function RetrieveWebpage($url, $options = array())
{
$startts = microtime(true);
$timeout = isset($options["timeout"]) ? $options["timeout"] : false;
if (!function_exists("stream_socket_client") && !function_exists("fsockopen")) {
return array("success" => false, "error" => HTTPTranslate("The functions 'stream_socket_client' and 'fsockopen' do not exist."), "errorcode" => "function_check");
}
// Process the URL.
$url = trim($url);
$url = ExtractURL($url);
if ($url["scheme"] != "http" && $url["scheme"] != "https") {
return array("success" => false, "error" => HTTPTranslate("RetrieveWebpage() only supports the 'http' and 'https' protocols."), "errorcode" => "protocol_check");
}
$secure = $url["scheme"] == "https";
$protocol = $secure ? isset($options["protocol"]) && strtolower($options["protocol"]) == "ssl" ? "ssl" : "tls" : "tcp";
if (function_exists("stream_get_transports") && !in_array($protocol, stream_get_transports())) {
return array("success" => false, "error" => HTTPTranslate("The desired transport protocol '%s' is not installed.", $protocol), "errorcode" => "transport_not_installed");
}
$host = str_replace(" ", "-", HTTPHeaderValueCleanup($url["host"]));
if ($host == "") {
return array("success" => false, "error" => HTTPTranslate("Invalid URL."));
}
$port = (int) $url["port"] ? (int) $url["port"] : ($secure ? 443 : 80);
$defaultport = !$secure && $port == 80 || $secure && $port == 443;
$path = $url["path"] == "" ? "/" : $url["path"];
$query = $url["query"];
$username = $url["loginusername"];
$password = $url["loginpassword"];
// Cleanup input headers.
if (!isset($options["headers"])) {
$options["headers"] = array();
}
$options["headers"] = HTTPNormalizeHeaders($options["headers"]);
// Process the proxy URL (if specified).
$useproxy = isset($options["proxyurl"]) && trim($options["proxyurl"]) != "";
if ($useproxy) {
$proxyurl = trim($options["proxyurl"]);
$proxyurl = ExtractURL($proxyurl);
$proxysecure = $proxyurl["scheme"] == "https";
$proxyprotocol = $proxysecure ? isset($options["proxyprotocol"]) && strtolower($options["proxyprotocol"]) == "ssl" ? "ssl" : "tls" : "tcp";
if (function_exists("stream_get_transports") && !in_array($proxyprotocol, stream_get_transports())) {
return array("success" => false, "error" => HTTPTranslate("The desired transport proxy protocol '%s' is not installed.", $proxyprotocol), "errorcode" => "proxy_transport_not_installed");
}
$proxyhost = str_replace(" ", "-", HTTPHeaderValueCleanup($proxyurl["host"]));
$proxyport = (int) $proxyurl["port"] ? (int) $proxyurl["port"] : ($proxysecure ? 443 : 80);
$proxypath = $proxyurl["path"] == "" ? "/" : $proxyurl["path"];
$proxyusername = $proxyurl["loginusername"];
$proxypassword = $proxyurl["loginpassword"];
// Open a tunnel instead of letting the proxy modify the request (HTTP CONNECT).
$proxyconnect = isset($options["proxyconnect"]) && $options["proxyconnect"] ? $options["proxyconnect"] : false;
if ($proxyconnect) {
$proxydata = "CONNECT " . $host . ":" . $port . " HTTP/1.1\r\n";
if (isset($options["headers"]["User-Agent"])) {
$data .= "User-Agent: " . $options["headers"]["User-Agent"] . "\r\n";
}
$proxydata .= "Host: " . $host . ($defaultport ? "" : ":" . $port) . "\r\n";
$proxydata .= "Proxy-Connection: keep-alive\r\n";
if ($proxyusername != "") {
$proxydata .= "Proxy-Authorization: BASIC " . base64_encode($proxyusername . ":" . $proxypassword) . "\r\n";
}
if (isset($options["proxyheaders"])) {
$options["proxyheaders"] = HTTPNormalizeHeaders($options["proxyheaders"]);
unset($options["proxyheaders"]["Accept-Encoding"]);
foreach ($options["proxyheaders"] as $name => $val) {
if ($name != "Content-Type" && $name != "Content-Length" && $name != "Proxy-Connection" && $name != "Host") {
$proxydata .= $name . ": " . $val . "\r\n";
}
}
}
$proxydata .= "\r\n";
if (isset($options["debug_callback"])) {
$options["debug_callback"]("rawproxyheaders", $proxydata, $options["debug_callback_opts"]);
}
}
}
// Process the method.
if (!isset($options["method"])) {
if (isset($options["write_body_callback"]) || isset($options["body"])) {
$options["method"] = "PUT";
} else {
if (isset($options["postvars"]) || isset($options["files"]) && count($options["files"])) {
$options["method"] = "POST";
} else {
$options["method"] = "GET";
}
}
}
$options["method"] = preg_replace('/[^A-Z]/', "", strtoupper($options["method"]));
// Process the HTTP version.
if (!isset($options["httpver"])) {
$options["httpver"] = "1.1";
}
$options["httpver"] = preg_replace('/[^0-9.]/', "", $options["httpver"]);
// Process the request.
