如何解析在PHP中使用GZip压缩的响应？

Question

我正在请求带有此处链接的api。

如您所见，响应是下载的.gz格式文件，实际上是xml格式文件。 我的问题是如何解析在PHP脚本中使用GZip压缩的响应并回显xml格式？ 谢谢！

header('content-type:text/html;charset=utf-8');
if (substr_count($_SERVER["HTTP_ACCEPT_ENCODING"], "gzip")) ob_start("ob_gzhandler"); else ob_start();
$appkey ='kwaninmacau';
$url ='http://services.eoddsmaker.net/demo/feeds/V1.0/markets.ashx';
$params ='l=1&bid=43&sid=50&cid=58&lid=10&u='.$appkey.'&p='.$appkey;
echo datafeedurl($url,$params,0);
function datafeedurl($url,$params=false,$ispost=0){
..
curl_setopt( $ch, CURLOPT_ENCODING , "gzip");
}

Answer 1

引用“如您所见，响应是.gz格式”，不，不是。 服务器说Content-Type：application / x-gzip，但这是错误的！ 它是一个XML文件，名称为“ markets_20151127T065210.gz”

引用“如何解析在php脚本中使用GZip压缩的响应并回显xml格式？”您的xml在第4行中位于$ xml中：

<?php
$ch=hhb_curl_init();
$xml=hhb_curl_exec2($ch,'http://services.eoddsmaker.net/demo/feeds/V1.0/markets.ashx?l=1&bid=43&sid=50&cid=58&lid=10&u=kwaninmacau&p=kwaninmacau',$headers,$cookies,$requeststring);
var_dump('headers:',$headers,'cookies:',$cookies,'requeststring:',$requeststring,'xml:',$xml);

function hhb_curl_init($custom_options_array = array())
{
    if (empty($custom_options_array)) {
        $custom_options_array = array();
        //i feel kinda bad about this.. argv[1] of curl_init wants a string(url), or NULL
        //at least i want to allow NULL aswell :/
    }
    if (!is_array($custom_options_array)) {
        throw new InvalidArgumentException('$custom_options_array must be an array!');
    }
    ;
    $options_array = array(
        CURLOPT_AUTOREFERER => true,
        CURLOPT_BINARYTRANSFER => true,
        CURLOPT_COOKIESESSION => true,
        CURLOPT_FOLLOWLOCATION => true,
        CURLOPT_FORBID_REUSE => false,
        CURLOPT_HTTPGET => true,
        CURLOPT_RETURNTRANSFER => true,
        CURLOPT_SSL_VERIFYPEER => false,
        CURLOPT_CONNECTTIMEOUT => 10,
        CURLOPT_TIMEOUT => 11,
        CURLOPT_ENCODING => ""
        //CURLOPT_REFERER=>'example.org',
        //CURLOPT_USERAGENT=>'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:36.0) Gecko/20100101 Firefox/36.0'
    );
    if (!array_key_exists(CURLOPT_COOKIEFILE, $custom_options_array)) {
        //do this only conditionally because tmpfile() call..
        static $curl_cookiefiles_arr = array(); //workaround for https://bugs.php.net/bug.php?id=66014
        $curl_cookiefiles_arr[]            = $options_array[CURLOPT_COOKIEFILE] = tmpfile();
        $options_array[CURLOPT_COOKIEFILE] = stream_get_meta_data($options_array[CURLOPT_COOKIEFILE]);
        $options_array[CURLOPT_COOKIEFILE] = $options_array[CURLOPT_COOKIEFILE]['uri'];

    }
    //we can't use array_merge() because of how it handles integer-keys, it would/could cause corruption
    foreach ($custom_options_array as $key => $val) {
        $options_array[$key] = $val;
    }
    unset($key, $val, $custom_options_array);
    $curl = curl_init();
    if($curl===false){
        throw new RuntimeException('could not create a curl handle! curl_init() returned false');
    }
    if(false===curl_setopt_array($curl, $options_array)){
        $errno=curl_errno($curl);
        $error=curl_error($curl);
        throw new RuntimeException('could not set options on curl! curl_setopt_array returned false. curl_errno :'.$curl_errno.'. curl_error: '.$curl_error);
    }
    return $curl;
}
function hhb_curl_exec($ch, $url)
{
    static $hhb_curl_domainCache = "";//warning, this will not work properly with 2 different curl's visiting 2 different sites. 
    //should probably use SplObjectStorage here, so each curl can have its own cache..
    //$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;
        }
    }
    ;

    if(false===curl_setopt($ch, CURLOPT_URL, $url)){
        $errno=curl_errno($curl);
        $error=curl_error($curl);
        throw new RuntimeException('could not set CURLOPT_URL on curl! curl_setopt returned false. curl_errno :'.$curl_errno.'. curl_error: '.$curl_error.'. url: '.var_export($url,true));
    }
    $html = curl_exec($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 $html;
}
function hhb_curl_exec2($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!');
    }
    $verbosefileh = tmpfile();
    if($verbosefileh===false){
        throw new RuntimeException('can not create a tmpfile for curl\'s stderr. tmpfile returned false');
    }
    $verbosefile  = stream_get_meta_data($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,&$len)
    {
        $len=0;
        $ret = "";
        $i   = 0;
        for ($i = 0; $i < strlen($str); ++$i) {
            ++$len;
            if ($str[$i] === ' ') {
                continue;
            }
            if ($str[$i] === '=') {
                --$len;
                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:")));
        $len=0;
        while (strlen($header) > 0) {
            $cookiename                 = $grabCookieName($header,$len);
            $returnCookies[$cookiename] = '';
            $header                     = substr($header, $len + 1); //also remove the = 
            if (strlen($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;
}

Answer 2

您可以将以下代码用于Gzip

curl_setopt($ch,CURLOPT_ENCODING , "gzip");