Download file or web page using PHP cURL and save it to file


<?php
/*** Initialize the cURL session */
$ch = curl_init();
/*** Set the URL of the page or file to download. */
curl_setopt($ch, CURLOPT_URL,
'http://news.google.com/news?hl=en&topic=t&output=rss');
/*** Create a new file */
$fp = fopen('rss.xml', 'w');
/*** Ask cURL to write the contents to a file */
curl_setopt($ch, CURLOPT_FILE, $fp);
/*** Execute the cURL session */
curl_exec ($ch);
/*** Close cURL session and file */
curl_close ($ch);
fclose($fp);
?>


<?php
error_reporting(E_ALL);
ini_set("display_errors", 1);
ini_set('memory_limit', '256M');
ini_set('max_execution_time', '0');
/*
 * vim: ts=4 sw=4 fdm=marker noet tw=78
 */
class curlDownloader
{
    private $remoteFileName = NULL;
    private $ch = NULL;
    private $headers = array();
    private $response = NULL;
    private $fp = NULL;
    private $debug = FALSE;
    private $fileSize = 0;

    const DEFAULT_FNAME = 'remote.out';

    public function __construct($url)
    {
        $this->init($url);
    }

    public function toggleDebug()
    {
        $this->debug = !$this->debug;
    }

    public function init($url)
    {
        if( !$url )
            throw new InvalidArgumentException("Need a URL");

        $this->ch = curl_init();
        curl_setopt($this->ch, CURLOPT_URL, $url);
        curl_setopt($this->ch, CURLOPT_HEADERFUNCTION,
            array($this, 'headerCallback'));
        curl_setopt($this->ch, CURLOPT_WRITEFUNCTION,
            array($this, 'bodyCallback'));
    }

    public function headerCallback($ch, $string)
    {
        $len = strlen($string);
        if( !strstr($string, ':') )
        {
            $this->response = trim($string);
            return $len;
        }
        list($name, $value) = explode(':', $string, 2);
        if( strcasecmp($name, 'Content-Disposition') == 0 )
        {
            $parts = explode(';', $value);
            if( count($parts) > 1 )
            {
                foreach($parts AS $crumb)
                {
                    if( strstr($crumb, '=') )
                    {
                        list($pname, $pval) = explode('=', $crumb);
                        $pname = trim($pname);
                        if( strcasecmp($pname, 'filename') == 0 )
                        {
                            // Using basename to prevent path injection
                            // in malicious headers.
                            $this->remoteFileName = basename(
                                $this->unquote(trim($pval)));
                            $this->fp = fopen($this->remoteFileName, 'wb');
                        }
                    }
                }
            }
        }

        $this->headers[$name] = trim($value);
        return $len;
    }
    public function bodyCallback($ch, $string)
    {
        if( !$this->fp )
        {
            trigger_error("No remote filename received, trying default",
                E_USER_WARNING);
            $this->remoteFileName = self::DEFAULT_FNAME;
            $this->fp = fopen($this->remoteFileName, 'wb');
            if( !$this->fp )
                throw new RuntimeException("Can't open default filename");
        }
        $len = fwrite($this->fp, $string);
        $this->fileSize += $len;
        return $len;
    }

    public function download()
    {
        $retval = curl_exec($this->ch);
        if( $this->debug )
            var_dump($this->headers);
        fclose($this->fp);
        curl_close($this->ch);
        return $this->fileSize;
    }

    public function getFileName() { return $this->remoteFileName; }

    private function unquote($string)
    {
        return str_replace(array("'", '"'), '', $string);
    }
}

$dl = new curlDownloader(
    'https://dl.example.org/torrent/cool-movie/4358-hash/download.torrent'
);
$size = $dl->download();
printf("Downloaded %u bytes to %s\n", $size, $dl->getFileName());
?>