$data = $options["method"] . " ";
$data .= ($useproxy && !$proxyconnect ? $url["scheme"] . "://" . $host . ":" . $port : "") . $path . ($query != "" ? "?" . $query : "");
$data .= " HTTP/" . $options["httpver"] . "\r\n";
// Process the headers.
if ($useproxy && !$proxyconnect && $proxyusername != "") {
$data .= "Proxy-Authorization: BASIC " . base64_encode($proxyusername . ":" . $proxypassword) . "\r\n";
}
if ($username != "") {
$data .= "Authorization: BASIC " . base64_encode($username . ":" . $password) . "\r\n";
}
$ver = explode(".", $options["httpver"]);
if ((int) $ver[0] > 1 || (int) $ver[0] == 1 && (int) $ver[1] >= 1) {
if (!isset($options["headers"]["Host"])) {
$options["headers"]["Host"] = $host . ($defaultport ? "" : ":" . $port);
}
$data .= "Host: " . $options["headers"]["Host"] . "\r\n";
}
$data .= "Connection: close\r\n";
if (isset($options["headers"])) {
foreach ($options["headers"] as $name => $val) {
if ($name != "Content-Type" && $name != "Content-Length" && $name != "Connection" && $name != "Host") {
$data .= $name . ": " . $val . "\r\n";
}
}
}
// Process the body.
$body = "";
$bodysize = 0;
if (isset($options["write_body_callback"])) {
$options["write_body_callback"]($body, $bodysize, $options["write_body_callback_opts"]);
} else {
if (isset($options["body"])) {
if (isset($options["headers"]["Content-Type"])) {
$data .= "Content-Type: " . $options["headers"]["Content-Type"] . "\r\n";
}
$body = $options["body"];
$bodysize = strlen($body);
unset($options["body"]);
} else {
if (isset($options["files"]) && count($options["files"])) {
$mime = "--------" . substr(sha1(uniqid(mt_rand(), true)), 0, 25);
$data .= "Content-Type: multipart/form-data; boundary=" . $mime . "\r\n";
if (isset($options["postvars"])) {
foreach ($options["postvars"] as $name => $val) {
$name = HTTPHeaderValueCleanup($name);
$name = str_replace("\"", "", $name);
if (is_string($val) || is_numeric($val)) {
$val = array($val);
}
foreach ($val as $val2) {
$body .= "--" . $mime . "\r\n";
$body .= "Content-Disposition: form-data; name=\"" . $name . "\"\r\n";
$body .= "\r\n";
$body .= $val2 . "\r\n";
}
}
unset($options["postvars"]);
}
$bodysize = strlen($body);
// Only count the amount of data to send.
foreach ($options["files"] as $num => $info) {
$name = HTTPHeaderValueCleanup($info["name"]);
$name = str_replace("\"", "", $name);
$filename = HTTPFilenameSafe(HTTPExtractFilename($info["filename"]));
$type = HTTPHeaderValueCleanup($info["type"]);
$body2 = "--" . $mime . "\r\n";
$body2 .= "Content-Disposition: form-data; name=\"" . $name . "\"; filename=\"" . $filename . "\"\r\n";
$body2 .= "Content-Type: " . $type . "\r\n";
$body2 .= "\r\n";
$info["filesize"] = isset($info["datafile"]) ? filesize($info["datafile"]) : strlen($info["data"]);
$bodysize += strlen($body2) + $info["filesize"] + 2;
$options["files"][$num] = $info;
}
$body2 = "--" . $mime . "--\r\n";
$bodysize += strlen($body2);
} else {
if (isset($options["postvars"])) {
foreach ($options["postvars"] as $name => $val) {
$name = HTTPHeaderValueCleanup($name);
if (is_string($val) || is_numeric($val)) {
$val = array($val);
}
foreach ($val as $val2) {
$body .= ($body != "" ? "&" : "") . urlencode($name) . "=" . urlencode($val2);
}
}
unset($options["postvars"]);
}
if ($body != "") {
$data .= "Content-Type: application/x-www-form-urlencoded\r\n";
}
$bodysize = strlen($body);
}
}
}
if ($bodysize < strlen($body)) {
$bodysize = strlen($body);
}
// Finalize the headers.
if ($bodysize || $body != "" || $options["method"] == "POST") {
$data .= "Content-Length: " . $bodysize . "\r\n";
}
$data .= "\r\n";
if (isset($options["debug_callback"])) {
$options["debug_callback"]("rawheaders", $data, $options["debug_callback_opts"]);
}
// Finalize the initial data to be sent.
