curl_exec ($curl);
curl_close ($curl);
return $html;
}
$content = getPage("http://sena.ir/");
$p1 = strpos($content,'<TABLE cellSpacing="3" cellPadding="3" width="100%" border="0">');
$p2 = strpos($content,"</TABLE>",$p1);
$content = substr($content, $p1, $p2-$p1);
echo $content;