3 * @copyright Copyright (C) 2020, Friendica
5 * @license GNU AGPL version 3 or any later version
7 * This program is free software: you can redistribute it and/or modify
8 * it under the terms of the GNU Affero General Public License as
9 * published by the Free Software Foundation, either version 3 of the
10 * License, or (at your option) any later version.
12 * This program is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 * GNU Affero General Public License for more details.
17 * You should have received a copy of the GNU Affero General Public License
18 * along with this program. If not, see <https://www.gnu.org/licenses/>.
20 * This module does parse an url for embeddable content (audio, video, image files or link)
21 * information and does format this information to BBCode
23 * @see ParseUrl::getSiteinfo() for more information about scraping embeddable content
27 use Friendica\Content\PageInfo;
28 use Friendica\Core\Hook;
29 use Friendica\Core\Logger;
30 use Friendica\Core\System;
32 use Friendica\Util\ParseUrl;
33 use Friendica\Util\Strings;
35 function parse_url_content(App $a)
40 $ret= ['success' => false, 'contentType' => ''];
44 if (!empty($_GET['binurl']) && Strings::isHex($_GET['binurl'])) {
45 $url = trim(hex2bin($_GET['binurl']));
46 } elseif (!empty($_GET['url'])) {
47 $url = trim($_GET['url']);
48 // fallback in case no url is valid
50 Logger::info('No url given');
54 if (!empty($_GET['title'])) {
55 $title = strip_tags(trim($_GET['title']));
58 if (!empty($_GET['description'])) {
59 $text = strip_tags(trim($_GET['description']));
62 if (!empty($_GET['tags'])) {
63 $arr_tags = ParseUrl::convertTagsToArray($_GET['tags']);
64 if (count($arr_tags)) {
65 $str_tags = $br . implode(' ', $arr_tags) . $br;
69 if (isset($_GET['format']) && $_GET['format'] == 'json') {
73 // Add url scheme if it is missing
74 $arrurl = parse_url($url);
75 if (empty($arrurl['scheme'])) {
76 if (!empty($arrurl['host'])) {
77 $url = 'http:' . $url;
79 $url = 'http://' . $url;
85 // Check if the URL is an image, video or audio file. If so format
86 // the URL with the corresponding BBCode media tag
87 // Fetch the header of the URL
88 $curlResponse = DI::httpRequest()->get($url, false, ['novalidate' => true, 'nobody' => true]);
90 if ($curlResponse->isSuccess()) {
91 // Convert the header fields into an array
93 $h = $curlResponse->getHeaders();
95 foreach ($l as $k => $v) {
96 if (empty($hdrs[$k])) {
99 $hdrs[$k] .= " " . $v;
105 if (array_key_exists('Content-Type', $hdrs)) {
106 $type = $hdrs['Content-Type'];
109 if (stripos($type, 'image/') !== false) {
110 $content_type = 'image';
111 $bbcode = $br . '[img]' . $url . '[/img]' . $br;
113 if (stripos($type, 'video/') !== false) {
114 $content_type = 'video';
115 $bbcode = $br . '[video]' . $url . '[/video]' . $br;
117 if (stripos($type, 'audio/') !== false) {
118 $content_type = 'audio';
119 $bbcode = $br . '[audio]' . $url . '[/audio]' . $br;
122 if (!empty($content_type)) {
123 if ($format == 'json') {
124 $ret['contentType'] = $content_type;
125 $ret['data'] = ['url' => $url];
126 $ret['success'] = true;
127 System::jsonExit($ret);
136 $template = '[bookmark=%s]%s[/bookmark]%s';
138 $arr = ['url' => $url, 'text' => ''];
140 Hook::callAll('parse_link', $arr);
142 if (strlen($arr['text'])) {
147 // If there is already some content information submitted we don't
148 // need to parse the url for content.
149 if (!empty($url) && !empty($title) && !empty($text)) {
150 $title = str_replace(["\r", "\n"], ['', ''], $title);
152 $text = '[quote]' . trim($text) . '[/quote]' . $br;
154 $result = sprintf($template, $url, ($title) ? $title : $url, $text) . $str_tags;
156 Logger::log('(unparsed): returns: ' . $result);
162 // Fetch the information directly from the webpage
163 $siteinfo = ParseUrl::getSiteinfo($url);
165 unset($siteinfo['keywords']);
167 // Bypass attachment if parse url for a comment
168 if (!empty($_GET['noAttachment'])) {
169 echo $br . '[url=' . $url . ']' . $siteinfo['title'] . '[/url]';
173 if ($format == 'json') {
174 $ret['data'] = $siteinfo;
175 $ret['contentType'] = 'attachment';
176 $ret['success'] = true;
178 System::jsonExit($ret);
181 // Format it as BBCode attachment
182 $info = "\n" . PageInfo::getFooterFromData($siteinfo);
190 * Legacy function to call ParseUrl::getSiteinfoCached
192 * Note: We have moved the function to ParseUrl.php. This function is only for
193 * legacy support and will be remove in the future
195 * @param string $url The url of the page which should be scraped
196 * @param bool $no_guessing If true the parse doens't search for
198 * @param bool $do_oembed The false option is used by the function fetch_oembed()
199 * to avoid endless loops
201 * @return array which contains needed data for embedding
203 * @throws \Friendica\Network\HTTPException\InternalServerErrorException
204 * @see ParseUrl::getSiteinfoCached()
206 * @deprecated since version 3.6 use ParseUrl::getSiteinfoCached instead
208 function parseurl_getsiteinfo_cached($url, $no_guessing = false, $do_oembed = true)
210 $siteinfo = ParseUrl::getSiteinfoCached($url, $no_guessing, $do_oembed);