$data .= $body;
$bodysize -= strlen($body);
$body = "";
$result = array("success" => true, "rawsendsize" => 0, "rawrecvsize" => 0, "rawrecvheadersize" => 0, "startts" => $startts);
$debug = isset($options["debug"]) && $options["debug"];
if ($debug) {
$result["rawsend"] = "";
$result["rawrecv"] = "";
}
if ($timeout !== false && HTTPGetTimeLeft($startts, $timeout) == 0) {
fclose($fp);
return array("success" => false, "error" => HTTPTranslate("HTTP timeout exceeded."), "errorcode" => "timeout_exceeded");
}
// Connect to the target server.
$errornum = 0;
$errorstr = "";
if ($useproxy) {
if (!isset($options["proxyconnecttimeout"])) {
$options["proxyconnecttimeout"] = 10;
}
$timeleft = HTTPGetTimeLeft($startts, $timeout);
if ($timeleft !== false) {
$options["proxyconnecttimeout"] = min($options["proxyconnecttimeout"], $timeleft);
}
if (!function_exists("stream_socket_client")) {
$fp = @fsockopen($proxyprotocol . "://" . $proxyhost, $proxyport, $errornum, $errorstr, $options["proxyconnecttimeout"]);
} else {
$context = @stream_context_create();
if ($proxysecure && isset($options["proxysslopts"]) && is_array($options["proxysslopts"])) {
HTTPProcessSSLOptions($options, "proxysslopts", $host);
foreach ($options["proxysslopts"] as $key => $val) {
@stream_context_set_option($context, "ssl", $key, $val);
}
}
$fp = @stream_socket_client($proxyprotocol . "://" . $host . ":" . $port, $errornum, $errorstr, $options["proxyconnecttimeout"], STREAM_CLIENT_CONNECT, $context);
$contextopts = stream_context_get_options($context);
if ($proxysecure && isset($options["proxysslopts"]) && is_array($options["proxysslopts"]) && ($protocol == "ssl" || $protocol == "tls") && isset($contextopts["ssl"]["peer_certificate"])) {
if (isset($options["debug_callback"])) {
$options["debug_callback"]("proxypeercert", @openssl_x509_parse($contextopts["ssl"]["peer_certificate"]), $options["debug_callback_opts"]);
}
}
}
if ($fp === false) {
return array("success" => false, "error" => HTTPTranslate("Unable to establish a connection to '%s'.", ($proxysecure ? $proxyprotocol . "://" : "") . $proxyhost . ":" . $proxyport), "info" => $errorstr . " (" . $errornum . ")", "errorcode" => "proxy_connect");
}
$result["connected"] = microtime(true);
if ($proxyconnect) {
// Send the HTTP CONNECT request.
fwrite($fp, $proxydata);
if ($timeout !== false && HTTPGetTimeLeft($startts, $timeout) == 0) {
fclose($fp);
return array("success" => false, "error" => HTTPTranslate("HTTP timeout exceeded."), "errorcode" => "timeout_exceeded");
}
$result["rawsendsize"] += strlen($proxydata);
$result["rawsendproxyheadersize"] = strlen($proxydata);
if (isset($options["sendratelimit"])) {
HTTPRateLimit($result["rawsendsize"], $result["sendstart"], $options["sendratelimit"]);
}
if (isset($options["debug_callback"])) {
$options["debug_callback"]("rawsend", $proxydata, $options["debug_callback_opts"]);
} else {
if ($debug) {
$result["rawsend"] .= $proxydata;
}
}
// Get the response - success is a 2xx code.
