本站消息

站长简介/公众号

  出租广告位,需要合作请联系站长

+关注
已关注

分类  

暂无分类

标签  

暂无标签

日期归档  

暂无数据

如何使用 cURL 和 PHP 抓取 LinkedIn 公司页面?在标头错误中找不到 CSRF 令牌

发布于2021-08-02 16:55     阅读(585)     评论(0)     点赞(21)     收藏(4)


我想用 cURL 和 PHP 抓取一些 LinkedIn 公司页面。LinkedIn 的 API 不是为此而构建的,所以我必须用 PHP 来做这件事。如果有其他选择,请告诉我...

在抓取公司页面之前,我必须通过 cURL 使用个人帐户登录 LinkedIn,但它似乎不起作用。

我有一个“在标头中找不到 CSRF 令牌”错误。

有人可以帮我吗?

谢谢!

<?php

require_once 'dom/simple_html_dom.php';

$linkedin_login_page = "https://www.linkedin.com/uas/login";

$username = 'linkedin_username';
$password = 'linkedin_password';

$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $linkedin_login_page);
curl_setopt($ch, CURLOPT_USERAGENT,'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.52 Safari/537.17');
curl_setopt($ch, CURLOPT_AUTOREFERER, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE);
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, FALSE);
curl_setopt($ch, CURLOPT_VERBOSE, 1);

$login_content = str_get_html(curl_exec($ch));

if(curl_error($ch)) {
  echo 'error:' . curl_error($ch);
}

if ($login_content) {

  if (($login_content->find('input[name=isJsEnabled]', 0))) {
    foreach($login_content->find('input[name=isJsEnabled]') as $element) {

      $isJsEnabled = trim($element->value);

      if ($isJsEnabled === "false") {
        $isJsEnabled = "true";
      }

    }
  }

  if (($login_content->find('input[name=source_app]', 0))) {
    foreach($login_content->find('input[name=source_app]') as $element) {
      $source_app = trim($element->value);
    }
  }

  if (($login_content->find('input[name=tryCount]', 0))) {
    foreach($login_content->find('input[name=tryCount]') as $element) {
      $tryCount = trim($element->value);
    }
  }

  if (($login_content->find('input[name=clickedSuggestion]', 0))) {
    foreach($login_content->find('input[name=clickedSuggestion]') as $element) {
      $clickedSuggestion = trim($element->value);
    }
  }

  if (($login_content->find('input[name=session_redirect]', 0))) {
    foreach($login_content->find('input[name=session_redirect]') as $element) {
      $session_redirect = trim($element->value);
    }
  }

  if (($login_content->find('input[name=trk]', 0))) {
    foreach($login_content->find('input[name=trk]') as $element) {
      $trk = trim($element->value);
    }
  }

  if (($login_content->find('input[name=loginCsrfParam]', 0))) {
    foreach($login_content->find('input[name=loginCsrfParam]') as $element) {
      $loginCsrfParam = trim($element->value);
    }
  }

  if (($login_content->find('input[name=fromEmail]', 0))) {
    foreach($login_content->find('input[name=fromEmail]') as $element) {
      $fromEmail = trim($element->value);
    }
  }

  if (($login_content->find('input[name=csrfToken]', 0))) {
    foreach($login_content->find('input[name=csrfToken]') as $element) {
      $csrfToken = trim($element->value);
    }
  }

  if (($login_content->find('input[name=sourceAlias]', 0))) {
    foreach($login_content->find('input[name=sourceAlias]') as $element) {
      $sourceAlias = trim($element->value);
    }
  }

}

curl_setopt($ch, CURLOPT_URL, "https://www.linkedin.com/uas/login-submit");
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, 'isJsEnabled='.$isJsEnabled.'&source_app='.$source_app.'&tryCount='.$tryCount.'&clickedSuggestion='.$clickedSuggestion.'&session_key='.$username.'&session_password='.$password.'&session_redirect='.$session_redirect.'&trk='.$trk.'&loginCsrfParam='.$loginCsrfParam.'&fromEmail='.$fromEmail.'&csrfToken='.$csrfToken.'&sourceAlias='.$sourceAlias);
curl_setopt($ch, CURLOPT_COOKIEJAR, 'cookie.txt');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
$store = curl_exec($ch);

curl_setopt($ch, CURLOPT_URL, 'https://www.linkedin.com/company/facebook');
curl_setopt($ch, CURLOPT_POST, false);
curl_setopt($ch, CURLOPT_POSTFIELDS, "");
$content = curl_exec($ch);
curl_close($ch);

echo $content;

