I'm new to using cURL and its hard to find good resources for it.
What I'm trying to do is login to a remote site, by having curl do the login form and then send back that it was successful.
The code I have doesn't seem to work and only tries to show the main page of the site.
$username="mylogin#gmail.com";
$password="mypassword";
$url="http://www.myremotesite.com/index.php?page=login";
$cookie="cookie.txt";
$postdata = "email=".$username."&password=".$password;
$ch = curl_init();
curl_setopt ($ch, CURLOPT_URL, $url);
curl_setopt ($ch, CURLOPT_SSL_VERIFYPEER, FALSE);
curl_setopt ($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.6) Gecko/20070725 Firefox/2.0.0.6");
curl_setopt ($ch, CURLOPT_TIMEOUT, 60);
curl_setopt ($ch, CURLOPT_FOLLOWLOCATION, 0);
curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt ($ch, CURLOPT_COOKIEJAR, $cookie);
curl_setopt ($ch, CURLOPT_REFERER, $url);
curl_setopt ($ch, CURLOPT_POSTFIELDS, $postdata);
curl_setopt ($ch, CURLOPT_POST, 1);
$result = curl_exec ($ch);
echo $result;
curl_close($ch);
What am I doing wrong. After this is working I want to redirect to another page and get content from my site.
I had let this go for a good while but revisited it later. Since this question is viewed regularly. This is eventually what I ended up using that worked for me.
define("DOC_ROOT","/path/to/html");
//username and password of account
$username = trim($values["email"]);
$password = trim($values["password"]);
//set the directory for the cookie using defined document root var
$path = DOC_ROOT."/ctemp";
//build a unique path with every request to store. the info per user with custom func. I used this function to build unique paths based on member ID, that was for my use case. It can be a regular dir.
//$path = build_unique_path($path); // this was for my use case
//login form action url
$url="https://www.example.com/login/action";
$postinfo = "email=".$username."&password=".$password;
$cookie_file_path = $path."/cookie.txt";
$ch = curl_init();
curl_setopt($ch, CURLOPT_HEADER, false);
curl_setopt($ch, CURLOPT_NOBODY, false);
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 0);
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_file_path);
//set the cookie the site has for certain features, this is optional
curl_setopt($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, $postinfo);
curl_exec($ch);
//page with the content I want to grab
curl_setopt($ch, CURLOPT_URL, "http://www.example.com/page/");
//do stuff with the info with DomDocument() etc
$html = curl_exec($ch);
curl_close($ch);
Update: This code was never meant to be a copy and paste. It was to show how I used it for my specific use case. You should adapt it to your code as needed. Such as directories, vars etc
I had same question and I found this answer on this website.
And I changed it just a little bit (the curl_close at last line)
$username = 'myuser';
$password = 'mypass';
$loginUrl = 'http://www.example.com/login/';
//init curl
$ch = curl_init();
//Set the URL to work with
curl_setopt($ch, CURLOPT_URL, $loginUrl);
// ENABLE HTTP POST
curl_setopt($ch, CURLOPT_POST, 1);
//Set the post parameters
curl_setopt($ch, CURLOPT_POSTFIELDS, 'user='.$username.'&pass='.$password);
//Handle cookies for the login
curl_setopt($ch, CURLOPT_COOKIEJAR, 'cookie.txt');
//Setting CURLOPT_RETURNTRANSFER variable to 1 will force cURL
//not to print out the results of its query.
//Instead, it will return the results as a string return value
//from curl_exec() instead of the usual true/false.
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
//execute the request (the login)
$store = curl_exec($ch);
//the login is now done and you can continue to get the
//protected content.
//set the URL to the protected file
curl_setopt($ch, CURLOPT_URL, 'http://www.example.com/protected/download.zip');
//execute the request
$content = curl_exec($ch);
curl_close($ch);
//save the data to disk
file_put_contents('~/download.zip', $content);
I think this was what you were looking for.Am I right?
And one useful related question. About how to keep a session alive in cUrl: https://stackoverflow.com/a/13020494/2226796
View the source of the login page. Look for the form HTML tag. Within that tag is something that will look like action= Use that value as $url, not the URL of the form itself.
Also, while you are there, verify the input boxes are named what you have them listed as.
For example, a basic login form will look similar to:
<form method='post' action='postlogin.php'>
Email Address: <input type='text' name='email'>
Password: <input type='password' name='password'>
</form>
Using the above form as an example, change your value of $url to:
$url="http://www.myremotesite.com/postlogin.php";
Verify the values you have listed in $postdata:
$postdata = "email=".$username."&password=".$password;
and it should work just fine.
This is how I solved this in ImpressPages:
//initial request with login data
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, 'http://www.example.com/login.php');
curl_setopt($ch, CURLOPT_USERAGENT,'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/32.0.1700.107 Chrome/32.0.1700.107 Safari/537.36');
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, "username=XXXXX&password=XXXXX");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_COOKIESESSION, true);
curl_setopt($ch, CURLOPT_COOKIEJAR, 'cookie-name'); //could be empty, but cause problems on some hosts
curl_setopt($ch, CURLOPT_COOKIEFILE, '/var/www/ip4.x/file/tmp'); //could be empty, but cause problems on some hosts
$answer = curl_exec($ch);
if (curl_error($ch)) {
echo curl_error($ch);
}
//another request preserving the session
curl_setopt($ch, CURLOPT_URL, 'http://www.example.com/profile');
curl_setopt($ch, CURLOPT_POST, false);
curl_setopt($ch, CURLOPT_POSTFIELDS, "");
$answer = curl_exec($ch);
if (curl_error($ch)) {
echo curl_error($ch);
}
Panama Jack Example not work for me - Give Fatal error: Call to undefined function build_unique_path(). I used this code - (more simple - my opinion) :
// options$login_email = 'alabala#gmail.com';$login_pass = 'alabala4807';$cookie_file_path = "/tmp/cookies.txt";$LOGINURL = "http://alabala.com/index.php?route=account/login"; $agent = "Nokia-Communicator-WWW-Browser/2.0 (Geos 3.0 Nokia-9000i)";// begin script$ch = curl_init();// extra headers$headers[] = "Accept: */*";$headers[] = "Connection: Keep-Alive";// basic curl options for all requestscurl_setopt($ch, CURLOPT_HTTPHEADER, $headers);curl_setopt($ch, CURLOPT_HEADER, 0);curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 0);curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false); curl_setopt($ch, CURLOPT_USERAGENT, $agent); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1); curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_file_path); curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_file_path); // set first URLcurl_setopt($ch, CURLOPT_URL, $LOGINURL);// execute session to get cookies and required form inputs$content = curl_exec($ch); // grab the hidden inputs from the form required to login$fields = getFormFields($content);$fields['email'] = $login_email;$fields['password'] = $login_pass;// set postfields using what we extracted from the form$POSTFIELDS = http_build_query($fields); // change URL to login URLcurl_setopt($ch, CURLOPT_URL, $LOGINURL); // set post optionscurl_setopt($ch, CURLOPT_POST, 1); curl_setopt($ch, CURLOPT_POSTFIELDS, $POSTFIELDS); // perform login$result = curl_exec($ch); print $result; function getFormFields($data){ if (preg_match('/()/is', $data, $matches)) { $inputs = getInputs($matches[1]); return $inputs; } else { die('didnt find login form'); }}function getInputs($form){ $inputs = array(); $elements = preg_match_all("/(]+>)/is", $form, $matches); if ($elements > 0) { for($i = 0;$i $el = preg_replace('/\s{2,}/', ' ', $matches[1][$i]); if (preg_match('/name=(?:["\'])?([^"\'\s]*)/i', $el, $name)) { $name = $name[1]; $value = ''; if (preg_match('/value=(?:["\'])?([^"\'\s]*)/i', $el, $value)) { $value = $value[1]; } $inputs[$name] = $value; } } } return $inputs;}$grab_url='http://grab.url/alabala';//page with the content I want to grabcurl_setopt($ch, CURLOPT_URL, $grab_url);//do stuff with the info with DomDocument() etc$html = curl_exec($ch);curl_close($ch);var_dump($html); die;
Related
Hey I am trying to login to the NJIT site to check if username and password are correct. For some reason I keep getting rejected even if I use correct credentials. Also how do I strip the $result to check if it contains "Fail" which would mean the credentials were wrong. Here is my code.
Main:
<?PHP
session_start();
require_once('functions.php');
//$UCID=$_POST['UCID'];
//$Pass=$_POST['Pass'];
$UCID="jko328";
$Pass="password";
$credentialsNJIT="user=".$UCID."&pass=".$Pass;
$njit_url="https://cp4.njit.edu/cp/home/login";
$njit_result=goCurlNJIT($credentialsNJIT, $njit_url);
echo $result;
?>
Here is the cURL function:
function goCurlNJIT($postdata, $url){
session_start();
$ch = curl_init();
curl_setopt ($ch, CURLOPT_URL, $url);
curl_setopt ($ch, CURLOPT_SSL_VERIFYPEER, FALSE);
curl_setopt ($ch, CURLOPT_TIMEOUT, 60);
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 0);
curl_setopt($ch, CURLOPT_PROTOCOLS, CURLPROTO_HTTPS);
curl_setopt($ch, CURLOPT_HTTPAUTH, CURLAUTH_ANY);
curl_setopt ($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt ($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt ($ch, CURLOPT_REFERER, $url);
curl_setopt ($ch, CURLOPT_POSTFIELDS, $postdata);
curl_setopt($ch, CURLOPT_CUSTOMREQUEST, "POST");
curl_setopt ($ch, CURLOPT_POST, true);
$result = curl_exec($ch);
curl_close($ch);
if(strpos($result, "Failed") === false){
$response = "NJIT did not like credentials";
}
else{
$response = "NJIT liked your credentials";
}
echo $response;
}
Actually when we load a page it saves the cookie and send it . So to sign in you first need to acess the page without credential and save the cookies . In next request you need to send the cookies . To avoid bot script login usually websites have dynamic hidden fields and other securities .. in this case you cant log on .
I'm updating the function too much and making it way more flexible. --You can update it further more if you want.
First and most importantly, you need to create a text file named cookie.txt in the directory where your scrapping file is.
function goCurlNJIT($header = array(), $url, $post = false)
{
$cookie = "cookie.txt";
$ch = curl_init();
curl_setopt($ch, CURLOPT_ENCODING, 'gzip,deflate,sdch');
if (isset($header) && !empty($header))
{
curl_setopt($ch, CURLOPT_HTTPHEADER, $header);
}
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_TIMEOUT, 200);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_MAXREDIRS, 5);
curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36");
curl_setopt($ch, CURLOPT_COOKIEJAR, realpath($cookie));
curl_setopt($ch, CURLOPT_COOKIEFILE, realpath($cookie));
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch, CURLOPT_REFERER, $url);
//if it's a POST request instead of GET
if (isset($post) && !empty($post) && $post)
{
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, $post);
} //endif
$data = curl_exec($ch);
curl_close($ch);
if($info['http_code'] == 200){
return ($data); //this will return page on successful, false otherwise
}else{
return false;
}
}
if you'd paid a close look to Requested Headers, you can notice that there is one unusual header there, that is Upgrade-Insecure-Requests:1(I personally haven't seen this before, so it's wise to send this along with request).
Next the request that you're posting is not like as it should be, you're missing stuff.
$UCID="jko328";
$Pass="password";
$credentialsNJIT="user=".$UCID."&pass=".$Pass; // where is uuid?
it should be something like this. You're skipping uuid from post string.
pass=password&user=jko328&uuid=0xACA021
so putting altogether,
$post['user'] = "jko328";
$post['pass'] = "password";
$post['uuid'] = '0xACA021';
$urlToPost = "https://cp4.njit.edu/cp/home/login";
$header['Upgrade-Insecure-Requests'] = 1;
//Now make call to function, and it'll work fine.
echo goCurlNJIT($header, $urlToPost, http_build_query($post));
and this will work fine. Make sure you've created cookie.txt file in the directory where your this scripts is.