$options2 = array();
if (isset($options["recvratelimit"])) {
$options2["recvratelimit"] = $options["recvratelimit"];
}
if (isset($options["debug_callback"])) {
$options2["debug_callback"] = $options["debug_callback"];
$options2["debug_callback_opts"] = $options["debug_callback_opts"];
}
$info = HTTPGetResponse($fp, $debug, $options2, $startts, $timeout);
if (!$info["success"]) {
fclose($fp);
return $info;
}
if (substr($info["response"]["code"], 0, 1) != "2") {
fclose($fp);
return array("success" => false, "error" => HTTPTranslate("Expected a 200 response from the CONNECT request. Received: %s.", $info["response"]["line"]), "info" => $info, "errorcode" => "proxy_connect_tunnel");
}
$result["rawrecvsize"] += $info["rawrecvsize"];
$result["rawrecvheadersize"] += $info["rawrecvheadersize"];
if (isset($options["debug_callback"])) {
$options["debug_callback"]("rawrecv", $info["rawrecv"], $options["debug_callback_opts"]);
} else {
if ($debug) {
$result["rawrecv"] .= $info["rawrecv"];
}
}
}
} else {
if (!isset($options["connecttimeout"])) {
$options["connecttimeout"] = 10;
}
$timeleft = HTTPGetTimeLeft($startts, $timeout);
if ($timeleft !== false) {
$options["connecttimeout"] = min($options["connecttimeout"], $timeleft);
}
if (!function_exists("stream_socket_client")) {
$fp = @fsockopen($protocol . "://" . $host, $port, $errornum, $errorstr, $options["connecttimeout"]);
} else {
$context = @stream_context_create();
if ($secure && isset($options["sslopts"]) && is_array($options["sslopts"]) && ($protocol == "ssl" || $protocol == "tls")) {
HTTPProcessSSLOptions($options, "sslopts", $host);
foreach ($options["sslopts"] as $key => $val) {
@stream_context_set_option($context, "ssl", $key, $val);
}
}
$fp = @stream_socket_client($protocol . "://" . $host . ":" . $port, $errornum, $errorstr, $options["connecttimeout"], STREAM_CLIENT_CONNECT, $context);
$contextopts = stream_context_get_options($context);
if ($secure && isset($options["sslopts"]) && is_array($options["sslopts"]) && ($protocol == "ssl" || $protocol == "tls") && isset($contextopts["ssl"]["peer_certificate"])) {
if (isset($options["debug_callback"])) {
$options["debug_callback"]("peercert", @openssl_x509_parse($contextopts["ssl"]["peer_certificate"]), $options["debug_callback_opts"]);
}
}
}
if ($fp === false) {
return array("success" => false, "error" => HTTPTranslate("Unable to establish a connection to '%s'.", ($secure ? $protocol . "://" : "") . $host . ":" . $port), "info" => $errorstr . " (" . $errornum . ")", "errorcode" => "connect_failed");
}
$result["connected"] = microtime(true);
}
// Send the initial data.
$result["sendstart"] = microtime(true);
fwrite($fp, $data);
if ($timeout !== false && HTTPGetTimeLeft($startts, $timeout) == 0) {
fclose($fp);
return array("success" => false, "error" => HTTPTranslate("HTTP timeout exceeded."), "errorcode" => "timeout_exceeded");
}
$result["rawsendsize"] += strlen($data);
$result["rawsendheadersize"] = strlen($data);
if (isset($options["sendratelimit"])) {
HTTPRateLimit($result["rawsendsize"], $result["sendstart"], $options["sendratelimit"]);
}
if (isset($options["debug_callback"])) {
$options["debug_callback"]("rawsend", $data, $options["debug_callback_opts"]);
} else {
if ($debug) {
$result["rawsend"] .= $data;
}
}
// Send extra data.
if (isset($options["write_body_callback"])) {
while ($bodysize > 0) {
$bodysize2 = $bodysize;
if (!$options["write_body_callback"]($body, $bodysize2, $options["write_body_callback_opts"]) || strlen($body) > $bodysize) {
fclose($fp);
return array("success" => false, "error" => HTTPTranslate("HTTP write body callback function failed."), "errorcode" => "write_body_callback");
}
fwrite($fp, $body);
if ($timeout !== false && HTTPGetTimeLeft($startts, $timeout) == 0) {
fclose($fp);
return array("success" => false, "error" => HTTPTranslate("HTTP timeout exceeded."), "errorcode" => "timeout_exceeded");
}
$result["rawsendsize"] += strlen($body);
if (isset($options["sendratelimit"])) {
HTTPRateLimit($result["rawsendsize"], $result["sendstart"], $options["sendratelimit"]);
}
if (isset($options["debug_callback"])) {
$options["debug_callback"]("rawsend", $body, $options["debug_callback_opts"]);
} else {
if ($debug) {
$result["rawsend"] .= $body;
}
}
$bodysize -= strlen($body);
$body = "";
}
unset($options["write_body_callback"]);
unset($options["write_body_callback_opts"]);
} else {
if (isset($options["files"]) && count($options["files"])) {
foreach ($options["files"] as $info) {
$name = HTTPHeaderValueCleanup($info["name"]);
$name = str_replace("\"", "", $name);
$filename = HTTPFilenameSafe(HTTPExtractFilename($info["filename"]));
$type = HTTPHeaderValueCleanup($info["type"]);
$body = "--" . $mime . "\r\n";
$body .= "Content-Disposition: form-data; name=\"" . $name . "\"; filename=\"" . $filename . "\"\r\n";
$body .= "Content-Type: " . $type . "\r\n";
$body .= "\r\n";
fwrite($fp, $body);
if ($timeout !== false && HTTPGetTimeLeft($startts, $timeout) == 0) {
fclose($fp);
return array("success" => false, "error" => HTTPTranslate("HTTP timeout exceeded."), "errorcode" => "timeout_exceeded");
}
$result["rawsendsize"] += strlen($body);
if (isset($options["sendratelimit"])) {
HTTPRateLimit($result["rawsendsize"], $result["sendstart"], $options["sendratelimit"]);
}
if (isset($options["debug_callback"])) {
$options["debug_callback"]("rawsend", $body, $options["debug_callback_opts"]);
} else {
if ($debug) {
$result["rawsend"] .= $body;
}
}
if (isset($info["datafile"])) {
$fp2 = @fopen($info["datafile"], "rb");
if ($fp2 === false) {
fclose($fp);
return array("success" => false, "error" => HTTPTranslate("The file '%s' does not exist.", $info["datafile"]), "errorcode" => "file_open");
}
// Read/Write 65K at a time.
while ($info["filesize"] >= 65536) {
$body = fread($fp2, 65536);
if ($body === false || strlen($body) != 65536) {
fclose($fp2);
fclose($fp);
return array("success" => false, "error" => HTTPTranslate("A read error was encountered with the file '%s'.", $info["datafile"]), "errorcode" => "file_read");
}
fwrite($fp, $body);
if ($timeout !== false && HTTPGetTimeLeft($startts, $timeout) == 0) {
fclose($fp);
return array("success" => false, "error" => HTTPTranslate("HTTP timeout exceeded."), "errorcode" => "timeout_exceeded");
}
$result["rawsendsize"] += strlen($body);
if (isset($options["sendratelimit"])) {
HTTPRateLimit($result["rawsendsize"], $result["sendstart"], $options["sendratelimit"]);
}
if (isset($options["debug_callback"])) {
$options["debug_callback"]("rawsend", $body, $options["debug_callback_opts"]);
} else {
if ($debug) {
$result["rawsend"] .= $body;
}
}
$info["filesize"] -= 65536;
}
if ($info["filesize"] > 0) {
$body = fread($fp2, $info["filesize"]);
if ($body === false || strlen($body) != $info["filesize"]) {
fclose($fp2);
fclose($fp);
return array("success" => false, "error" => HTTPTranslate("A read error was encountered with the file '%s'.", $info["datafile"]), "errorcode" => "file_read");
}
} else {
$body = "";
}
fclose($fp2);
} else {
$body = $info["data"];
}
$body .= "\r\n";
fwrite($fp, $body);
if ($timeout !== false && HTTPGetTimeLeft($startts, $timeout) == 0) {
fclose($fp);
return array("success" => false, "error" => HTTPTranslate("HTTP timeout exceeded."), "errorcode" => "timeout_exceeded");
}
$result["rawsendsize"] += strlen($body);
if (isset($options["sendratelimit"])) {
HTTPRateLimit($result["rawsendsize"], $result["sendstart"], $options["sendratelimit"]);
}
if (isset($options["debug_callback"])) {
$options["debug_callback"]("rawsend", $body, $options["debug_callback_opts"]);
} else {
if ($debug) {
$result["rawsend"] .= $body;
}
}
}
$body = "--" . $mime . "--\r\n";
fwrite($fp, $body);
if ($timeout !== false && HTTPGetTimeLeft($startts, $timeout) == 0) {
fclose($fp);
return array("success" => false, "error" => HTTPTranslate("HTTP timeout exceeded."), "errorcode" => "timeout_exceeded");
}
$result["rawsendsize"] += strlen($body);
if (isset($options["sendratelimit"])) {
HTTPRateLimit($result["rawsendsize"], $result["sendstart"], $options["sendratelimit"]);
}
if (isset($options["debug_callback"])) {
$options["debug_callback"]("rawsend", $body, $options["debug_callback_opts"]);
} else {
if ($debug) {
$result["rawsend"] .= $body;
}
}
unset($options["files"]);
} else {
if ($bodysize > 0) {
fclose($fp);
return array("success" => false, "error" => HTTPTranslate("A weird internal HTTP error that should never, ever happen...just happened."), "errorcode" => "impossible");
}
}
}
// Get the response.
$info = HTTPGetResponse($fp, $debug, $options, $startts, $timeout);
fclose($fp);
$info["rawsendsize"] = $result["rawsendsize"];
if (!$info["success"]) {
return $info;
}
$result["rawrecvsize"] += $info["rawrecvsize"];
$result["rawrecvheadersize"] += $info["rawrecvheadersize"];
if ($debug) {
$result["rawrecv"] .= $info["rawrecv"];
}
$result["recvstart"] = $info["recvstart"];
$result["response"] = $info["response"];
$result["headers"] = $info["headers"];
$result["body"] = (string) $info["body"];
$result["endts"] = microtime(true);
return $result;
}
public function Process($url, $profile = "auto", $tempoptions = array())
{
$startts = microtime(true);
$redirectts = $startts;
if (isset($tempoptions["timeout"])) {
$timeout = $tempoptions["timeout"];
} else {
if (isset($this->data["httpopts"]["timeout"])) {
$timeout = $this->data["httpopts"]["timeout"];
} else {
$timeout = false;
}
}
if (!isset($this->data["httpopts"]["headers"])) {
$this->data["httpopts"]["headers"] = array();
}
$this->data["httpopts"]["headers"] = HTTPNormalizeHeaders($this->data["httpopts"]["headers"]);
unset($this->data["httpopts"]["method"]);
unset($this->data["httpopts"]["write_body_callback"]);
unset($this->data["httpopts"]["body"]);
unset($this->data["httpopts"]["postvars"]);
unset($this->data["httpopts"]["files"]);
$httpopts = $this->data["httpopts"];
$numfollow = $this->data["maxfollow"];
$numredirects = 0;
$totalrawsendsize = 0;
if (!isset($tempoptions["headers"])) {
$tempoptions["headers"] = array();
}
$tempoptions["headers"] = HTTPNormalizeHeaders($tempoptions["headers"]);
if (isset($tempoptions["headers"]["Referer"])) {
$this->data["referer"] = $tempoptions["headers"]["Referer"];
}
// If a referrer is specified, use it to generate an absolute URL.
if ($this->data["referer"] != "") {
$url = ConvertRelativeToAbsoluteURL($this->data["referer"], $url);
}
$urlinfo = ExtractURL($url);
do {
if (!isset($this->data["allowedprotocols"][$urlinfo["scheme"]]) || !$this->data["allowedprotocols"][$urlinfo["scheme"]]) {
return array("success" => false, "error" => HTTPTranslate("Protocol '%s' is not allowed in '%s'.", $urlinfo["scheme"], $url), "errorcode" => "allowed_protocols");
}
$filename = HTTPExtractFilename($urlinfo["path"]);
$pos = strrpos($filename, ".");
$fileext = $pos !== false ? strtolower(substr($filename, $pos + 1)) : "";
// Set up some standard headers.
$headers = array();
$profile = strtolower($profile);
$tempprofile = explode("-", $profile);
if (count($tempprofile) == 2) {
$profile = $tempprofile[0];
$fileext = $tempprofile[1];
}
if (substr($profile, 0, 2) == "ie" || $profile == "auto" && substr($this->data["useragent"], 0, 2) == "ie") {
if ($fileext == "css") {
$headers["Accept"] = "text/css";
} else {
if ($fileext == "png" || $fileext == "jpg" || $fileext == "jpeg" || $fileext == "gif" || $fileext == "svg") {
$headers["Accept"] = "image/png, image/svg+xml, image/*;q=0.8, */*;q=0.5";
} else {
if ($fileext == "js") {
$headers["Accept"] = "application/javascript, */*;q=0.8";
} else {
if ($this->data["referer"] != "" || $fileext == "" || $fileext == "html" || $fileext == "xhtml" || $fileext == "xml") {
$headers["Accept"] = "text/html, application/xhtml+xml, */*";
} else {
$headers["Accept"] = "*/*";
}
}
}
}
$headers["Accept-Language"] = "en-US";
$headers["User-Agent"] = GetWebUserAgent(substr($profile, 0, 2) == "ie" ? $profile : $this->data["useragent"]);
} else {
if ($profile == "firefox" || $profile == "auto" && $this->data["useragent"] == "firefox") {
if ($fileext == "css") {
$headers["Accept"] = "text/css,*/*;q=0.1";
} else {
if ($fileext == "png" || $fileext == "jpg" || $fileext == "jpeg" || $fileext == "gif" || $fileext == "svg") {
$headers["Accept"] = "image/png,image/*;q=0.8,*/*;q=0.5";
} else {
if ($fileext == "js") {
$headers["Accept"] = "*/*";
} else {
$headers["Accept"] = "text/html, application/xhtml+xml, */*";
}
}
}
$headers["Accept-Language"] = "en-us,en;q=0.5";
$headers["Cache-Control"] = "max-age=0";
$headers["User-Agent"] = GetWebUserAgent("firefox");
} else {
if ($profile == "opera" || $profile == "auto" && $this->data["useragent"] == "opera") {
// Opera has the right idea: Just send the same thing regardless of the request type.
