Im trying to use CURL to scrape the results from the page http://adlab.msn.com/Online-Commercial-Intention/Default.aspx
My understanding, is that i visit this page, it places cookie info and sets a few variables. I enter my query, select the query radio option, and click go.
The problem, is that its not working the way that it does through the website as im trying to get it to using the code below.
Ive tweaked several things, but im posting here in hopes someone can find what im missing.
This is my code as it stands now:
include("simple_html_dom.php");
$ckfile = tempnam ("/tmp", "CURLCOOKIE");
$query = $_GET['query'];
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, "http://adlab.msn.com/Online-Commercial-Intention/default.aspx");
curl_setopt($ch, CURLOPT_HEADER, 1);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch, CURLOPT_COOKIEJAR, $ckfile);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.3) Gecko/20070309 Firefox/2.0.0.3");
$pagetext1 = curl_exec($ch);
curl_exec($ch);
$html2 = str_get_html($pagetext1);
$viewstate = $html2->find('input[id=__VIEWSTATE]', 1)->plaintext;
echo $query."<br>".$viewstate."<br>";
$params = array(
'__EVENTTARGET' => "",
'__EVENTARGUMENT' => "",
'__LASTFOCUS' => "",
'__VIEWSTATE' => "$viewstate",
'MyMaster%3ADemoPageContent%3AtxtQuery' => "$query",
'MyMaster%3ADemoPageContent%3Alan' => "QueryRadio",
'MyMaster%3ADemoPageContent%3AgoButton.x' => "17",
'MyMaster%3ADemoPageContent%3AgoButton.y' => "12",
'MyMaster%3ADemoPageContent%3AidQuery' => "$query",
'MyMaster%3AHiddenKeywordTextBox' => "",
);
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, 'http://adlab.msn.com/Online-Commercial-Intention/default.aspx');
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_REFERER, 'http://adlab.msn.com/Online-Commercial-Intention/default.aspx');
curl_setopt($ch, CURLOPT_POSTFIELDS, '$params');
curl_setopt($ch, CURLOPT_HEADER, 1);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt ($ch, CURLOPT_COOKIEFILE, $ckfile);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.3) Gecko/20070309 Firefox/2.0.0.3");
$pagetext = curl_exec($ch);
curl_exec($ch);
// echo $ckfile;
$html = str_get_html($pagetext);
$ret = $html->find('.intentionLabel', 1)->plaintext;
echo $ret."<br><br><br>";
echo $pagetext;
