php 抓取app数据库,PHP CURL 怎么模拟登录后抓取排行榜数据(

5

2016-03-17 10:48:10 +08:00

function HttpsPost($url, $data = []) {

$ch = curl_init();

//设置选项，包括 URL

curl_setopt($ch, CURLOPT_URL, $url);

curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, 0); //对证书来源的检查

curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1.5) Gecko/20091102 Firefox/3.5.5"); //模拟用户使用的浏览器

curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1); //使用自动跳转

curl_setopt($ch, CURLOPT_AUTOREFERER, 1); //自动设置 Referer

curl_setopt($ch, CURLOPT_POST, 1); //发送一个 常规的 Post 请求

curl_setopt($ch, CURLOPT_POSTFIELDS, http_build_query($data)); //要提交的信息

curl_setopt($ch, CURLOPT_TIMEOUT, 30); //设置超时限制防止死循环

curl_setopt($ch, CURLOPT_HEADER, 0); //显示返回的 Header 区域内容

curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); //获取的信息以文件流的形式返回

curl_setopt($ch, CURLOPT_COOKIEFILE, dirname(__FILE__) . '/curl.cookie');

curl_setopt($ch, CURLOPT_COOKIEJAR, dirname(__FILE__) . '/curl.cookie');

$output = curl_exec($ch); //执行操作

if (curl_errno($ch)) {

return "Errno" . curl_error($ch); //捕抓异常

}

curl_close($ch); //关闭 CURL

return $output;

}

//获取登录所需参数

$loginFormUrl = 'https://www.appannie.com/account/login';

//设置 cookie 保存路径

$loginForm = HttpsPost($loginFormUrl, []);

$preg_csrfmiddlewaretoken = "//";

$preg_next = "//";

preg_match($preg_csrfmiddlewaretoken, $loginForm, $match_csrfmiddlewaretoken);

preg_match($preg_next, $loginForm, $match_next);

//设置 post 的数据

$post['csrfmiddlewaretoken'] = $match_csrfmiddlewaretoken[1];

$post['next'] = isset($match_next[1]) ? $match_next[1] : '/apps/ios/top/china/games/';

$post['username'] = '***@***.com';

$post['password'] = '******';

$post['remember_user'] = 'on';

//提交登录

$loginPost = HttpsPost($loginFormUrl, $post);//未登录成功

//获取信息

$url2 = 'http://www.appannie.com/apps/ios/top/china/games/?device=iphone';

$iphone_china = HttpsPost($loginFormUrl);

echo $iphone_china;