2016-06-28 17:07:55 +00:00
|
|
|
<?php
|
|
|
|
|
|
|
|
namespace Wallabag\CoreBundle\Helper;
|
|
|
|
|
|
|
|
use Psr\Log\LoggerInterface as Logger;
|
|
|
|
use Symfony\Component\DomCrawler\Crawler;
|
|
|
|
|
|
|
|
define('REGENERATE_PICTURES_QUALITY', 75);
|
2016-06-28 20:06:00 +00:00
|
|
|
define('HTTP_PORT', 80);
|
|
|
|
define('SSL_PORT', 443);
|
2016-10-22 07:22:30 +00:00
|
|
|
define('BASE_URL', '');
|
2016-06-28 17:07:55 +00:00
|
|
|
|
2016-10-22 07:22:30 +00:00
|
|
|
class DownloadImages
|
|
|
|
{
|
2016-06-28 17:07:55 +00:00
|
|
|
private $folder;
|
|
|
|
private $url;
|
|
|
|
private $html;
|
|
|
|
private $fileName;
|
|
|
|
private $logger;
|
|
|
|
|
2016-10-22 07:22:30 +00:00
|
|
|
public function __construct($html, $url, Logger $logger)
|
|
|
|
{
|
2016-06-28 17:07:55 +00:00
|
|
|
$this->html = $html;
|
|
|
|
$this->url = $url;
|
|
|
|
$this->setFolder();
|
|
|
|
$this->logger = $logger;
|
|
|
|
}
|
|
|
|
|
2016-10-22 07:22:30 +00:00
|
|
|
public function setFolder($folder = 'assets/images')
|
|
|
|
{
|
2016-06-28 17:07:55 +00:00
|
|
|
// if folder doesn't exist, attempt to create one and store the folder name in property $folder
|
2016-10-22 07:22:30 +00:00
|
|
|
if (!file_exists($folder)) {
|
2016-06-28 17:07:55 +00:00
|
|
|
mkdir($folder);
|
|
|
|
}
|
|
|
|
$this->folder = $folder;
|
|
|
|
}
|
|
|
|
|
2016-10-22 07:22:30 +00:00
|
|
|
public function process()
|
|
|
|
{
|
2016-06-28 17:07:55 +00:00
|
|
|
//instantiate the symfony DomCrawler Component
|
|
|
|
$crawler = new Crawler($this->html);
|
|
|
|
// create an array of all scrapped image links
|
|
|
|
$this->logger->log('debug', 'Finding images inside document');
|
|
|
|
$result = $crawler
|
|
|
|
->filterXpath('//img')
|
|
|
|
->extract(array('src'));
|
|
|
|
|
|
|
|
// download and save the image to the folder
|
|
|
|
foreach ($result as $image) {
|
|
|
|
$file = file_get_contents($image);
|
|
|
|
|
|
|
|
// Checks
|
|
|
|
$absolute_path = self::getAbsoluteLink($image, $this->url);
|
|
|
|
$filename = basename(parse_url($absolute_path, PHP_URL_PATH));
|
2016-10-22 07:22:30 +00:00
|
|
|
$fullpath = $this->folder.'/'.$filename;
|
2016-06-28 17:07:55 +00:00
|
|
|
self::checks($file, $fullpath, $absolute_path);
|
2016-10-22 07:22:30 +00:00
|
|
|
$this->html = str_replace($image, self::getPocheUrl().'/'.$fullpath, $this->html);
|
2016-06-28 17:07:55 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
return $this->html;
|
|
|
|
}
|
|
|
|
|
2016-10-22 07:22:30 +00:00
|
|
|
private function checks($rawdata, $fullpath, $absolute_path)
|
|
|
|
{
|
2016-06-28 17:07:55 +00:00
|
|
|
$fullpath = urldecode($fullpath);
|
|
|
|
|
|
|
|
if (file_exists($fullpath)) {
|
|
|
|
unlink($fullpath);
|
|
|
|
}
|
|
|
|
|
|
|
|
// check extension
|
2016-10-22 07:22:30 +00:00
|
|
|
$this->logger->log('debug', 'Checking extension');
|
2016-06-28 17:07:55 +00:00
|
|
|
|
|
|
|
$file_ext = strrchr($fullpath, '.');
|
|
|
|
$whitelist = array('.jpg', '.jpeg', '.gif', '.png');
|
|
|
|
if (!(in_array($file_ext, $whitelist))) {
|
2016-10-22 07:22:30 +00:00
|
|
|
$this->logger->log('debug', 'processed image with not allowed extension. Skipping '.$fullpath);
|
2016-06-28 17:07:55 +00:00
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
// check headers
|
2016-10-22 07:22:30 +00:00
|
|
|
$this->logger->log('debug', 'Checking headers');
|
2016-06-28 17:07:55 +00:00
|
|
|
$imageinfo = getimagesize($absolute_path);
|
|
|
|
if ($imageinfo['mime'] != 'image/gif' && $imageinfo['mime'] != 'image/jpeg' && $imageinfo['mime'] != 'image/jpg' && $imageinfo['mime'] != 'image/png') {
|
2016-10-22 07:22:30 +00:00
|
|
|
$this->logger->log('debug', 'processed image with bad header. Skipping '.$fullpath);
|
2016-06-28 17:07:55 +00:00
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
// regenerate image
|
2016-10-22 07:22:30 +00:00
|
|
|
$this->logger->log('debug', 'regenerating image');
|
2016-06-28 17:07:55 +00:00
|
|
|
$im = imagecreatefromstring($rawdata);
|
|
|
|
if ($im === false) {
|
2016-10-22 07:22:30 +00:00
|
|
|
$this->logger->log('error', 'error while regenerating image '.$fullpath);
|
2016-06-28 17:07:55 +00:00
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
switch ($imageinfo['mime']) {
|
|
|
|
case 'image/gif':
|
|
|
|
$result = imagegif($im, $fullpath);
|
2016-10-22 07:22:30 +00:00
|
|
|
$this->logger->log('debug', 'Re-creating gif');
|
2016-06-28 17:07:55 +00:00
|
|
|
break;
|
|
|
|
case 'image/jpeg':
|
|
|
|
case 'image/jpg':
|
|
|
|
$result = imagejpeg($im, $fullpath, REGENERATE_PICTURES_QUALITY);
|
2016-10-22 07:22:30 +00:00
|
|
|
$this->logger->log('debug', 'Re-creating jpg');
|
2016-06-28 17:07:55 +00:00
|
|
|
break;
|
|
|
|
case 'image/png':
|
2016-10-22 07:22:30 +00:00
|
|
|
$this->logger->log('debug', 'Re-creating png');
|
2016-06-28 17:07:55 +00:00
|
|
|
$result = imagepng($im, $fullpath, ceil(REGENERATE_PICTURES_QUALITY / 100 * 9));
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
imagedestroy($im);
|
|
|
|
|
|
|
|
return $result;
|
|
|
|
}
|
|
|
|
|
|
|
|
private static function getAbsoluteLink($relativeLink, $url)
|
|
|
|
{
|
|
|
|
/* return if already absolute URL */
|
|
|
|
if (parse_url($relativeLink, PHP_URL_SCHEME) != '') {
|
|
|
|
return $relativeLink;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* queries and anchors */
|
|
|
|
if ($relativeLink[0] == '#' || $relativeLink[0] == '?') {
|
|
|
|
return $url.$relativeLink;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* parse base URL and convert to local variables:
|
|
|
|
$scheme, $host, $path */
|
|
|
|
extract(parse_url($url));
|
|
|
|
|
|
|
|
/* remove non-directory element from path */
|
|
|
|
$path = preg_replace('#/[^/]*$#', '', $path);
|
|
|
|
|
|
|
|
/* destroy path if relative url points to root */
|
|
|
|
if ($relativeLink[0] == '/') {
|
|
|
|
$path = '';
|
|
|
|
}
|
|
|
|
|
|
|
|
/* dirty absolute URL */
|
|
|
|
$abs = $host.$path.'/'.$relativeLink;
|
|
|
|
|
|
|
|
/* replace '//' or '/./' or '/foo/../' with '/' */
|
|
|
|
$re = array('#(/\.?/)#', '#/(?!\.\.)[^/]+/\.\./#');
|
|
|
|
for ($n = 1; $n > 0; $abs = preg_replace($re, '/', $abs, -1, $n)) {
|
|
|
|
}
|
|
|
|
|
|
|
|
/* absolute URL is ready! */
|
|
|
|
return $scheme.'://'.$abs;
|
|
|
|
}
|
2016-06-28 20:06:00 +00:00
|
|
|
|
|
|
|
public static function getPocheUrl()
|
|
|
|
{
|
2016-10-22 07:22:30 +00:00
|
|
|
$baseUrl = '';
|
2016-06-28 20:06:00 +00:00
|
|
|
$https = (!empty($_SERVER['HTTPS'])
|
|
|
|
&& (strtolower($_SERVER['HTTPS']) == 'on'))
|
2016-10-22 07:22:30 +00:00
|
|
|
|| (isset($_SERVER['SERVER_PORT'])
|
|
|
|
&& $_SERVER['SERVER_PORT'] == '443') // HTTPS detection.
