Cannot get an http markup of google [duplicate] - php

Question

I'm trying to make curl follow a redirect but I can't quite get it to work right. I have a string that I want to send as a GET param to a server and get the resulting URL.
Example:
String = Kobold Vermin
Url = www.wowhead.com/search?q=Kobold+Worker
If you go to that url it will redirect you to "www.wowhead.com/npc=257". I want curl to return this URL to my PHP code so that i can extract the "npc=257" and use it.
Current code:
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);
}
This however returns www.wowhead.com/search?q=Kobold+Worker and not www.wowhead.com/npc=257.
I suspect PHP is returning before the external redirect happens. How can I fix this?

Answer 1

To make cURL follow a redirect, use:
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
Erm... I don't think you're actually executing the curl... Try:
curl_exec($ch);
...after setting the options, and before the curl_getinfo() call.
EDIT: If you just want to find out where a page redirects to, I'd use the advice here, and just use Curl to grab the headers and extract the Location: header from them:
$ch = curl_init();
curl_setopt($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]);
}

Answer 2

Add this line to curl inizialization
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
and use getinfo before curl_close
$redirectURL = curl_getinfo($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($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT ,0);
curl_setopt($ch, CURLOPT_TIMEOUT, 60);
$html = curl_exec($ch);
$redirectURL = curl_getinfo($ch,CURLINFO_EFFECTIVE_URL );
curl_close($ch);

Answer 3

The answer above didn't work for me on one of my servers, something to to with basedir, so I re-hashed it a little. The code below works on all my servers.
$ch = curl_init();
curl_setopt($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;

Answer 4

The chosen answer here is decent but its case sensitive, doesn't protect against relative location: headers (which some sites do) or pages that might actually have the phrase Location: in their content... (which zillow currently does).
A bit sloppy, but a couple quick edits to make this a bit smarter are:
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;
}
Note that this still only goes 1 redirection deep. To go deeper, you actually need to get the content and follow the redirects.

Answer 5

Sometimes you need to get HTTP headers but at the same time you don't want return those headers.**
This skeleton takes care of cookies and HTTP redirects using recursion. The main idea here is to avoid return HTTP headers to the client code.
You can build a very strong curl class over it. Add POST functionality, etc.
<?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]);
}
}

Answer 6

You can use:
$redirectURL = curl_getinfo($ch,CURLINFO_REDIRECT_URL);

Answer 7

Lot's of regex here, despite the fact i really like them this way might be more stable to me:
$resultCurl=curl_exec($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;
The location part is a link in the HTML sent by apache. So Xpath is perfect to recover it.