确定还是新的屏幕抓取的东西。PHP的屏幕抓取和会话
我已经设法登录到我需要的站点,但现在如何重定向到另一个页面? 我登录后,我试图在我需要的页面上执行另一个GET请求,但它有一个重定向,它将我带回登录页面。
所以我在想,SESSION变量没有被传递,我怎么能过来呢?
问题:
即使我上传它仍然重定向我回到登录页面,除非我已经在我登录第2页URL,但屏幕抓取代码不允许会话数据传递?
我发现这个代码another screen scraper question here @stack
class Curl {
public $cookieJar = "";
public function __construct($cookieJarFile = 'cookies.txt') {
$this->cookieJar = $cookieJarFile;
}
function setup() {
$header = array();
$header[0] = "Accept: text/xml,application/xml,application/xhtml+xml,";
$header[0] .= "text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5";
$header[] = "Cache-Control: max-age=0";
$header[] = "Connection: keep-alive";
$header[] = "Keep-Alive: 300";
$header[] = "Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7";
$header[] = "Accept-Language: en-us,en;q=0.5";
$header[] = "Pragma: "; // browsers keep this blank.
curl_setopt($this->curl, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US; rv:1.8.1.7) Gecko/20070914 Firefox/2.0.0.7');
curl_setopt($this->curl, CURLOPT_HTTPHEADER, $header);
curl_setopt($this->curl, CURLOPT_COOKIEJAR, $cookieJar);
curl_setopt($this->curl, CURLOPT_COOKIEFILE, $cookieJar);
curl_setopt($this->curl, CURLOPT_AUTOREFERER, true);
curl_setopt($this->curl, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($this->curl, CURLOPT_RETURNTRANSFER, true);
}
function get($url) {
$this->curl = curl_init($url);
$this->setup();
return $this->request();
}
function getAll($reg, $str) {
preg_match_all($reg, $str, $matches);
return $matches[1];
}
function postForm($url, $fields, $referer = '') {
$this->curl = curl_init($url);
$this->setup();
curl_setopt($this->curl, CURLOPT_URL, $url);
curl_setopt($this->curl, CURLOPT_POST, 1);
curl_setopt($this->curl, CURLOPT_REFERER, $referer);
curl_setopt($this->curl, CURLOPT_POSTFIELDS, $fields);
return $this->request();
}
function getInfo($info) {
$info = ($info == 'lasturl') ? curl_getinfo($this->curl, CURLINFO_EFFECTIVE_URL) : curl_getinfo($this->curl, $info);
return $info;
}
function request() {
return curl_exec($this->curl);
}
}
调用类
include('/var/www/html/curl.php');
$curl = new Curl();
$url = "here.com";
$newURL = "here.com/newpage.php";
$fields = "usr=user1&pass=PassWord";
// Calling URL
$referer = "http://here.com/index.php";
$html = $curl->postForm($url, $fields, $referer);
$html = $curl->get($newURL);
echo $html; // takes me back to $url instead of $newURL
谢谢你的问题以及cookies.txt文件没有正确的权限。这样的新手错误。再次感谢 – 2009-10-12 17:33:34