2016-11-24 00:11:22 +00:00
|
|
|
<?php
|
|
|
|
/**
|
2020-02-09 15:18:46 +00:00
|
|
|
* @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/>.
|
|
|
|
*
|
2016-11-24 00:11:22 +00:00
|
|
|
*/
|
2020-02-09 15:18:46 +00:00
|
|
|
|
2018-01-04 17:03:15 +00:00
|
|
|
namespace Friendica\Util;
|
2016-11-24 00:11:22 +00:00
|
|
|
|
2018-07-20 02:15:21 +00:00
|
|
|
use DOMDocument;
|
|
|
|
use DOMXPath;
|
2018-01-01 01:58:09 +00:00
|
|
|
use Friendica\Content\OEmbed;
|
2018-12-26 06:06:24 +00:00
|
|
|
use Friendica\Core\Hook;
|
2018-10-29 21:20:46 +00:00
|
|
|
use Friendica\Core\Logger;
|
2020-11-19 19:34:48 +00:00
|
|
|
use Friendica\Database\Database;
|
2018-07-20 12:19:26 +00:00
|
|
|
use Friendica\Database\DBA;
|
2020-03-04 21:35:09 +00:00
|
|
|
use Friendica\DI;
|
2021-02-16 15:16:04 +00:00
|
|
|
use Friendica\Network\HTTPException;
|
2017-05-11 15:53:04 +00:00
|
|
|
|
2016-11-24 00:11:22 +00:00
|
|
|
/**
|
2020-02-09 15:18:46 +00:00
|
|
|
* Get information about a given URL
|
|
|
|
*
|
2020-01-19 06:05:23 +00:00
|
|
|
* Class with methods for extracting certain content from an url
|
2016-11-24 00:11:22 +00:00
|
|
|
*/
|
2017-11-08 22:02:50 +00:00
|
|
|
class ParseUrl
|
|
|
|
{
|
2021-02-16 15:16:04 +00:00
|
|
|
const DEFAULT_EXPIRATION_FAILURE = 'now + 1 day';
|
|
|
|
const DEFAULT_EXPIRATION_SUCCESS = 'now + 3 months';
|
|
|
|
|
2019-11-15 13:28:42 +00:00
|
|
|
/**
|
|
|
|
* Maximum number of characters for the description
|
|
|
|
*/
|
|
|
|
const MAX_DESC_COUNT = 250;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Minimum number of characters for the description
|
|
|
|
*/
|
|
|
|
const MIN_DESC_COUNT = 100;
|
|
|
|
|
2021-03-12 23:04:51 +00:00
|
|
|
/**
|
|
|
|
* Fetch the content type of the given url
|
|
|
|
* @param string $url URL of the page
|
2021-03-13 13:17:42 +00:00
|
|
|
* @return array content type
|
2021-03-12 23:04:51 +00:00
|
|
|
*/
|
|
|
|
public static function getContentType(string $url)
|
|
|
|
{
|
|
|
|
$curlResult = DI::httpRequest()->head($url);
|
|
|
|
if (!$curlResult->isSuccess()) {
|
2021-03-13 13:17:42 +00:00
|
|
|
return [];
|
2021-03-12 23:04:51 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
$contenttype = $curlResult->getHeader('Content-Type');
|
|
|
|
if (empty($contenttype)) {
|
2021-03-13 13:17:42 +00:00
|
|
|
return [];
|
2021-03-12 23:04:51 +00:00
|
|
|
}
|
|
|
|
|
2021-03-13 13:17:42 +00:00
|
|
|
return explode('/', current(explode(';', $contenttype)));
|
2021-03-12 23:04:51 +00:00
|
|
|
}
|
|
|
|
|
2016-11-27 22:41:55 +00:00
|
|
|
/**
|
2020-01-19 06:05:23 +00:00
|
|
|
* Search for chached embeddable data of an url otherwise fetch it
|
2017-02-18 03:32:33 +00:00
|
|
|
*
|
2017-12-17 20:27:50 +00:00
|
|
|
* @param string $url The url of the page which should be scraped
|
2019-01-06 21:06:53 +00:00
|
|
|
* @param bool $do_oembed The false option is used by the function fetch_oembed()
|
|
|
|
* to avoid endless loops
|
2017-02-18 03:32:33 +00:00
|
|
|
*
|
2016-11-27 22:41:55 +00:00
|
|
|
* @return array which contains needed data for embedding
|
2020-07-17 23:18:27 +00:00
|
|
|
* string 'url' => The url of the parsed page
|
|
|
|
* string 'type' => Content type
|
|
|
|
* string 'title' => (optional) The title of the content
|
|
|
|
* string 'text' => (optional) The description for the content
|
2021-03-16 07:15:20 +00:00
|
|
|
* string 'image' => (optional) A preview image of the content
|
2020-07-17 23:18:27 +00:00
|
|
|
* array 'images' => (optional) Array of preview pictures
|
|
|
|
* string 'keywords' => (optional) The tags which belong to the content
|
2017-02-18 03:32:33 +00:00
|
|
|
*
|
2021-02-16 15:16:04 +00:00
|
|
|
* @throws HTTPException\InternalServerErrorException
|
2019-01-06 21:06:53 +00:00
|
|
|
* @see ParseUrl::getSiteinfo() for more information about scraping
|
2017-02-18 03:32:33 +00:00
|
|
|
* embeddable content
|
2016-11-27 22:41:55 +00:00
|
|
|
*/
|
2021-03-16 07:15:20 +00:00
|
|
|
public static function getSiteinfoCached($url, $do_oembed = true): array
|
2017-11-08 22:02:50 +00:00
|
|
|
{
|
2021-02-16 15:16:04 +00:00
|
|
|
if (empty($url)) {
|
|
|
|
return [
|
|
|
|
'url' => '',
|
|
|
|
'type' => 'error',
|
|
|
|
];
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
|
2021-02-16 15:16:04 +00:00
|
|
|
$urlHash = hash('sha256', $url);
|
|
|
|
|
2018-07-20 12:19:26 +00:00
|
|
|
$parsed_url = DBA::selectFirst('parsed_url', ['content'],
|
2021-03-16 07:15:20 +00:00
|
|
|
['url_hash' => $urlHash, 'oembed' => $do_oembed]
|
2017-11-08 22:02:50 +00:00
|
|
|
);
|
2018-02-14 05:05:00 +00:00
|
|
|
if (!empty($parsed_url['content'])) {
|
|
|
|
$data = unserialize($parsed_url['content']);
|
2016-11-24 00:11:22 +00:00
|
|
|
return $data;
|
|
|
|
}
|
|
|
|
|
2021-03-16 07:15:20 +00:00
|
|
|
$data = self::getSiteinfo($url, $do_oembed);
|
2016-11-24 00:11:22 +00:00
|
|
|
|
2021-02-16 15:16:04 +00:00
|
|
|
$expires = $data['expires'];
|
|
|
|
|
|
|
|
unset($data['expires']);
|
|
|
|
|
|
|
|
DI::dba()->insert(
|
2017-11-08 22:02:50 +00:00
|
|
|
'parsed_url',
|
2018-01-15 13:05:12 +00:00
|
|
|
[
|
2021-02-16 15:16:04 +00:00
|
|
|
'url_hash' => $urlHash,
|
|
|
|
'oembed' => $do_oembed,
|
|
|
|
'url' => $url,
|
|
|
|
'content' => serialize($data),
|
|
|
|
'created' => DateTimeFormat::utcNow(),
|
|
|
|
'expires' => $expires,
|
2018-01-25 02:08:45 +00:00
|
|
|
],
|
2020-11-19 19:34:48 +00:00
|
|
|
Database::INSERT_UPDATE
|
2017-11-08 22:02:50 +00:00
|
|
|
);
|
2016-11-24 00:11:22 +00:00
|
|
|
|
|
|
|
return $data;
|
|
|
|
}
|
2019-01-06 21:06:53 +00:00
|
|
|
|
2016-11-27 22:41:55 +00:00
|
|
|
/**
|
2020-01-19 06:05:23 +00:00
|
|
|
* Parse a page for embeddable content information
|
2017-02-18 03:32:33 +00:00
|
|
|
*
|
2016-11-27 22:41:55 +00:00
|
|
|
* This method parses to url for meta data which can be used to embed
|
|
|
|
* the content. If available it prioritizes Open Graph meta tags.
