如何从一个PHPcurl获取cookie到一个variables
所以其他一些公司的一些人认为，如果不是使用soap或者xml-rpc或者其他合理的通信协议，他只是把所有的响应作为cookiesembedded到头文件中，那就太棒了。
我需要把这些cookies放在希望从这个curl响应数组中。 如果我不得不浪费大量时间为此写一个parsing器，我会很不高兴。
有谁知道这可以简单地完成，最好不写任何文件？
如果有人能帮我解决这个问题，我将非常感激。
$ch = curl_init('http://www.google.com/'); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); // get headers too with this line curl_setopt($ch, CURLOPT_HEADER, 1); $result = curl_exec($ch); // get cookie // multi-cookie variant contributed by @Combuster in comments preg_match_all('/^Set-Cookie:\s*([^;]*)/mi', $result, $matches); $cookies = array(); foreach($matches[1] as $item) { parse_str($item, $cookie); $cookies = array_merge($cookies, $cookie); } var_dump($cookies); 虽然这个问题是相当老的，而且接受的答案是有效的，但是我觉得它有点不合适，因为HTTP响应（HTML，XML，JSON，二进制或其他）的内容与标题混合在一起。
我find了另一种select。 CURL提供了一个选项（ CURLOPT_HEADERFUNCTION ）来设置一个callbackCURLOPT_HEADERFUNCTION ，这个callback函数将被调用给每个响应头文件行。 该函数将收到curl对象和一个带有标题行的string。
你可以使用这样的代码（改编自TML响应）：
$cookies = Array(); $ch = curl_init('http://www.google.com/'); // Ask for the callback. curl_setopt($ch, CURLOPT_HEADERFUNCTION, "curlResponseHeaderCallback"); $result = curl_exec($ch); var_dump($cookies); function curlResponseHeaderCallback($ch, $headerLine) { global $cookies; if (preg_match('/^Set-Cookie:\s*([^;]*)/mi', $headerLine, $cookie) == 1) $cookies[] = $cookie; return strlen($headerLine); // Needed by curl }
此解决scheme有使用全局variables的缺点，但我想这不是短脚本的问题。 而且，如果将curl包装到类中，则始终可以使用静态方法和属性。
这没有正则expression式，但需要PECL HTTP扩展 。
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); curl_setopt($ch, CURLOPT_HEADER, 1); $result = curl_exec($ch); curl_close($ch); $headers = http_parse_headers($result); $cookobjs = Array(); foreach($headers AS $k => $v){ if (strtolower($k)=="set-cookie"){ foreach($v AS $k2 => $v2){ $cookobjs[] = http_parse_cookie($v2); } } } $cookies = Array(); foreach($cookobjs AS $row){ $cookies[] = $row->cookies; } $tmp = Array(); // sort k=>v format foreach($cookies AS $v){ foreach ($v AS $k1 => $v1){ $tmp[$k1]=$v1; } } $cookies = $tmp; print_r($cookies);
如果使用CURLOPT_COOKIE_FILE和CURLOPT_COOKIE_JAR，curl将从文件读取/写入cookie。 您可以在curl完成后，根据需要阅读和/或修改它。
libcurl还提供CURLOPT_COOKIELIST，它提取所有已知的cookie。 所有你需要的是确保PHP / CURL绑定可以使用它。
curl_setopt($ch, CURLOPT_HEADER, 1); //Return everything $res = curl_exec($ch); //Split into lines $lines = explode("\n", $res); $headers = array(); $body = ""; foreach($lines as $num => $line){ $l = str_replace("\r", "", $line); //Empty line indicates the start of the message body and end of headers if(trim($l) == ""){ $headers = array_slice($lines, 0, $num); $body = $lines[$num + 1]; //Pull only cookies out of the headers $cookies = preg_grep('/^Set-Cookie:/', $headers); break; } }
我的理解是，来自curl cookies必须写出到一个文件（ curl -c cookie_file ）。 如果您通过PHP的exec或systemfunction（或该系列中的任何其他function）运行curl ，则应该可以将cookie保存到文件，然后打开文件并将其读入。
这里的某个人可能会觉得有用。 hhb_curl_exec2与curl_exec非常类似，但是arg3是一个数组，它将被返回的http头（数字索引）填充，而arg4是一个数组，它将被返回的cookie填充（$ cookies [“expires”] =>“星期五，06-May-2016 05:58:51 GMT“），arg5将被填充… curl所做的原始请求信息。
缺点是它需要CURLOPT_RETURNTRANSFER，否则它错误了，它会覆盖CURLOPT_STDERR 和 CURLOPT_VERBOSE，如果你已经使用他们的东西..（我可能会解决这个问题）
如何使用它的例子：
<?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:',$body);
和函数本身..
function hhb_curl_exec2($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; }
