我只是想使用"file_get_html"来获取特定页面的内容,但该内容仅供登录用户使用,是否有办法发送cookie让目标站点知道该页面被登录用户访问。
require_once 'simple_html_dom.php';
$opts = array("Cookie: __qca=P0-1170249003-1395413811270"); //__qca=P0-1170249003-1395413811270
$current_url = 'http://abc.xyz';
// But it will be redirect to
$url = 'http://www.blogger.com/blogin.g?blogspotURL=http://abc.xyz'
$context = stream_context_create($opts);
$html = file_get_html($url, FALSE, $context);
echo $html;
我做了这样的事情,但它不起作用。我怎么用Curl做到这一点?谢谢。
$ch = curl_init(); // your curl instance
curl_setopt_array($ch, [CURLOPT_URL => "http://www.blogger.com/blogin.g?blogspotURL=http://abc.xyz", CURLOPT_COOKIE => "__qca=P0-1170249003-1395413811270"], CURLOPT_RETURNTRANSFER => true]);
$result = curl_exec($ch); // request's result
$html = new simple_html_dom(); // create new parser instance
$html->load($result); // load and parse previous result
在这个例子中,我使用curl_setopt_array()
来设置各种CURL参数,而不是为每个参数调用curl_setopt()
。
CURLOPT_URL
设置目标URL, CURLOPT_COOKIE
设置要发送的cookie,如果有多个cookie,那么它们必须用分号后跟空格分隔,最后CURLOPT_RETURNTRANSFER
告诉CURL以字符串形式返回服务器的响应。
curl_exec()
执行请求并返回结果。
然后我们创建一个simple_html_dom
的实例,并将之前的结果加载到其中。
非常感谢@andre,我昨天花了一晚上才找到解决方案。首先,我们使curl exe登录到谷歌帐户。并将cookie保存到文本文件(exam: "/tmp/cookie.txt")下次我们要做的就是在这个文件中获取cookie内容来获取远程内容。
<?php
require_once 'simple_html_dom.php';
// Construct an HTTP POST request
$clientlogin_url = "https://www.google.com/accounts/ClientLogin";
$clientlogin_post = array(
"accountType" => "HOSTED_OR_GOOGLE",
"Email" => "youracc@gmail.com",
"Passwd" => "yourpasswd",
"service" => "blogger",
"source" => "your application name"
);
// Initialize the curl object
$curl = curl_init($clientlogin_url);
// Set some options (some for SHTTP)
curl_setopt($curl, CURLOPT_POST, true);
curl_setopt($curl, CURLOPT_POSTFIELDS, $clientlogin_post);
curl_setopt($curl, CURLOPT_HTTPAUTH, CURLAUTH_ANY);
curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_COOKIEFILE, "/tmp/cookie.txt");
curl_setopt($curl, CURLOPT_COOKIEJAR, "/tmp/cookie.txt");
// Execute
$response = curl_exec($curl);
echo $response;
// Get the Auth string and save it
preg_match("/Auth=([a-z0-9_'-]+)/i", $response, $matches);
$auth = $matches[1];
echo "The auth string is: " . $auth;
// Include the Auth string in the headers
// Together with the API version being used
$headers = array(
"Authorization: GoogleLogin auth=" . $auth,
"GData-Version: 3.0",
);
$url = 'http://testlink.html';
$curl = curl_init();
// Make the request
curl_setopt($curl, CURLOPT_URL, $url );
//curl_setopt($curl, CURLOPT_HTTPHEADER, $headers);
curl_setopt($curl, CURLOPT_POST, false);
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 1);
curl_setopt($curl, CURLOPT_COOKIEFILE, "/tmp/cookie.txt");
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
$response = curl_exec($curl);
curl_close($curl);
$html = new simple_html_dom(); // Create new parser instance
$html->load($response);
foreach($html->find('img') as $img) {
//echo $img->src . '</br>';
}