PhpCURL模拟登陆论坛并采集数据实例

模拟浏览器登陆应用开发,最关键的地方是突破登陆验证,CURL技术不只支持http,还支持https,区别就在多了一层SSL加密传输,如果是要登陆 https网站,php记得要支持openssl,还是先拿一个例子来分析,代码如下:

/i&＃39;, $contents, $matches);
if (!emptyempty($matches)) {
    $formhash = $matches[1];
} else {
    die(&＃39;Not found the forumhash.&＃39;);
}
//POST数据，获取COOKIE,COOKIE文件放在网站的temp目录下
$COOKIE_file = tempnam(&＃39;./temp&＃39;, &＃39;COOKIE&＃39;);
$ch = curl_init($login_url);
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, $post_fields);
curl_setopt($ch, CURLOPT_COOKIEJAR, $COOKIE_file);
curl_exec($ch);
curl_close($ch);
//取到了关键的COOKIE文件就可以带着COOKIE文件去模拟发帖,fid为论坛的栏目ID
$send_url = $discuz_url . "post.php?action=newthread&fid=2";
$ch = curl_init($send_url);
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_COOKIEFILE, $COOKIE_file);
$cOntents= curl_exec($ch);
curl_close($ch);
//这里的hash码和登陆窗口的hash码的正则不太一样，这里的hidden多了一个id属性
preg_match(&＃39;//i&＃39;, $contents, $matches);
if (!emptyempty($matches)) {
    $formhash = $matches[1];
} else {
    die(&＃39;Not found the forumhash.&＃39;);
}
$post_data = array();
//帖子标题
$post_data[&＃39;subject&＃39;] = &＃39;test2&＃39;;
//帖子内容
$post_data[&＃39;message&＃39;] = &＃39;test2&＃39;;
$post_data[&＃39;topicsubmit&＃39;] = "yes";
$post_data[&＃39;extra&＃39;] = &＃39;&＃39;;
//帖子标签
$post_data[&＃39;tags&＃39;] = &＃39;test&＃39;;
//帖子的hash码，这个非常关键！假如缺少这个hash码，discuz会警告你来路的页面不正确
$post_data[&＃39;formhash&＃39;] = $formhash;
$ch = curl_init($send_url);
curl_setopt($ch, CURLOPT_REFERER, $send_url); //伪装REFERER
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 0);
curl_setopt($ch, CURLOPT_COOKIEFILE, $COOKIE_file);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, $post_data);
$cOntents= curl_exec($ch);
curl_close($ch);
//清理COOKIE文件
unlink($COOKIE_file);
?>

CURL实现网站模拟登陆,代码如下: