Question

我正在使用cURL来获取网站。我可以获取登录页面并使用cURL登录成功通过POST表单发送凭证详细信息。当我尝试使用GET完成下一页时（因为我的Web浏览器在调试实用程序的网络部分中报告它），Web浏览器显示您通常看到的页面，但cURL向我显示另一页（登录页面）。我在我的cURL脚本中启用了cookie。我尝试禁用Javascript以防它正在使用cookie但它仍然在没有它的浏览器中工作。我还缺少什么？

以下是我的curl脚本：

function HttpGet($url)
{
    $header = array();
    $header[] = 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8';
    $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: ';
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $url);

    curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.0.11) Gecko/2009060215 Firefox/3.0.11 (.NET CLR 3.5.30729)');
    curl_setopt($ch, CURLOPT_HTTPHEADER, $header);
    curl_setopt($ch, CURLOPT_AUTOREFERER, true);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
    curl_setopt($ch, CURLOPT_ENCODING, '');
    curl_setopt($ch, CURLOPT_TIMEOUT, 60);
    curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE);
    //curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 2);
    curl_setopt($ch, CURLOPT_COOKIESESSION, true);
    curl_setopt($ch, CURLOPT_COOKIEFILE, "cookie.txt");
    curl_setopt($ch, CURLOPT_COOKIEJAR, "cookie.txt");

    if (! $html_content = curl_exec($ch))
    {
        trigger_error(curl_error($ch)); 
    }

    echo "CURLINFO_EFFECTIVE_URL: " . curl_getinfo($ch, CURLINFO_EFFECTIVE_URL) . "\n";
    echo "CURLINFO_HTTP_CODE: " . curl_getinfo($ch, CURLINFO_HTTP_CODE) . "\n";

    curl_close ($ch);
    return $html_content;
}

和

function HttpPost($address, $fields, $outputFilename, $currentUrl)
{
    $header = array();
    $header[] = 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8';
    $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: ';
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $address);
    curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.0.11) Gecko/2009060215 Firefox/3.0.11 (.NET CLR 3.5.30729)');
    curl_setopt($ch, CURLOPT_HTTPHEADER, $header);
    curl_setopt($ch, CURLOPT_AUTOREFERER, true);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
    curl_setopt($ch, CURLOPT_ENCODING, '');
    curl_setopt($ch, CURLOPT_TIMEOUT, 60);
    curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE);
    curl_setopt($ch, CURLOPT_COOKIESESSION, true);
    curl_setopt($ch, CURLOPT_COOKIEFILE, "cookie.txt");
    curl_setopt($ch, CURLOPT_COOKIEJAR, "cookie.txt");

    foreach($fields as $key=>$value) { $fields_string .= $key.'='.$value.'&'; }
    $fields_string = rtrim($fields_string, '&');

    curl_setopt($ch,CURLOPT_POST, count($fields));
    curl_setopt($ch,CURLOPT_POSTFIELDS, $fields_string);

    if (! $html_content = curl_exec($ch))
    {
        trigger_error(curl_error($ch)); 
    }

    $currentUrl = curl_getinfo($ch, CURLINFO_EFFECTIVE_URL);
    echo "CURLINFO_EFFECTIVE_URL: " . curl_getinfo($ch, CURLINFO_EFFECTIVE_URL) . "\n";
    echo "CURLINFO_HTTP_CODE: " . curl_getinfo($ch, CURLINFO_HTTP_CODE) . "\n";

    curl_close ($ch);
    return $html_content;
}

Answer 1

找出原因。我使用的源代码中有错误。这一行：

curl_setopt($ch, CURLOPT_COOKIESESSION, true);

用于在每次执行脚本时重置cookie文件。通过删除它，cookie保持不变并且一切正常。

为什么cURL的行为与Web浏览器不同

1 个答案: