friendica/mod/parse_url.php

<?php
/**
 * @copyright Copyright (C) 2020, Friendica
 *
 * @license GNU AGPL version 3 or any later version
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Affero General Public License as
 * published by the Free Software Foundation, either version 3 of the
 * License, or (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Affero General Public License for more details.
 *
 * You should have received a copy of the GNU Affero General Public License
 * along with this program.  If not, see <https://www.gnu.org/licenses/>.
 *
 * This module does parse an url for embeddable content (audio, video, image files or link)
 * information and does format this information to BBCode
 *
 * @see ParseUrl::getSiteinfo() for more information about scraping embeddable content
 */

use Friendica\App;
use Friendica\Content\PageInfo;
use Friendica\Core\Hook;
use Friendica\Core\Logger;
use Friendica\Core\System;
use Friendica\DI;
use Friendica\Util\ParseUrl;
use Friendica\Util\Strings;

function parse_url_content(App $a)
{
	$text = null;
	$str_tags = '';
	$format = '';
	$ret= ['success' => false, 'contentType' => ''];

	$br = "\n";

	if (!empty($_GET['binurl']) && Strings::isHex($_GET['binurl'])) {
		$url = trim(hex2bin($_GET['binurl']));
	} elseif (!empty($_GET['url'])) {
		$url = trim($_GET['url']);
	// fallback in case no url is valid
	} else {
		Logger::info('No url given');
		exit();
	}

	if (!empty($_GET['title'])) {
		$title = strip_tags(trim($_GET['title']));
	}

	if (!empty($_GET['description'])) {
		$text = strip_tags(trim($_GET['description']));
	}

	if (!empty($_GET['tags'])) {
		$arr_tags = ParseUrl::convertTagsToArray($_GET['tags']);
		if (count($arr_tags)) {
			$str_tags = $br . implode(' ', $arr_tags) . $br;
		}
	}

	if (isset($_GET['format']) && $_GET['format'] == 'json') {
		$format = 'json';
	}

	// Add url scheme if it is missing
	$arrurl = parse_url($url);
	if (empty($arrurl['scheme'])) {
		if (!empty($arrurl['host'])) {
			$url = 'http:' . $url;
		} else {
			$url = 'http://' . $url;
		}
	}

	Logger::log($url);

	// Check if the URL is an image, video or audio file. If so format
	// the URL with the corresponding BBCode media tag
	// Fetch the header of the URL
	$curlResponse = DI::httpRequest()->head($url);

	if ($curlResponse->isSuccess()) {
		$hdrs = $curlResponse->getHeaderArray();

		$type = null;
		$content_type = '';
		$bbcode = '';
		if (array_key_exists('Content-Type', $hdrs)) {
			$type = $hdrs['Content-Type'];
		}
		if ($type) {
			if (stripos($type, 'image/') !== false) {
				$content_type = 'image';
				$bbcode = $br . '[img]' . $url . '[/img]' . $br;
			}
			if (stripos($type, 'video/') !== false) {
				$content_type = 'video';
				$bbcode = $br . '[video]' . $url . '[/video]' . $br;
			}
			if (stripos($type, 'audio/') !== false) {
				$content_type = 'audio';
				$bbcode = $br . '[audio]' . $url . '[/audio]' . $br;
			}
		}
		if (!empty($content_type)) {
			if ($format == 'json') {
				$ret['contentType'] = $content_type;
				$ret['data'] = ['url' => $url];
				$ret['success'] = true;
				System::jsonExit($ret);
			}

			echo $bbcode;
			exit();
		}
	}


	$template = '[bookmark=%s]%s[/bookmark]%s';

	$arr = ['url' => $url, 'format' => $format, 'text' => null];

	Hook::callAll('parse_link', $arr);

	if ($arr['text']) {
		if ($format == 'json') {
			System::jsonExit($arr['text']);
		} else {
			echo $arr['text'];
			exit();
		}
	}

	// If there is already some content information submitted we don't
	// need to parse the url for content.
	if (!empty($url) && !empty($title) && !empty($text)) {
		$title = str_replace(["\r", "\n"], ['', ''], $title);

		$text = '[quote]' . trim($text) . '[/quote]' . $br;

		$result = sprintf($template, $url, ($title) ? $title : $url, $text) . $str_tags;

		Logger::log('(unparsed): returns: ' . $result);

		echo $result;
		exit();
	}

	// Fetch the information directly from the webpage
	$siteinfo = ParseUrl::getSiteinfo($url);

	unset($siteinfo['keywords']);

	// Bypass attachment if parse url for a comment
	if (!empty($_GET['noAttachment'])) {
		echo $br . '[url=' . $url . ']' . $siteinfo['title'] . '[/url]';
		exit();
	}

	if ($format == 'json') {
		$ret['data'] = $siteinfo;
		$ret['contentType'] = 'attachment';
		$ret['success'] = true;

		System::jsonExit($ret);
	}

	// Format it as BBCode attachment
	$info = "\n" . PageInfo::getFooterFromData($siteinfo);

	echo $info;

	exit();
}