note 78046 added to ref.curl
| From: | OjasOjasvi at osu1 dot php dot net | Date: | Tue, 25 Sep 2007 17:52:57 +0000 |
| Subject: | note 78046 added to ref.curl | ||
| Groups: | php.notes | ||
| Request: | Send a blank email to php-notes+get-130781@lists.php.net to get a copy of this message | ||
<?
/*
* Author: Ojas Ojasvi
* Released: September 25, 2007
* Description: An example of the disguise_curl() function in order to grab contents from a website
while remaining fully camouflaged by using a fake user agent and fake headers.
*/
$url = 'http://www.php.net';
// disguises the curl using fake headers and a fake user agent.
function disguise_curl($url)
{
$curl = curl_init();
// Setup headers - I used the same headers from Firefox version 2.0.0.6
// below was split up because php.net said the line was too long. :/
$header[0] = "Accept: text/xml,application/xml,application/xhtml+xml,";
$header[0] .= "text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5";
$header[] = "Cache-Control: max-age=0";
$header[] = "Connection: keep-alive";
$header[] = "Keep-Alive: 300";
$header[] = "Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7";
$header[] = "Accept-Language: en-us,en;q=0.5";
$header[] = "Pragma: "; // browsers keep this blank.
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_USERAGENT, 'Googlebot/2.1 (+http://www.google.com/bot.html)');
curl_setopt($curl, CURLOPT_HTTPHEADER, $header);
curl_setopt($curl, CURLOPT_REFERER, 'http://www.google.com');
curl_setopt($curl, CURLOPT_ENCODING, 'gzip,deflate');
curl_setopt($curl, CURLOPT_AUTOREFERER, true);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_TIMEOUT, 10);
$html = curl_exec($curl); // execute the curl command
curl_close($curl); // close the connection
return $html; // and finally, return $html
}
// uses the function and displays the text off the website
$text = disguise_curl($url);
echo $text;
?>
Ojas Ojasvi
----
Server IP: 203.199.69.133
Probable Submitter: 59.176.111.201
----
Manual Page -- http://www.php.net/manual/en/ref.curl.php
Edit -- https://master.php.net/note/edit/78046
Del: integrated -- https://master.php.net/note/delete/78046/integrated
Del: useless -- https://master.php.net/note/delete/78046/useless
Del: bad code -- https://master.php.net/note/delete/78046/bad+code
Del: spam -- https://master.php.net/note/delete/78046/spam
Del: non-english -- https://master.php.net/note/delete/78046/non-english
Del: in docs -- https://master.php.net/note/delete/78046/in+docs
Del: other reasons-- https://master.php.net/note/delete/78046
Reject -- https://master.php.net/note/reject/78046
Search -- https://master.php.net/manage/user-notes.php