friendica/mod/parse_url.php

212 lines
5.7 KiB
PHP
Raw Normal View History

2010-07-23 05:41:45 +00:00
<?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
2018-09-02 21:24:56 +00:00
*/
use Friendica\App;
use Friendica\Content\PageInfo;
use Friendica\Core\Hook;
2018-10-29 21:20:46 +00:00
use Friendica\Core\Logger;
use Friendica\Core\System;
use Friendica\DI;
2018-01-04 17:03:15 +00:00
use Friendica\Util\ParseUrl;
use Friendica\Util\Strings;
2018-09-02 21:24:56 +00:00
function parse_url_content(App $a)
{
$text = null;
2018-09-02 21:24:56 +00:00
$str_tags = '';
$format = '';
$ret= ['success' => false, 'contentType' => ''];
$br = "\n";
if (!empty($_GET['binurl']) && Strings::isHex($_GET['binurl'])) {
2018-09-02 21:24:56 +00:00
$url = trim(hex2bin($_GET['binurl']));
} elseif (!empty($_GET['url'])) {
2018-09-02 21:24:56 +00:00
$url = trim($_GET['url']);
// fallback in case no url is valid
} else {
2019-05-30 11:45:39 +00:00
Logger::info('No url given');
exit();
}
2018-09-02 21:24:56 +00:00
if (!empty($_GET['title'])) {
$title = strip_tags(trim($_GET['title']));
}
2018-09-02 21:24:56 +00:00
if (!empty($_GET['description'])) {
$text = strip_tags(trim($_GET['description']));
}
2018-09-02 21:24:56 +00:00
if (!empty($_GET['tags'])) {
$arr_tags = ParseUrl::convertTagsToArray($_GET['tags']);
if (count($arr_tags)) {
2018-09-02 21:24:56 +00:00
$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'])) {
2018-09-02 21:24:56 +00:00
$url = 'http:' . $url;
} else {
2018-09-02 21:24:56 +00:00
$url = 'http://' . $url;
2015-03-07 22:14:26 +00:00
}
}
2018-10-29 21:20:46 +00:00
Logger::log($url);
2016-11-25 15:59:31 +00:00
// 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
$curlResponse = DI::httpRequest()->get($url, false, ['novalidate' => true, 'nobody' => true]);
2018-09-02 21:24:56 +00:00
if ($curlResponse->isSuccess()) {
// Convert the header fields into an array
$hdrs = [];
$h = explode("\n", $curlResponse->getHeader());
foreach ($h as $l) {
$header = array_map('trim', explode(':', trim($l), 2));
if (count($header) == 2) {
list($k, $v) = $header;
$hdrs[$k] = $v;
}
}
2018-10-16 22:27:13 +00:00
$type = null;
$content_type = '';
$bbcode = '';
2018-09-02 21:24:56 +00:00
if (array_key_exists('Content-Type', $hdrs)) {
$type = $hdrs['Content-Type'];
}
if ($type) {
2018-09-02 21:24:56 +00:00
if (stripos($type, 'image/') !== false) {
$content_type = 'image';
$bbcode = $br . '[img]' . $url . '[/img]' . $br;
}
2018-09-02 21:24:56 +00:00
if (stripos($type, 'video/') !== false) {
$content_type = 'video';
$bbcode = $br . '[video]' . $url . '[/video]' . $br;
}
2018-09-02 21:24:56 +00:00
if (stripos($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();
2015-03-07 22:14:26 +00:00
}
}
2018-09-02 21:24:56 +00:00
$template = '[bookmark=%s]%s[/bookmark]%s';
2010-07-23 05:41:45 +00:00
2018-09-02 21:24:56 +00:00
$arr = ['url' => $url, 'text' => ''];
2010-12-25 23:01:02 +00:00
Hook::callAll('parse_link', $arr);
2010-12-25 23:01:02 +00:00
2018-09-02 21:24:56 +00:00
if (strlen($arr['text'])) {
echo $arr['text'];
exit();
2010-12-25 23:01:02 +00:00
}
// If there is already some content information submitted we don't
2016-11-25 15:59:31 +00:00
// need to parse the url for content.
if (!empty($url) && !empty($title) && !empty($text)) {
2018-09-02 21:24:56 +00:00
$title = str_replace(["\r", "\n"], ['', ''], $title);
2018-09-02 21:24:56 +00:00
$text = '[quote]' . trim($text) . '[/quote]' . $br;
$result = sprintf($template, $url, ($title) ? $title : $url, $text) . $str_tags;
2018-10-29 21:20:46 +00:00
Logger::log('(unparsed): returns: ' . $result);
echo $result;
2018-09-02 21:24:56 +00:00
exit();
}
2016-11-25 15:59:31 +00:00
// Fetch the information directly from the webpage
$siteinfo = ParseUrl::getSiteinfo($url);
2018-09-02 21:24:56 +00:00
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);
2016-04-18 18:57:01 +00:00
echo $info;
2018-09-02 21:24:56 +00:00
exit();
}
/**
2020-01-19 06:05:23 +00:00
* Legacy function to call ParseUrl::getSiteinfoCached
*
* Note: We have moved the function to ParseUrl.php. This function is only for
* legacy support and will be remove in the future
*
2019-01-07 06:07:42 +00:00
* @param string $url The url of the page which should be scraped
* @param bool $no_guessing If true the parse doens't search for
* preview pictures
* @param bool $do_oembed The false option is used by the function fetch_oembed()
* to avoid endless loops
*
* @return array which contains needed data for embedding
*
2019-01-07 06:07:42 +00:00
* @throws \Friendica\Network\HTTPException\InternalServerErrorException
* @see ParseUrl::getSiteinfoCached()
*
2019-01-07 06:07:42 +00:00
* @deprecated since version 3.6 use ParseUrl::getSiteinfoCached instead
*/
2018-09-02 21:24:56 +00:00
function parseurl_getsiteinfo_cached($url, $no_guessing = false, $do_oembed = true)
{
$siteinfo = ParseUrl::getSiteinfoCached($url, $no_guessing, $do_oembed);
return $siteinfo;
}