$headers["Accept"] = "text/html, application/xml;q=0.9, application/xhtml+xml, image/png, image/webp, image/jpeg, image/gif, image/x-xbitmap, */*;q=0.1";
$headers["Accept-Language"] = "en-US,en;q=0.9";
$headers["Cache-Control"] = "no-cache";
$headers["User-Agent"] = GetWebUserAgent("opera");
} else {
if ($profile == "safari" || $profile == "chrome" || $profile == "auto" && ($this->data["useragent"] == "safari" || $this->data["useragent"] == "chrome")) {
if ($fileext == "css") {
$headers["Accept"] = "text/css,*/*;q=0.1";
} else {
if ($fileext == "png" || $fileext == "jpg" || $fileext == "jpeg" || $fileext == "gif" || $fileext == "svg" || $fileext == "js") {
$headers["Accept"] = "*/*";
} else {
$headers["Accept"] = "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8";
}
}
$headers["Accept-Charset"] = "ISO-8859-1,utf-8;q=0.7,*;q=0.3";
$headers["Accept-Language"] = "en-US,en;q=0.8";
$headers["User-Agent"] = GetWebUserAgent($profile == "safari" || $profile == "chrome" ? $profile : $this->data["useragent"]);
}
}
}
}
if ($this->data["referer"] != "") {
$headers["Referer"] = $this->data["referer"];
}
// Generate the final headers array.
$headers = array_merge($headers, $httpopts["headers"], $tempoptions["headers"]);
// Calculate the host and reverse host and remove port information.
$host = isset($headers["Host"]) ? $headers["Host"] : $urlinfo["host"];
$pos = strpos($host, "]");
if (substr($host, 0, 1) == "[" && $pos !== false) {
$host = substr($host, 0, $pos + 1);
} else {
$pos = strpos($host, ":");
if ($pos !== false) {
$host = substr($host, 0, $pos);
}
}
$dothost = $host;
if (substr($dothost, 0, 1) != ".") {
$dothost = "." . $dothost;
}
// Append cookies and delete old, invalid cookies.
$secure = $urlinfo["scheme"] == "https";
$cookiepath = $urlinfo["path"];
if ($cookiepath == "") {
$cookiepath = "/";
}
$pos = strrpos($cookiepath, "/");
if ($pos !== false) {
$cookiepath = substr($cookiepath, 0, $pos + 1);
}
$cookies = array();
foreach ($this->data["cookies"] as $domain => $paths) {
if (substr($domain, -strlen($dothost)) == $dothost) {
foreach ($paths as $path => $cookies2) {
if (substr($cookiepath, 0, strlen($path)) == $path) {
foreach ($cookies2 as $num => $info) {
if (isset($info["expires_ts"]) && $this->GetExpiresTimestamp($info["expires_ts"]) < time()) {
unset($this->data["cookies"][$domain][$path][$num]);
} else {
if ($secure || !isset($info["secure"])) {
$cookies[$info["name"]] = $info["value"];
}
}
}
if (!count($this->data["cookies"][$domain][$path])) {
unset($this->data["cookies"][$domain][$path]);
}
}
}
if (!count($this->data["cookies"][$domain])) {
unset($this->data["cookies"][$domain]);
}
}
}
$cookies2 = array();
foreach ($cookies as $name => $value) {
$cookies2[] = rawurlencode($name) . "=" . rawurlencode($value);
}
$headers["Cookie"] = implode("; ", $cookies2);
if ($headers["Cookie"] == "") {
unset($headers["Cookie"]);
}
// Generate the final options array.
$options = array_merge($httpopts, $tempoptions);
$options["headers"] = $headers;
if ($timeout !== false) {
$options["timeout"] = HTTPGetTimeLeft($startts, $timeout);
}
// Process the request.