|
|
|
|
|| (isset($_SERVER['SERVER_PORT']) //Custom HTTPS port detection
|
|
|
|
&& $_SERVER['SERVER_PORT'] == SSL_PORT)
|
2016-06-28 20:06:00 +00:00
|
|
|
|| (isset($_SERVER['HTTP_X_FORWARDED_PROTO'])
|
|
|
|
&& $_SERVER['HTTP_X_FORWARDED_PROTO'] == 'https');
|
2016-10-22 07:22:30 +00:00
|
|
|
$serverport = (!isset($_SERVER['SERVER_PORT'])
|
|
|
|
|| $_SERVER['SERVER_PORT'] == '80'
|
|
|
|
|| $_SERVER['SERVER_PORT'] == HTTP_PORT
|
|
|
|
|| ($https && $_SERVER['SERVER_PORT'] == '443')
|
|
|
|
|| ($https && $_SERVER['SERVER_PORT'] == SSL_PORT) //Custom HTTPS port detection
|
|
|
|
? '' : ':'.$_SERVER['SERVER_PORT']);
|
|
|
|
|
|
|
|
if (isset($_SERVER['HTTP_X_FORWARDED_PORT'])) {
|
|
|
|
$serverport = ':'.$_SERVER['HTTP_X_FORWARDED_PORT'];
|
2016-06-28 20:06:00 +00:00
|
|
|
}
|
|
|
|
// $scriptname = str_replace('/index.php', '/', $_SERVER["SCRIPT_NAME"]);
|
|
|
|
// if (!isset($_SERVER["HTTP_HOST"])) {
|
|
|
|
// return $scriptname;
|
|
|
|
// }
|
|
|
|
$host = (isset($_SERVER['HTTP_X_FORWARDED_HOST']) ? $_SERVER['HTTP_X_FORWARDED_HOST'] : (isset($_SERVER['HTTP_HOST']) ? $_SERVER['HTTP_HOST'] : $_SERVER['SERVER_NAME']));
|
|
|
|
if (strpos($host, ':') !== false) {
|
|
|
|
$serverport = '';
|
|
|
|
}
|
|
|
|
// check if BASE_URL is configured
|
2016-10-22 07:22:30 +00:00
|
|
|
if (BASE_URL) {
|
2016-06-28 20:06:00 +00:00
|
|
|
$baseUrl = BASE_URL;
|
|
|
|
} else {
|
2016-10-22 07:22:30 +00:00
|
|
|
$baseUrl = 'http'.($https ? 's' : '').'://'.$host.$serverport;
|
2016-06-28 20:06:00 +00:00
|
|
|
}
|
2016-10-22 07:22:30 +00:00
|
|
|
|
|
|
|
return $baseUrl;
|
2016-06-28 20:06:00 +00:00
|
|
|
}
|
2016-06-28 17:07:55 +00:00
|
|
|
}
|