?>

解决方案


这是登录的解决方案,如果您想确保它正常工作,只需将内容保存在文件中,您就会看到登录成功

而不是使用我们在 fetch_value 上面使用的 simple_html_dom,你仍然可以使用 simple_html_dom

<?php
function fetch_value($str, $find_start = '', $find_end = '')
{
    if ($find_start == '')
    {
        return '';
    }
    $start = strpos($str, $find_start);
    if ($start === false)
    {
        return '';
    }
    $length = strlen($find_start);
    $substr = substr($str, $start + $length);
    if ($find_end == '')
    {
        return $substr;
    }
    $end = strpos($substr, $find_end);
    if ($end === false)
    {
        return $substr;
    }
    return substr($substr, 0, $end);
}

$linkedin_login_page = "https://www.linkedin.com/uas/login";
$linkedin_ref = "https://www.linkedin.com";

$username = 'username';
$password = 'password';

$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $linkedin_login_page);
curl_setopt($ch, CURLOPT_REFERER, $linkedin_ref);
curl_setopt($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($ch, CURLOPT_AUTOREFERER, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE);
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 2);
curl_setopt($ch, CURLOPT_COOKIEJAR, 'cookie.txt');
curl_setopt($ch, CURLOPT_COOKIEFILE, 'cookie.txt');


$login_content = curl_exec($ch);


if(curl_error($ch)) {
  echo 'error:' . curl_error($ch);
}

$var = array(
            'isJsEnabled' => 'false',
            'source_app' => '',
            'clickedSuggestion' => 'false',
            'session_key' => trim($username),
            'session_password' => trim($password),
            'signin' => 'Sign In',
            'session_redirect' => '',
            'trk' => '',
            'fromEmail' => '');
        $var['loginCsrfParam'] = fetch_value($login_content, 'type="hidden" name="loginCsrfParam" value="', '"');
        $var['csrfToken'] = fetch_value($login_content, 'type="hidden" name="csrfToken" value="', '"');
        $var['sourceAlias'] = fetch_value($login_content, 'input type="hidden" name="sourceAlias" value="', '"');

        $post_array = array();
            foreach ($var as $key => $value)
            {
                $post_array[] = urlencode($key) . '=' . urlencode($value);
            }
        $post_string = implode('&', $post_array);

curl_setopt($ch, CURLOPT_URL, "https://www.linkedin.com/uas/login-submit");
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, $post_string);

$store = curl_exec($ch);


if (stripos($store, "session_password-login-error") !== false){
    $err = trim(strip_tags(fetch_value($store, '<span class="error" id="session_password-login-error">', '</span>')));
    echo "Login error : ".$err;
}elseif (stripos($store, 'profile-nav-item') !== false) {
        curl_setopt($ch, CURLOPT_URL, 'https://www.linkedin.com/company-beta/10667/?pathWildcard=10667');
        curl_setopt($ch, CURLOPT_POST, false);
        curl_setopt($ch, CURLOPT_POSTFIELDS, "");
        $content = curl_exec($ch);
        curl_close($ch);

        echo $content;
}else{
    echo "unknown error";
}


?>

您会注意到公司页面没有加载,因为linkedin 刚刚更改了他们的设计和他们的公司链接以保持跟踪打开的公司页面。



所属网站分类: 技术文章 > 问答

作者:黑洞官方问答小能手

链接:http://www.phpheidong.com/blog/article/121069/ae15b0604c2cfaf1cfe4/

来源:php黑洞网

任何形式的转载都请注明出处,如有侵权 一经发现 必将追究其法律责任

21 0
收藏该文
已收藏

评论内容:(最多支持255个字符)