someone here may find it useful. hhb_curl_exec2 works pretty much like curl_exec, but arg3 is an array which will be populated with the returned http headers (numeric index), and arg4 is an array which will be populated with the returned cookies ($cookies["expires"]=>"Fri, 06-May-2016 05:58:51 GMT"), and arg5 will be populated with... info about the raw request made by curl.
the downside is that it requires CURLOPT_RETURNTRANSFER to be on, else it error out, and that it will overwrite CURLOPT_STDERR and CURLOPT_VERBOSE, if you were already using them for something else.. (i might fix this later)
example of how to use it:
<?php
header("content-type: text/plain;charset=utf8");
$ch=curl_init();
$headers=array();
$cookies=array();
$debuginfo="";
$body="";
curl_setopt($ch,CURLOPT_SSL_VERIFYPEER,false);
curl_setopt($ch,CURLOPT_RETURNTRANSFER,true);
$body=hhb_curl_exec2($ch,'https://www.youtube.com/',$headers,$cookies,$debuginfo);
var_dump('$cookies:',$cookies,'$headers:',$headers,'$debuginfo:',$debuginfo,'$body:',$body);
and the function itself..
function hhb_curl_exec2($ch, $url, &$returnHeaders = array(), &$returnCookies = array(), &$verboseDebugInfo = "")
{
$returnHeaders = array();
$returnCookies = array();
$verboseDebugInfo = "";
if (!is_resource($ch) || get_resource_type($ch) !== 'curl') {
throw new InvalidArgumentException('$ch must be a curl handle!');
}
if (!is_string($url)) {
throw new InvalidArgumentException('$url must be a string!');
}
$verbosefileh = tmpfile();
$verbosefile = stream_get_meta_data($verbosefileh);
$verbosefile = $verbosefile['uri'];
curl_setopt($ch, CURLOPT_VERBOSE, 1);
curl_setopt($ch, CURLOPT_STDERR, $verbosefileh);
curl_setopt($ch, CURLOPT_HEADER, 1);
$html = hhb_curl_exec($ch, $url);
$verboseDebugInfo = file_get_contents($verbosefile);
curl_setopt($ch, CURLOPT_STDERR, NULL);
fclose($verbosefileh);
unset($verbosefile, $verbosefileh);
$headers = array();
$crlf = "\x0d\x0a";
$thepos = strpos($html, $crlf . $crlf, 0);
$headersString = substr($html, 0, $thepos);
$headerArr = explode($crlf, $headersString);
$returnHeaders = $headerArr;
unset($headersString, $headerArr);
$htmlBody = substr($html, $thepos + 4); //should work on utf8/ascii headers... utf32? not so sure..
unset($html);
//I REALLY HOPE THERE EXIST A BETTER WAY TO GET COOKIES.. good grief this looks ugly..
//at least it's tested and seems to work perfectly...
$grabCookieName = function($str)
{
$ret = "";
$i = 0;
for ($i = 0; $i < strlen($str); ++$i) {
if ($str[$i] === ' ') {
continue;
}
if ($str[$i] === '=') {
break;
}
$ret .= $str[$i];
}
return urldecode($ret);
};
foreach ($returnHeaders as $header) {
//Set-Cookie: crlfcoookielol=crlf+is%0D%0A+and+newline+is+%0D%0A+and+semicolon+is%3B+and+not+sure+what+else
/*Set-Cookie:ci_spill=a%3A4%3A%7Bs%3A10%3A%22session_id%22%3Bs%3A32%3A%22305d3d67b8016ca9661c3b032d4319df%22%3Bs%3A10%3A%22ip_address%22%3Bs%3A14%3A%2285.164.158.128%22%3Bs%3A10%3A%22user_agent%22%3Bs%3A109%3A%22Mozilla%2F5.0+%28Windows+NT+6.1%3B+WOW64%29+AppleWebKit%2F537.36+%28KHTML%2C+like+Gecko%29+Chrome%2F43.0.2357.132+Safari%2F537.36%22%3Bs%3A13%3A%22last_activity%22%3Bi%3A1436874639%3B%7Dcab1dd09f4eca466660e8a767856d013; expires=Tue, 14-Jul-2015 13:50:39 GMT; path=/
Set-Cookie: sessionToken=abc123; Expires=Wed, 09 Jun 2021 10:18:14 GMT;
//Cookie names cannot contain any of the following '=,; \t\r\n\013\014'
//
*/
if (stripos($header, "Set-Cookie:") !== 0) {
continue;
/**/
}
$header = trim(substr($header, strlen("Set-Cookie:")));
while (strlen($header) > 0) {
$cookiename = $grabCookieName($header);
$returnCookies[$cookiename] = '';
$header = substr($header, strlen($cookiename) + 1); //also remove the =
if (strlen($header) < 1) {
break;
}
;
$thepos = strpos($header, ';');
if ($thepos === false) { //last cookie in this Set-Cookie.
$returnCookies[$cookiename] = urldecode($header);
break;
}
$returnCookies[$cookiename] = urldecode(substr($header, 0, $thepos));
$header = trim(substr($header, $thepos + 1)); //also remove the ;
}
}
unset($header, $cookiename, $thepos);
return $htmlBody;
}
function hhb_curl_exec($ch, $url)
{
static $hhb_curl_domainCache = "";
//$hhb_curl_domainCache=&$this->hhb_curl_domainCache;
//$ch=&$this->curlh;
if (!is_resource($ch) || get_resource_type($ch) !== 'curl') {
throw new InvalidArgumentException('$ch must be a curl handle!');
}
if (!is_string($url)) {
throw new InvalidArgumentException('$url must be a string!');
}
$tmpvar = "";
if (parse_url($url, PHP_URL_HOST) === null) {
if (substr($url, 0, 1) !== '/') {
$url = $hhb_curl_domainCache . '/' . $url;
} else {
$url = $hhb_curl_domainCache . $url;
}
}
;
curl_setopt($ch, CURLOPT_URL, $url);
$html = curl_exec($ch);
if (curl_errno($ch)) {
throw new Exception('Curl error (curl_errno=' . curl_errno($ch) . ') on url ' . var_export($url, true) . ': ' . curl_error($ch));
// echo 'Curl error: ' . curl_error($ch);
}
if ($html === '' && 203 != ($tmpvar = curl_getinfo($ch, CURLINFO_HTTP_CODE)) /*203 is "success, but no output"..*/ ) {
throw new Exception('Curl returned nothing for ' . var_export($url, true) . ' but HTTP_RESPONSE_CODE was ' . var_export($tmpvar, true));
}
;
//remember that curl (usually) auto-follows the "Location: " http redirects..
$hhb_curl_domainCache = parse_url(curl_getinfo($ch, CURLINFO_EFFECTIVE_URL), PHP_URL_HOST);
return $html;
}
