cURL Html output different from original page when rendered
You should use <base>
to specify a base url for all relative links:
If you curl http://example.com/thisPage.html
then add a base
tag in your echoed output of ''. This should technically be in the <head>
, but this will work:
echo '<base href="http://example.com/" />';echo $html;
Use this
//Get the html of url function get_data($url) { $ch = curl_init(); $timeout = 5; //$userAgent = "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US)AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.X.Y.Z Safari/525.13."; $userAgent = "IE 7 – Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30)"; curl_setopt($ch, CURLOPT_USERAGENT, $userAgent); curl_setopt($ch, CURLOPT_FAILONERROR, true); curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true); curl_setopt($ch, CURLOPT_AUTOREFERER, true); curl_setopt($ch, CURLOPT_TIMEOUT, 10); curl_setopt($ch,CURLOPT_URL,$url); curl_setopt($ch,CURLOPT_RETURNTRANSFER,1); curl_setopt($ch,CURLOPT_CONNECTTIMEOUT,$timeout); $data = curl_exec($ch); curl_close($ch); return $data; }$parse = parse_url($url);$count = "http://".$parse['host'].dirname($parse['path'])."//";$page = str_replace("<head>", "<head>\n<base href=\"" . $count . "\" />", $page);$page = str_replace("<HEAD>", "<head>\n<base href=\"" . $count . "\" />", $page);echo $page;?>