我是使用cURL的新手,很难为它找到好的资源。 我正在尝试做的是登录到远程站点,让curl执行登录表单,然后发回成功。
我的代码似乎不起作用,只是试图显示网站的主页面。
$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);
我做错了什么。在此工作之后,我想重定向到另一个页面并从我的网站获取内容。
答案 0 :(得分:48)
我已经让它好好享受了一段时间,但后来再次重访。由于这个问题定期查看。这最终是我最终使用的对我有用的东西。
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);
更新:此代码从未打算复制和粘贴。这是为了展示我如何将它用于我的特定用例。您应该根据需要将其调整为您的代码。如目录,变量等
答案 1 :(得分:18)
我有同样的问题,我找到了这个答案on this website。
我稍微改了一下(最后一行的curl_close)
$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', $content);
我认为这就是你要找的东西。我是对的吗?
一个有用的相关问题。关于如何在cUrl中保持会话活动:https://stackoverflow.com/a/13020494/2226796
答案 2 :(得分:15)
查看登录页面的来源。查找form
HTML标记。在该标记内的内容类似于action=
。将该值用作$url
,而不是表单本身的网址。
此外,当您在那里时,请确认输入框的名称是您列出的内容。
例如,基本登录表单看起来类似于:
<form method='post' action='postlogin.php'>
Email Address: <input type='text' name='email'>
Password: <input type='password' name='password'>
</form>
使用上述表单作为示例,将$url
的值更改为:
$url="http://www.myremotesite.com/postlogin.php";
验证$postdata
中列出的值:
$postdata = "email=".$username."&password=".$password;
它应该可以正常工作。
答案 3 :(得分:11)
这就是我在ImpressPages中解决这个问题的方法:
//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);
}
答案 4 :(得分:1)
巴拿马杰克示例对我不起作用 - 给出致命错误:调用未定义的函数build_unique_path()。我使用了这段代码 - (更简单 - 我的意见):
// 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: */*";
$headers[] = "Connection: Keep-Alive";
// basic curl options for all requests
curl_setopt($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, $cookie_file_path);
// set first URL
curl_setopt($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 URL
curl_setopt($ch, CURLOPT_URL, $LOGINURL);
// set post options
curl_setopt($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;
}
$grab_url='http://grab.url/alabala';
//page with the content I want to grab
curl_setopt($ch, CURLOPT_URL, $grab_url);
//do stuff with the info with DomDocument() etc
$html = curl_exec($ch);
curl_close($ch);
var_dump($html);
die;