1

<?php
/************************************************
* ASP.NET web site scraping script;
* Developed by MishaInTheCloud.com
* Copyright 2009 MishaInTheCloud.com. All rights reserved.
* The use of this script is governed by the CodeProject Open License
* See the following link for full details on use and restrictions.
*   http://www.codeproject.com/info/cpol10.aspx
*
* The above copyright notice must be included in any reproductions of this script.
************************************************/

/************************************************
* values used throughout the script
************************************************/
// urls to call - the login page and the secured page
$urlLogin = "urldellogin";
//$urlSecuredPage = "urlavisitar";
$urlSecuredPage = 'urlavisitar';

// POST names and values to support login
$nameUsername='ctl00$ContentPlaceHolder1$CtrlLogin1$tbNifEmail';       // the name of the username textbox on the login
 form
$namePassword='ctl00$ContentPlaceHolder1$CtrlLogin1$tbPassword';       // the name of the password textbox on the login
 form
$valLoginBtn='ctl00$ContentPlaceHolder1$CtrlLogin1$btnValidar';          // the name of the login button (submit) on th
e login form
$valUsername ='eluser';        // the value to submit for the username
$valPassword ='laclave';        // the value to submit for the password
$nameLoginBtn ='__EVENTTARGET';             // the text value of the login button itself
$evArgName = '__EVENTARGUMENT';
$evArgValue = '';
$pubName = 'ctl00$ContentPlaceHolder1$hdnSelectedPubli';
$pubValue = '';

// the path to a file we can read/write; this will
// store cookies we need for accessing secured pages
$cookieFile = './ctemp/cookie.txt';

// regular expressions to parse out the special ASP.NET
// values for __VIEWSTATE and __EVENTVALIDATION
$regexViewstate = '/__VIEWSTATE\" value=\"(.*)\"/i';
$regexEventVal  = '/__EVENTVALIDATION\" value=\"(.*)\"/i';


/************************************************
* utility function: regexExtract
*    use the given regular expression to extract
*    a value from the given text;  $regs will
*    be set to an array of all group values
*    (assuming a match) and the nthValue item
*    from the array is returned as a string
************************************************/
function regexExtract($text, $regex, $regs, $nthValue)
{
if (preg_match($regex, $text, $regs)) {
 $result = $regs[$nthValue];
}
else {
 $result = "";
/************************************************
* initialize a curl handle; we'll use this
*   handle throughout the script
************************************************/
$ch = curl_init();


/************************************************
* first, issue a GET call to the ASP.NET login
*   page.  This is necessary to retrieve the
*   __VIEWSTATE and __EVENTVALIDATION values
*   that the server issues
************************************************/
curl_setopt($ch, CURLOPT_URL, $urlLogin);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, TRUE);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, TRUE);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE);
$data=curl_exec($ch);

// from the returned html, parse out the __VIEWSTATE and
// __EVENTVALIDATION values
$viewstate = regexExtract($data,$regexViewstate,$regs,1);
$eventval = regexExtract($data, $regexEventVal,$regs,1);


/************************************************
* now issue a second call to the Login page;
*   this time, it will be a POST; we'll send back
*   as post data the __VIEWSTATE and __EVENTVALIDATION
*   values the server previously sent us, as well as the
*   username/password.  We'll also set up a cookie
*   jar to retrieve the authentication cookie that
*   the server will generate and send us upon login.
************************************************/
$postData = '__VIEWSTATE='.rawurlencode($viewstate)
          .'&__EVENTVALIDATION='.rawurlencode($eventval)
          .'&'.$nameUsername.'='.$valUsername
          .'&'.$namePassword.'='.$valPassword
          .'&'.$nameLoginBtn.'='.$valLoginBtn
          .'&'.$evArgName.'='.$evArgValue
          .'&'.$pubName.'='.$pubValue
          ;

curl_setOpt($ch, CURLOPT_POST, TRUE);
curl_setopt($ch, CURLOPT_POSTFIELDS, $postData);
curl_setopt($ch, CURLOPT_URL, $urlLogin);
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookieFile);

#curl_setopt($ch, CURLOPT_HEADER, false);
#curl_setopt($ch, CURLOPT_NOBODY, false);
#curl_setopt($ch, CURLOPT_URL, $urlLogin);
#curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 0);

#curl_setopt($ch, CURLOPT_COOKIEJAR, $cookieFile);
//set the cookie the site has for certain features, this is optional
#curl_setopt($ch, CURLOPT_COOKIE, "cookiename=0");
#curl_setopt($ch, CURLOPT_USERAGENT,
#    "Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.7.12) Gecko/20050915 Firefox/1.0.7");
#curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
#curl_setopt($ch, CURLOPT_REFERER, $_SERVER['REQUEST_URI']);
#curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, 0);
#curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 0);

#curl_setopt($ch, CURLOPT_CUSTOMREQUEST, "POST");
#curl_setopt($ch, CURLOPT_POST, 1);
#curl_setopt($ch, CURLOPT_POSTFIELDS, $postData);

$data = curl_exec($ch);

/************************************************
* with the authentication cookie in the jar,
* we'll now issue a GET to the secured page;
* we set curl's COOKIEFILE option to the same
* file we used for the jar before to ensure the
* authentication cookie is sent back to the
* server
************************************************/
curl_setOpt($ch, CURLOPT_POST, FALSE);
curl_setopt($ch, CURLOPT_URL, $urlSecuredPage);
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookieFile);

$data = curl_exec($ch);

// at this point the secured page may be parsed for
// values, or additional POSTS made to submit parameters
// and retrieve data.  For this sample, we'll just
// echo the results.
echo $data;



/************************************************
* that's it! Close the curl handle
************************************************/
curl_close($ch);


?>