I try to login to a forum via curl. The forum generates a unique id everytime the login page is displayed. That kinda bugs me :( I am able to parse the id and use it. But somehow the id is changed when I try the actual login.
My code so far:
$ch = curl_init();
$url ="http://theforum.dk/index.php/Login/";
$cookie="cookie.txt";
//Fetching the id
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
$output = curl_exec($ch); (1)
$pos = strpos($output, '"t"')+11;
$pos2 = strpos($output, " />",$pos)-1;
$unique_id = substr($output, $pos,$pos2-$pos);
echo $unique_id; //Shows correct id
//Filling the POST array and submitting it
$arrSubmit="username=TESTUSER&action=login&password=TESTPASS&useCookies=1&url=&t=".$unique_id;
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, $arrSubmit);
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookies);
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookies);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, false);
curl_setopt($ch, CURLOPT_FRESH_CONNECT, false);
//Exectute and display result
echo curl_exec($ch); (2)
The output is something like "your id isn't valid anymore". The id at (1) differs from the id in the page source at (2) :(
The login form just a basic HTML form- Submitting the data isn't the problem, just using the fetched id from the start.
Do you guys got any idea?
Any help is appreciated :)
Hi my curl login example.
Good luck
$login_email = 'mehmet';
$login_pass = '112233';
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, 'http://www.mysites.com/giris');
curl_setopt($ch, CURLOPT_POSTFIELDS,'username='.urlencode($login_email).'&password='.urlencode($login_pass));
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
curl_setopt($ch, CURLOPT_COOKIEJAR, "my_cookies.txt");
curl_setopt($ch, CURLOPT_COOKIEFILE, "my_cookies.txt");
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");
curl_setopt($ch, CURLOPT_REFERER, "http://www.mysites.com/package-details/237");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
$curl_handle = curl_init ("http://www.mysites.com/package-details/237");
curl_setopt ($curl_handle, CURLOPT_COOKIEFILE, 'cookie.txt');
curl_setopt ($curl_handle, CURLOPT_RETURNTRANSFER, true);
$page = curl_exec($ch);
echo $page;
I'm using curl to login to a website, It manages to log me in and display the page back saying "Thanks for logging in Jack Brown" and I can see the member area.
However a cookie file is not being created on my server "/tmp/cookie.txt"
Since I have logged in, I then want to use curl again to retrieve data from the members area but when running this part of the page I just get the "Please login to continue".
The first bit of code is for logging in (this logs me in okay but don't create a cookie file):
<?php
$email = 'email#here.com';
$password = 'passwordhere';
$rememberMe = '';
$redirect = '';
// initial login page which redirects to correct sign in page, sets some cookies
$URL = 'https://www.website.co.uk/home';
$coookie = tempnam ("/tmp", "CURLCOOKIE");
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $URL);
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie);
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie);
curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.13) Gecko/20101206 Ubuntu/10.10 (maverick) Firefox/3.6.13');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_HEADER, 1);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
$page = curl_exec($ch);
$URL2 = "login url is normally here"; // this is our post url
$postdata = "_58_login=".$email."&_58_password=".$password."&_58_rememberMe=".$rememberMe."&_58_redirect=".$redirect;
$post = substr($post, 0, -1);
// set additional curl options using our previous options
curl_setopt($ch, CURLOPT_URL, $URL2);
curl_setopt($ch, CURLOPT_REFERER, $URL);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, $postdata);
$page = curl_exec($ch); // make request
// try to find the actual login form
if (!preg_match('/Thanks for loggin in/is', $page, $form)) {
die('Erorr: Could not login!');
}
var_dump($page); // should be logged in
// END OF LOGIN
This next bit of code is in the same document, and is used to open another page in the members area which I can pull content from however this page just returns saying that i'm not logged in:
$URLOPEN = 'http://www.website.co.uk/membersareacontent';
$URL5 = 'http://www.website.co.uk/thanksforlogginin';
curl_setopt($ch, CURLOPT_URL, $URLOPEN);
curl_setopt($ch, CURLOPT_REFERER, $URL5);
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie);
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie);
curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.13) Gecko/20101206 Ubuntu/10.10 (maverick) Firefox/3.6.13');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_HEADER, 1);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
$page2 = curl_exec($ch);
var_dump($page2); // should be show members content
Perhaps because the variable name has an extra o when declared at the top then the one you're using in your cURL later on:
$coookie = tempnam ("/tmp", "CURLCOOKIE"); // Notice coookie with the extra o
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie); // Spelled with only two o's here
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie); // Spelled with only two o's here
Edit: sbeliv01 has point that cookie is misspelled
If not try to add this at top of your code to display if there is any error:
error_reporting(E_ALL);
ini_set("display_errors",1);
And this code to check if file is available to write, and make sure cookie file is writeable:
// change $cookie_file_path to yours
$fp = fopen($cookie_file_path,'wb') or die("can't open cookie file");
fclose($fp);
Also i noticed you have not set your cookie options here:
// set additional curl options using our previous options
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $URL2);
curl_setopt($ch, CURLOPT_REFERER, $URL);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, $postdata);
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie);
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_HEADER, 1);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
I am trying to make a API call to wikipedia through: http://en.wikipedia.org/w/api.php?action=parse&page=Petunia&format=xml, but the xml is full with html and css tags.
Is there a way to fetch only plain text without tags? Thanks!
*Edit 1:
$json = json_decode(file_get_contents('http://en.wikipedia.org/w/api.php?action=parse&page=Petunia&format=json'));
$txt = strip_tags($json->text);
var_dump($json);
Null displayed.
Question was partially answered here
$url = 'http://en.wikipedia.org/w/api.php?action=parse&page=Petunia&format=json&prop=text';
$ch = curl_init($url);
curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt ($ch, CURLOPT_USERAGENT, "TestScript"); // required by wikipedia.org server
$c = curl_exec($ch);
$json = json_decode($c);
var_dump(strip_tags($json->{'parse'}->{'text'}->{'*'}))
I was not able to use file_get_contents but it works fine with cURL.
it is possible to fetch info or description from wikipedia by using xml.
$url = "http://en.wikipedia.org/w/api.php?action=opensearch&search=".$term."&format=xml&limit=1";
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_HTTPGET, TRUE);
curl_setopt($ch, CURLOPT_POST, FALSE);
curl_setopt($ch, CURLOPT_HEADER, false); // Include head as needed
curl_setopt($ch, CURLOPT_NOBODY, FALSE); // Return body
curl_setopt($ch, CURLOPT_VERBOSE, FALSE); // Minimize logs
curl_setopt($ch, CURLOPT_REFERER, ""); // Referer value
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE); // No certificate
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, TRUE); // Follow redirects
curl_setopt($ch, CURLOPT_MAXREDIRS, 4); // Limit redirections to four
curl_setopt($ch, CURLOPT_RETURNTRANSFER, TRUE); // Return in string
curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 6.1; he; rv:1.9.2.8) Gecko/20100722 Firefox/3.6.8"); // Webbot name
$page = curl_exec($ch);
$xml = simplexml_load_string($page);
if((string)$xml->Section->Item->Description) {
print_r(array((string)$xml->Section->Item->Text,
(string)$xml->Section->Item->Description,
(string)$xml->Section->Item->Url));
} else {
echo "sorry";
}
But curl must be install on server... have a nice day...
I'm new to using cURL and its hard to find good resources for it.
What I'm trying to do is login to a remote site, by having curl do the login form and then send back that it was successful.
The code I have doesn't seem to work and only tries to show the main page of the site.
$username="mylogin#gmail.com";
$password="mypassword";
$url="http://www.myremotesite.com/index.php?page=login";
$cookie="cookie.txt";
$postdata = "email=".$username."&password=".$password;
$ch = curl_init();
curl_setopt ($ch, CURLOPT_URL, $url);
curl_setopt ($ch, CURLOPT_SSL_VERIFYPEER, FALSE);
curl_setopt ($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.6) Gecko/20070725 Firefox/2.0.0.6");
curl_setopt ($ch, CURLOPT_TIMEOUT, 60);
curl_setopt ($ch, CURLOPT_FOLLOWLOCATION, 0);
curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt ($ch, CURLOPT_COOKIEJAR, $cookie);
curl_setopt ($ch, CURLOPT_REFERER, $url);
curl_setopt ($ch, CURLOPT_POSTFIELDS, $postdata);
curl_setopt ($ch, CURLOPT_POST, 1);
$result = curl_exec ($ch);
echo $result;
curl_close($ch);
What am I doing wrong. After this is working I want to redirect to another page and get content from my site.
I had let this go for a good while but revisited it later. Since this question is viewed regularly. This is eventually what I ended up using that worked for me.
define("DOC_ROOT","/path/to/html");
//username and password of account
$username = trim($values["email"]);
$password = trim($values["password"]);
//set the directory for the cookie using defined document root var
$path = DOC_ROOT."/ctemp";
//build a unique path with every request to store. the info per user with custom func. I used this function to build unique paths based on member ID, that was for my use case. It can be a regular dir.
//$path = build_unique_path($path); // this was for my use case
//login form action url
$url="https://www.example.com/login/action";
$postinfo = "email=".$username."&password=".$password;
$cookie_file_path = $path."/cookie.txt";
$ch = curl_init();
curl_setopt($ch, CURLOPT_HEADER, false);
curl_setopt($ch, CURLOPT_NOBODY, false);
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 0);
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_file_path);
//set the cookie the site has for certain features, this is optional
curl_setopt($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, $postinfo);
curl_exec($ch);
//page with the content I want to grab
curl_setopt($ch, CURLOPT_URL, "http://www.example.com/page/");
//do stuff with the info with DomDocument() etc
$html = curl_exec($ch);
curl_close($ch);
Update: This code was never meant to be a copy and paste. It was to show how I used it for my specific use case. You should adapt it to your code as needed. Such as directories, vars etc
I had same question and I found this answer on this website.
And I changed it just a little bit (the curl_close at last line)
$username = 'myuser';
$password = 'mypass';
$loginUrl = 'http://www.example.com/login/';
//init curl
$ch = curl_init();
//Set the URL to work with
curl_setopt($ch, CURLOPT_URL, $loginUrl);
// ENABLE HTTP POST
curl_setopt($ch, CURLOPT_POST, 1);
//Set the post parameters
curl_setopt($ch, CURLOPT_POSTFIELDS, 'user='.$username.'&pass='.$password);
//Handle cookies for the login
curl_setopt($ch, CURLOPT_COOKIEJAR, 'cookie.txt');
//Setting CURLOPT_RETURNTRANSFER variable to 1 will force cURL
//not to print out the results of its query.
//Instead, it will return the results as a string return value
//from curl_exec() instead of the usual true/false.
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
//execute the request (the login)
$store = curl_exec($ch);
//the login is now done and you can continue to get the
//protected content.
//set the URL to the protected file
curl_setopt($ch, CURLOPT_URL, 'http://www.example.com/protected/download.zip');
//execute the request
$content = curl_exec($ch);
curl_close($ch);
//save the data to disk
file_put_contents('~/download.zip', $content);
I think this was what you were looking for.Am I right?
And one useful related question. About how to keep a session alive in cUrl: https://stackoverflow.com/a/13020494/2226796
View the source of the login page. Look for the form HTML tag. Within that tag is something that will look like action= Use that value as $url, not the URL of the form itself.
Also, while you are there, verify the input boxes are named what you have them listed as.
