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 = explode("\n", $curlResponse->getHeader());
95 $header = array_map('trim', explode(':', trim($l), 2));
96 if (count($header) == 2) {
97 list($k, $v) = $header;
104 if (array_key_exists('Content-Type', $hdrs)) {
105 $type = $hdrs['Content-Type'];
108 if (stripos($type, 'image/') !== false) {
109 $content_type = 'image';
110 $bbcode = $br . '[img]' . $url . '[/img]' . $br;
112 if (stripos($type, 'video/') !== false) {
113 $content_type = 'video';
114 $bbcode = $br . '[video]' . $url . '[/video]' . $br;
116 if (stripos($type, 'audio/') !== false) {
117 $content_type = 'audio';
118 $bbcode = $br . '[audio]' . $url . '[/audio]' . $br;
121 if (!empty($content_type)) {
122 if ($format == 'json') {
123 $ret['contentType'] = $content_type;
124 $ret['data'] = ['url' => $url];
125 $ret['success'] = true;
126 System::jsonExit($ret);
135 $template = '[bookmark=%s]%s[/bookmark]%s';
137 $arr = ['url' => $url, 'text' => ''];
139 Hook::callAll('parse_link', $arr);
141 if (strlen($arr['text'])) {
146 // If there is already some content information submitted we don't
147 // need to parse the url for content.
148 if (!empty($url) && !empty($title) && !empty($text)) {
149 $title = str_replace(["\r", "\n"], ['', ''], $title);
151 $text = '[quote]' . trim($text) . '[/quote]' . $br;
153 $result = sprintf($template, $url, ($title) ? $title : $url, $text) . $str_tags;
155 Logger::log('(unparsed): returns: ' . $result);
161 // Fetch the information directly from the webpage
162 $siteinfo = ParseUrl::getSiteinfo($url);
164 unset($siteinfo['keywords']);
166 // Bypass attachment if parse url for a comment
167 if (!empty($_GET['noAttachment'])) {
168 echo $br . '[url=' . $url . ']' . $siteinfo['title'] . '[/url]';
172 if ($format == 'json') {
173 $ret['data'] = $siteinfo;
174 $ret['contentType'] = 'attachment';
175 $ret['success'] = true;
177 System::jsonExit($ret);
180 // Format it as BBCode attachment
181 $info = "\n" . PageInfo::getFooterFromData($siteinfo);
189 * Legacy function to call ParseUrl::getSiteinfoCached
191 * Note: We have moved the function to ParseUrl.php. This function is only for
192 * legacy support and will be remove in the future
194 * @param string $url The url of the page which should be scraped
195 * @param bool $no_guessing If true the parse doens't search for
197 * @param bool $do_oembed The false option is used by the function fetch_oembed()
198 * to avoid endless loops
200 * @return array which contains needed data for embedding
202 * @throws \Friendica\Network\HTTPException\InternalServerErrorException
203 * @see ParseUrl::getSiteinfoCached()
205 * @deprecated since version 3.6 use ParseUrl::getSiteinfoCached instead
207 function parseurl_getsiteinfo_cached($url, $no_guessing = false, $do_oembed = true)
209 $siteinfo = ParseUrl::getSiteinfoCached($url, $no_guessing, $do_oembed);