Question

使用curl来提取数据我还有点新意，我最近开始使用Fiddler帮助找到需要设置的选项。

我正试图看看我是否可以从网站上提取图片。我首先点击搜索页面 - 我设置搜索参数，然后开始点击结果中的链接。当我尝试在图像的一个结果中找到一个链接时，我得到一个从curl_exec（）返回的空字符串。

奇怪的是 - 在某一点上，它起作用了 - 我得到了数据并成功地在本地保存了图像。但后来它停了下来，我不知道我在做什么让它工作。当然，一切都在浏览器中正常运行。：（

我正在使用Simple HTML DOM来解析结果，并使用cUrl来查看实际的页面请求。 curl_error（）没有显示错误，curl_getinfo（）认为一切正常。这可能是微不足道的，但我不确定如何解决它超出我的位置。

<?php
include 'includes/simple_html_dom.php';

$url = "http://nwweb.co.bell.tx.us/NewWorld.Aegis.WebPortal/Corrections/InmateInquiry.aspx";

// Get Cookie - ASP.NET_SessionId
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_HEADER, 1);
$r = curl_exec($ch);
preg_match_all('/^Set-Cookie:\s*([^;]*)/mi', $r, $matches);
$cookies = array();
foreach($matches[1] as $item)
{
    parse_str($item, $cookie);
    $cookies = array_merge($cookies, $cookie);
}
$sessionCookie = "ASP_NET_SessionId=".$cookies['ASP_NET_SessionId'];

// now load up page into Simple HTML DOM and get all inputs - ignore buttons and populate our dates
$startDate = "02%2F01%2F2000";
$endDate = "02%2F07%2F2016";

$getInputs = str_get_html($r);
$inputs = $getInputs->find('input');

$inputs_array = array();
$buttons_array = array();

for ($i=0; $i<count($inputs); $i++)
{
    if ($inputs[$i]->type != "submit")
    {
        $inputs_array[$inputs[$i]->id] = $inputs[$i]->value;
        if (stripos($inputs[$i]->id, "FromDate") > 0)
            $inputs_array[$inputs[$i]->id] = $startDate;
        if (stripos($inputs[$i]->id, "ToDate") > 0)
            $inputs_array[$inputs[$i]->id] = $endDate;
    }
}

// build up our curl data - includes hidden inputs, our to & from dates, plus the Search button
$curl_data = http_build_query($inputs_array)."&ctl00%24DefaultContent%24uxSearch=Search"; 

// POST the data, include session cookie
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_HEADER, 1);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, $curl_data);
curl_setopt($ch, CURLOPT_COOKIE, $sessionCookie);
$response = curl_exec($ch);

// this shows that we can get data
// find the links from the HTML

$htmlDom = str_get_html($response); // load up Simple HTML DOM
// get the table of results
$divTable = $htmlDom->find('div#ctl00_DefaultContent_uxResultsWrapper',0)->find('table',0);
$rows = $divTable->find('tr');
for ($i=1; $i<count($rows);$i++)
{
    if ($i>3) break; // limit the length of script for debugging
    $link = $rows[$i]->find('td',1)->find('a',0)->href;

    // build up query to get inmate details from the link above
    $url = "http://nwweb.co.bell.tx.us/NewWorld.Aegis.WebPortal/Corrections/".$link;
    $ch = curl_init($url);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt($ch, CURLOPT_HEADER, 1);
    curl_setopt($ch, CURLOPT_COOKIE, $sessionCookie);
    $page = curl_exec($ch);
    $pageData = str_get_html($page);

    // Now find the Photo, there's a thumb in div.BookingPhotos
    // It is linked to a full size image, the link is of the form http://nwweb.co.bell.tx.us/NewWorld.Aegis.WebPortal/GetImage.aspx?ImageKey=17C030IS, but in the href, it has ../GetImage.aspx?ImageKey=xxxx
    $photoLink = $pageData->find('div.BookingPhotos',0)->find('a',0)->href;
    // get rid of .. and put the base URL on the front
    $imgLink = str_replace("..", "http://nwweb.co.bell.tx.us/NewWorld.Aegis.WebPortal", $photoLink);

    // now attempt to pull the image
    $ch = curl_init($imgLink);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt($ch, CURLOPT_HEADER, 1);
    curl_setopt($ch, CURLOPT_COOKIE, $sessionCookie);

    // here is the PROBLEM - NO DATA RETURNED
    $imgData = curl_exec($ch); // I get a header back, but NO data
}
?>

curl_exec返回空字符串

0 个答案: