如何找到使用cURL重定向到的位置？

我正在尝试使curl遵循重定向，但无法完全正常工作。我有一个字符串，我想将它作为GET参数发送到服务器并获取结果URL。

例：

字符串= Kobold害虫
网址= www.wowhead.com/search?q=Kobold+Worker

如果您转到该URL，它将把您重定向到“ www.wowhead.com/npc=257”。我希望curl将此URL返回到我的PHP代码，以便我可以提取“ npc = 257”并使用它。

当前代码：

function npcID($name) {
    $urltopost = "http://www.wowhead.com/search?q=" . $name;
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.1) Gecko/20061204 Firefox/2.0.0.1");
    curl_setopt($ch, CURLOPT_URL, $urltopost);
    curl_setopt($ch, CURLOPT_REFERER, "http://www.wowhead.com");
    curl_setopt($ch, CURLOPT_HTTPHEADER, Array("Content-Type:application/x-www-form-urlencoded"));
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, TRUE);
    return curl_getinfo($ch, CURLINFO_EFFECTIVE_URL);
}

但是，这将返回www.wowhead.com/search?q=Kobold+Worker而不是www.wowhead.com/npc=257。

我怀疑PHP会在外部重定向发生之前返回。我怎样才能解决这个问题？

要使cURL跟随重定向，请使用：

curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);

嗯...我认为您实际上并没有执行卷曲...请尝试：

curl_exec($ch);

...在设置选项之后，在curl_getinfo()通话之前。

编辑：如果您只是想找出页面重定向到的位置，我将在此处使用建议，然后使用Curl抓取标题并从中提取Location：标题：

$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_HEADER, true);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, false);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
$result = curl_exec($ch);
if (preg_match('~Location: (.*)~i', $result, $match)) {
   $location = trim($match[1]);
}

添加此行以卷曲inizialization

curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);

并在curl_close之前使用getinfo

$redirectURL = curl_getinfo($ch,CURLINFO_EFFECTIVE_URL );

es：

$ch = curl_init($url);
curl_setopt($ch, CURLOPT_HEADER, false);
curl_setopt($ch, CURLOPT_USERAGENT,'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.13) Gecko/20080311 Firefox/2.0.0.13');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_BINARYTRANSFER, true);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT ,0); 
curl_setopt($ch, CURLOPT_TIMEOUT, 60);
$html = curl_exec($ch);
$redirectURL = curl_getinfo($ch,CURLINFO_EFFECTIVE_URL );
curl_close($ch);

上面的答案在我的一台服务器上不适合我，这对于basedir来说有点麻烦，所以我重新整理了一下。以下代码可在我的所有服务器上使用。

$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_HEADER, true);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, false);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, TRUE);
$a = curl_exec($ch);
curl_close( $ch ); 
// the returned headers
$headers = explode("\n",$a);
// if there is no redirection this will be the final url
$redir = $url;
// loop through the headers and check for a Location: str
$j = count($headers);
for($i = 0; $i < $j; $i++){
// if we find the Location header strip it and fill the redir var       
if(strpos($headers[$i],"Location:") !== false){
        $redir = trim(str_replace("Location:","",$headers[$i]));
        break;
    }
}
// do whatever you want with the result
echo redir;

此处选择的答案很不错，但区分大小写，无法防止相对location:标头（某些站点可以这样做）或可能实际上Location:在其内容中包含该短语的页面……（zillow当前可以做到）。

有点草率，但是进行了一些快速编辑以使其更聪明：

function getOriginalURL($url) {
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_HEADER, true);
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, false);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, TRUE);
    $result = curl_exec($ch);
    $httpStatus = curl_getinfo($ch, CURLINFO_HTTP_CODE);
    curl_close($ch);

    // if it's not a redirection (3XX), move along
    if ($httpStatus < 300 || $httpStatus >= 400)
        return $url;

    // look for a location: header to find the target URL
    if(preg_match('/location: (.*)/i', $result, $r)) {
        $location = trim($r[1]);

        // if the location is a relative URL, attempt to make it absolute
        if (preg_match('/^\/(.*)/', $location)) {
            $urlParts = parse_url($url);
            if ($urlParts['scheme'])
                $baseURL = $urlParts['scheme'].'://';

            if ($urlParts['host'])
                $baseURL .= $urlParts['host'];

            if ($urlParts['port'])
                $baseURL .= ':'.$urlParts['port'];

            return $baseURL.$location;
        }

        return $location;
    }
    return $url;
}

请注意，这仍然只进行1个重定向。要深入了解，您实际上需要获取内容并遵循重定向。

有时您需要获取HTTP标头，但同时又不想返回这些标头。**

该框架负责处理cookie和使用递归的HTTP重定向。这里的主要思想是避免将HTTP标头返回给客户端代码。

您可以在其上建立一个非常强大的curl类。添加POST功能等

<?php

class curl {

  static private $cookie_file            = '';
  static private $user_agent             = '';  
  static private $max_redirects          = 10;  
  static private $followlocation_allowed = true;

  function __construct()
  {
    // set a file to store cookies
    self::$cookie_file = 'cookies.txt';

    // set some general User Agent
    self::$user_agent = 'Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)';

    if ( ! file_exists(self::$cookie_file) || ! is_writable(self::$cookie_file))
    {
      throw new Exception('Cookie file missing or not writable.');
    }

    // check for PHP settings that unfits
    // correct functioning of CURLOPT_FOLLOWLOCATION 
    if (ini_get('open_basedir') != '' || ini_get('safe_mode') == 'On')
    {
      self::$followlocation_allowed = false;
    }    
  }

  /**
   * Main method for GET requests
   * @param  string $url URI to get
   * @return string      request's body
   */
  static public function get($url)
  {
    $process = curl_init($url);    

    self::_set_basic_options($process);

    // this function is in charge of output request's body
    // so DO NOT include HTTP headers
    curl_setopt($process, CURLOPT_HEADER, 0);

    if (self::$followlocation_allowed)
    {
      // if PHP settings allow it use AUTOMATIC REDIRECTION
      curl_setopt($process, CURLOPT_FOLLOWLOCATION, true);
      curl_setopt($process, CURLOPT_MAXREDIRS, self::$max_redirects); 
    }
    else
    {
      curl_setopt($process, CURLOPT_FOLLOWLOCATION, false);
    }

    $return = curl_exec($process);

    if ($return === false)
    {
      throw new Exception('Curl error: ' . curl_error($process));
    }

    // test for redirection HTTP codes
    $code = curl_getinfo($process, CURLINFO_HTTP_CODE);
    if ($code == 301 || $code == 302)
    {
      curl_close($process);

      try
      {
        // go to extract new Location URI
        $location = self::_parse_redirection_header($url);
      }
      catch (Exception $e)
      {
        throw $e;
      }

      // IMPORTANT return 
      return self::get($location);
    }

    curl_close($process);

    return $return;
  }

  static function _set_basic_options($process)
  {

    curl_setopt($process, CURLOPT_USERAGENT, self::$user_agent);
    curl_setopt($process, CURLOPT_COOKIEFILE, self::$cookie_file);
    curl_setopt($process, CURLOPT_COOKIEJAR, self::$cookie_file);
    curl_setopt($process, CURLOPT_RETURNTRANSFER, 1);
    // curl_setopt($process, CURLOPT_VERBOSE, 1);
    // curl_setopt($process, CURLOPT_SSL_VERIFYHOST, false);
    // curl_setopt($process, CURLOPT_SSL_VERIFYPEER, false);
  }

  static function _parse_redirection_header($url)
  {
    $process = curl_init($url);    

    self::_set_basic_options($process);

    // NOW we need to parse HTTP headers
    curl_setopt($process, CURLOPT_HEADER, 1);

    $return = curl_exec($process);

    if ($return === false)
    {
      throw new Exception('Curl error: ' . curl_error($process));
    }

    curl_close($process);

    if ( ! preg_match('#Location: (.*)#', $return, $location))
    {
      throw new Exception('No Location found');
    }

    if (self::$max_redirects-- <= 0)
    {
      throw new Exception('Max redirections reached trying to get: ' . $url);
    }

    return trim($location[1]);
  }

}

尽管我真的很喜欢这种方式，但这里的很多正则表达式对我来说可能更稳定：

$resultCurl=curl_exec($curl); //get curl result
//Optional line if you want to store the http status code
$headerHttpCode=curl_getinfo($curl,CURLINFO_HTTP_CODE);

//let's use dom and xpath
$dom = new \DOMDocument();
libxml_use_internal_errors(true);
$dom->loadHTML($resultCurl, LIBXML_HTML_NODEFDTD);
libxml_use_internal_errors(false);
$xpath = new \DOMXPath($dom);
$head=$xpath->query("/html/body/p/a/@href");

$newUrl=$head[0]->nodeValue;

位置部分是apache发送的HTML中的链接。因此，Xpath非常适合恢复它。

您可以使用：

$redirectURL = curl_getinfo($ch,CURLINFO_REDIRECT_URL);