$result = RetrieveWebpage($url, $options);
$result["url"] = $url;
$result["options"] = $options;
$result["firstreqts"] = $startts;
$result["numredirects"] = $numredirects;
$result["redirectts"] = $redirectts;
if (isset($result["rawsendsize"])) {
$totalrawsendsize += $result["rawsendsize"];
}
$result["totalrawsendsize"] = $totalrawsendsize;
unset($result["options"]["files"]);
unset($result["options"]["body"]);
if (!$result["success"]) {
return array("success" => false, "error" => HTTPTranslate("Unable to retrieve content. %s", $result["error"]), "info" => $result, "errorcode" => "retrievewebpage");
}
// Set up structures for another round.
if ($this->data["autoreferer"]) {
$this->data["referer"] = $url;
}
if (isset($result["headers"]["Location"]) && $this->data["followlocation"]) {
$redirectts = microtime(true);
unset($tempoptions["method"]);
unset($tempoptions["write_body_callback"]);
unset($tempoptions["body"]);
unset($tempoptions["postvars"]);
unset($tempoptions["files"]);
$tempoptions["headers"]["Referer"] = $url;
$url = $result["headers"]["Location"][0];
// Generate an absolute URL.
if ($this->data["referer"] != "") {
$url = ConvertRelativeToAbsoluteURL($this->data["referer"], $url);
}
$urlinfo2 = ExtractURL($url);
if (!isset($this->data["allowedredirprotocols"][$urlinfo2["scheme"]]) || !$this->data["allowedredirprotocols"][$urlinfo2["scheme"]]) {
return array("success" => false, "error" => HTTPTranslate("Protocol '%s' is not allowed. Server attempted to redirect to '%s'.", $urlinfo2["scheme"], $url), "info" => $result, "errorcode" => "allowed_redir_protocols");
}
if ($urlinfo2["host"] != $urlinfo["host"]) {
unset($tempoptions["headers"]["Host"]);
unset($httpopts["headers"]["Host"]);
}
$urlinfo = $urlinfo2;
$numredirects++;
}
// Handle any 'Set-Cookie' headers.
if (isset($result["headers"]["Set-Cookie"])) {
foreach ($result["headers"]["Set-Cookie"] as $cookie) {
$items = explode("; ", $cookie);
$item = trim(array_shift($items));
if ($item != "") {
$cookie2 = array();
$pos = strpos($item, "=");
if ($pos === false) {
$cookie2["name"] = urldecode($item);
$cookie2["value"] = "";
} else {
$cookie2["name"] = urldecode(substr($item, 0, $pos));
$cookie2["value"] = urldecode(substr($item, $pos + 1));
}
$cookie = array();
foreach ($items as $item) {
$item = trim($item);
if ($item != "") {
$pos = strpos($item, "=");
if ($pos === false) {
$cookie[strtolower(trim(urldecode($item)))] = "";
} else {
$cookie[strtolower(trim(urldecode(substr($item, 0, $pos))))] = urldecode(substr($item, $pos + 1));
}
}
}
$cookie = array_merge($cookie, $cookie2);
if (isset($cookie["expires"])) {
$ts = GetHTTPDateTimestamp($cookie["expires"]);
$cookie["expires_ts"] = gmdate("Y-m-d H:i:s", $ts === false ? time() - 24 * 60 * 60 : $ts);
} else {
if (isset($cookie["max-age"])) {
$cookie["expires_ts"] = gmdate("Y-m-d H:i:s", time() + (int) $cookie["max-age"]);
} else {
unset($cookie["expires_ts"]);
}
}
if (!isset($cookie["domain"])) {
$cookie["domain"] = $dothost;
}
if (substr($cookie["domain"], 0, 1) != ".") {
$cookie["domain"] = "." . $cookie["domain"];
}
if (!isset($cookie["path"])) {
$cookie["path"] = $cookiepath;
}
$cookie["path"] = str_replace("\\", "/", $cookie["path"]);
if (substr($cookie["path"], -1) != "/") {
$cookie["path"] = "/";
}
if (!isset($this->data["cookies"][$cookie["domain"]])) {
$this->data["cookies"][$cookie["domain"]] = array();
}
if (!isset($this->data["cookies"][$cookie["domain"]][$cookie["path"]])) {
$this->data["cookies"][$cookie["domain"]][$cookie["path"]] = array();
}
$this->data["cookies"][$cookie["domain"]][$cookie["path"]][] = $cookie;
}
}
}
if ($numfollow > 0) {
$numfollow--;
}
} while (isset($result["headers"]["Location"]) && $this->data["followlocation"] && $numfollow);
$result["numredirects"] = $numredirects;
$result["redirectts"] = $redirectts;
// Extract the forms from the page in a parsed format.
// Call WebBrowser::GenerateFormRequest() to prepare an actual request for Process().
if ($this->data["extractforms"]) {
$result["forms"] = $this->ExtractForms($result["url"], $result["body"]);
}
return $result;
}
function get_check_curl_multi_init_key($ch)
{
global $curl_init__map;
$key = get_curl_multi_init_key($ch);
if (!isset($curl_multi_init__map[$key])) {
throw new Exception(HTTPTranslate("cURL Emulator: Unable to find key mapping for resource."));
}
return $key;
}
