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\Core\Hook;
28 use Friendica\Core\Logger;
29 use Friendica\Core\System;
30 use Friendica\Util\Network;
31 use Friendica\Util\ParseUrl;
32 use Friendica\Util\Strings;
34 function parse_url_content(App $a)
39 $ret= ['success' => false, 'contentType' => ''];
43 if (!empty($_GET['binurl']) && Strings::isHex($_GET['binurl'])) {
44 $url = trim(hex2bin($_GET['binurl']));
45 } elseif (!empty($_GET['url'])) {
46 $url = trim($_GET['url']);
47 // fallback in case no url is valid
49 Logger::info('No url given');
53 if (!empty($_GET['title'])) {
54 $title = strip_tags(trim($_GET['title']));
57 if (!empty($_GET['description'])) {
58 $text = strip_tags(trim($_GET['description']));
61 if (!empty($_GET['tags'])) {
62 $arr_tags = ParseUrl::convertTagsToArray($_GET['tags']);
63 if (count($arr_tags)) {
64 $str_tags = $br . implode(' ', $arr_tags) . $br;
68 if (isset($_GET['format']) && $_GET['format'] == 'json') {
72 // Add url scheme if it is missing
73 $arrurl = parse_url($url);
74 if (empty($arrurl['scheme'])) {
75 if (!empty($arrurl['host'])) {
76 $url = 'http:' . $url;
78 $url = 'http://' . $url;
84 // Check if the URL is an image, video or audio file. If so format
85 // the URL with the corresponding BBCode media tag
86 // Fetch the header of the URL
87 $curlResponse = Network::curl($url, false, ['novalidate' => true, 'nobody' => true]);
89 if ($curlResponse->isSuccess()) {
90 // Convert the header fields into an array
92 $h = explode("\n", $curlResponse->getHeader());
94 $header = array_map('trim', explode(':', trim($l), 2));
95 if (count($header) == 2) {
96 list($k, $v) = $header;
103 if (array_key_exists('Content-Type', $hdrs)) {
104 $type = $hdrs['Content-Type'];
107 if (stripos($type, 'image/') !== false) {
108 $content_type = 'image';
109 $bbcode = $br . '[img]' . $url . '[/img]' . $br;
111 if (stripos($type, 'video/') !== false) {
112 $content_type = 'video';
113 $bbcode = $br . '[video]' . $url . '[/video]' . $br;
115 if (stripos($type, 'audio/') !== false) {
116 $content_type = 'audio';
117 $bbcode = $br . '[audio]' . $url . '[/audio]' . $br;
120 if (!empty($content_type)) {
121 if ($format == 'json') {
122 $ret['contentType'] = $content_type;
123 $ret['data'] = ['url' => $url];
124 $ret['success'] = true;
125 System::jsonExit($ret);
134 $template = '[bookmark=%s]%s[/bookmark]%s';
136 $arr = ['url' => $url, 'text' => ''];
138 Hook::callAll('parse_link', $arr);
140 if (strlen($arr['text'])) {
145 // If there is already some content information submitted we don't
146 // need to parse the url for content.
147 if (!empty($url) && !empty($title) && !empty($text)) {
148 $title = str_replace(["\r", "\n"], ['', ''], $title);
150 $text = '[quote]' . trim($text) . '[/quote]' . $br;
152 $result = sprintf($template, $url, ($title) ? $title : $url, $text) . $str_tags;
154 Logger::log('(unparsed): returns: ' . $result);
160 // Fetch the information directly from the webpage
161 $siteinfo = ParseUrl::getSiteinfo($url);
163 unset($siteinfo['keywords']);
165 // Bypass attachment if parse url for a comment
166 if (!empty($_GET['noAttachment'])) {
167 echo $br . '[url=' . $url . ']' . $siteinfo['title'] . '[/url]';
171 if ($format == 'json') {
172 $ret['data'] = $siteinfo;
173 $ret['contentType'] = 'attachment';
174 $ret['success'] = true;
176 System::jsonExit($ret);
179 // Format it as BBCode attachment
180 $info = add_page_info_data($siteinfo);
188 * Legacy function to call ParseUrl::getSiteinfoCached
190 * Note: We have moved the function to ParseUrl.php. This function is only for
191 * legacy support and will be remove in the future
193 * @param string $url The url of the page which should be scraped
194 * @param bool $no_guessing If true the parse doens't search for
196 * @param bool $do_oembed The false option is used by the function fetch_oembed()
197 * to avoid endless loops
199 * @return array which contains needed data for embedding
201 * @throws \Friendica\Network\HTTPException\InternalServerErrorException
202 * @see ParseUrl::getSiteinfoCached()
204 * @deprecated since version 3.6 use ParseUrl::getSiteinfoCached instead
206 function parseurl_getsiteinfo_cached($url, $no_guessing = false, $do_oembed = true)
208 $siteinfo = ParseUrl::getSiteinfoCached($url, $no_guessing, $do_oembed);