For example, a basic login form will look similar to:
<form method='post' action='postlogin.php'>
Email Address: <input type='text' name='email'>
Password: <input type='password' name='password'>
</form>
Using the above form as an example, change your value of $url to:
$url="http://www.myremotesite.com/postlogin.php";
Verify the values you have listed in $postdata:
$postdata = "email=".$username."&password=".$password;
and it should work just fine.
This is how I solved this in ImpressPages:
//initial request with login data
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, 'http://www.example.com/login.php');
curl_setopt($ch, CURLOPT_USERAGENT,'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/32.0.1700.107 Chrome/32.0.1700.107 Safari/537.36');
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, "username=XXXXX&password=XXXXX");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_COOKIESESSION, true);
curl_setopt($ch, CURLOPT_COOKIEJAR, 'cookie-name'); //could be empty, but cause problems on some hosts
curl_setopt($ch, CURLOPT_COOKIEFILE, '/var/www/ip4.x/file/tmp'); //could be empty, but cause problems on some hosts
$answer = curl_exec($ch);
if (curl_error($ch)) {
echo curl_error($ch);
}
//another request preserving the session
curl_setopt($ch, CURLOPT_URL, 'http://www.example.com/profile');
curl_setopt($ch, CURLOPT_POST, false);
curl_setopt($ch, CURLOPT_POSTFIELDS, "");
$answer = curl_exec($ch);
if (curl_error($ch)) {
echo curl_error($ch);
}
Panama Jack Example not work for me - Give Fatal error: Call to undefined function build_unique_path(). I used this code - (more simple - my opinion) :
// options$login_email = 'alabala#gmail.com';$login_pass = 'alabala4807';$cookie_file_path = "/tmp/cookies.txt";$LOGINURL = "http://alabala.com/index.php?route=account/login"; $agent = "Nokia-Communicator-WWW-Browser/2.0 (Geos 3.0 Nokia-9000i)";// begin script$ch = curl_init();// extra headers$headers[] = "Accept: */*";$headers[] = "Connection: Keep-Alive";// basic curl options for all requestscurl_setopt($ch, CURLOPT_HTTPHEADER, $headers);curl_setopt($ch, CURLOPT_HEADER, 0);curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 0);curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false); curl_setopt($ch, CURLOPT_USERAGENT, $agent); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1); curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_file_path); curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_file_path); // set first URLcurl_setopt($ch, CURLOPT_URL, $LOGINURL);// execute session to get cookies and required form inputs$content = curl_exec($ch); // grab the hidden inputs from the form required to login$fields = getFormFields($content);$fields['email'] = $login_email;$fields['password'] = $login_pass;// set postfields using what we extracted from the form$POSTFIELDS = http_build_query($fields); // change URL to login URLcurl_setopt($ch, CURLOPT_URL, $LOGINURL); // set post optionscurl_setopt($ch, CURLOPT_POST, 1); curl_setopt($ch, CURLOPT_POSTFIELDS, $POSTFIELDS); // perform login$result = curl_exec($ch); print $result; function getFormFields($data){ if (preg_match('/()/is', $data, $matches)) { $inputs = getInputs($matches[1]); return $inputs; } else { die('didnt find login form'); }}function getInputs($form){ $inputs = array(); $elements = preg_match_all("/(]+>)/is", $form, $matches); if ($elements > 0) { for($i = 0;$i $el = preg_replace('/\s{2,}/', ' ', $matches[1][$i]); if (preg_match('/name=(?:["\'])?([^"\'\s]*)/i', $el, $name)) { $name = $name[1]; $value = ''; if (preg_match('/value=(?:["\'])?([^"\'\s]*)/i', $el, $value)) { $value = $value[1]; } $inputs[$name] = $value; } } } return $inputs;}$grab_url='http://grab.url/alabala';//page with the content I want to grabcurl_setopt($ch, CURLOPT_URL, $grab_url);//do stuff with the info with DomDocument() etc$html = curl_exec($ch);curl_close($ch);var_dump($html); die;