|
|
|
|
* If this is not available it uses the twitter cards meta tags.
|
|
|
|
* As fallback it uses standard html elements with meta informations
|
|
|
|
* like \<title\>Awesome Title\</title\> or
|
|
|
|
* \<meta name="description" content="An awesome description"\>
|
2017-02-18 03:32:33 +00:00
|
|
|
*
|
2017-12-17 20:27:50 +00:00
|
|
|
* @param string $url The url of the page which should be scraped
|
2019-01-06 21:06:53 +00:00
|
|
|
* @param bool $do_oembed The false option is used by the function fetch_oembed()
|
|
|
|
* to avoid endless loops
|
|
|
|
* @param int $count Internal counter to avoid endless loops
|
2017-02-18 03:32:33 +00:00
|
|
|
*
|
2016-11-27 22:41:55 +00:00
|
|
|
* @return array which contains needed data for embedding
|
2020-07-17 23:18:27 +00:00
|
|
|
* string 'url' => The url of the parsed page
|
2021-02-16 15:16:04 +00:00
|
|
|
* string 'type' => Content type (error, link, photo, image, audio, video)
|
2020-07-17 23:18:27 +00:00
|
|
|
* string 'title' => (optional) The title of the content
|
|
|
|
* string 'text' => (optional) The description for the content
|
2021-03-16 07:15:20 +00:00
|
|
|
* string 'image' => (optional) A preview image of the content
|
2020-07-17 23:18:27 +00:00
|
|
|
* array 'images' => (optional) Array of preview pictures
|
|
|
|
* string 'keywords' => (optional) The tags which belong to the content
|
2017-02-18 03:32:33 +00:00
|
|
|
*
|
2019-01-06 21:06:53 +00:00
|
|
|
* @throws \Friendica\Network\HTTPException\InternalServerErrorException
|
|
|
|
* @todo https://developers.google.com/+/plugins/snippet/
|
2016-11-27 22:41:55 +00:00
|
|
|
* @verbatim
|
|
|
|
* <meta itemprop="name" content="Awesome title">
|
|
|
|
* <meta itemprop="description" content="An awesome description">
|
|
|
|
* <meta itemprop="image" content="http://maple.libertreeproject.org/images/tree-icon.png">
|
2017-02-18 03:32:33 +00:00
|
|
|
*
|
2016-11-27 22:41:55 +00:00
|
|
|
* <body itemscope itemtype="http://schema.org/Product">
|
|
|
|
* <h1 itemprop="name">Shiny Trinket</h1>
|
|
|
|
* <img itemprop="image" src="{image-url}" />
|
|
|
|
* <p itemprop="description">Shiny trinkets are shiny.</p>
|
|
|
|
* </body>
|
|
|
|
* @endverbatim
|
|
|
|
*/
|
2021-03-16 07:15:20 +00:00
|
|
|
public static function getSiteinfo($url, $do_oembed = true, $count = 1)
|
2017-11-08 22:02:50 +00:00
|
|
|
{
|
2021-02-16 15:16:04 +00:00
|
|
|
if (empty($url)) {
|
|
|
|
return [
|
|
|
|
'url' => '',
|
|
|
|
'type' => 'error',
|
|
|
|
];
|
|
|
|
}
|
|
|
|
|
2016-11-24 00:11:22 +00:00
|
|
|
// Check if the URL does contain a scheme
|
|
|
|
$scheme = parse_url($url, PHP_URL_SCHEME);
|
|
|
|
|
2018-09-02 21:35:55 +00:00
|
|
|
if ($scheme == '') {
|
2020-07-17 23:18:27 +00:00
|
|
|
$url = 'http://' . ltrim($url, '/');
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
|
2020-07-17 23:18:27 +00:00
|
|
|
$url = trim($url, "'\"");
|
|
|
|
|
|
|
|
$url = Network::stripTrackingQueryParams($url);
|
|
|
|
|
|
|
|
$siteinfo = [
|
|
|
|
'url' => $url,
|
|
|
|
'type' => 'link',
|
2021-02-16 15:16:04 +00:00
|
|
|
'expires' => DateTimeFormat::utc(self::DEFAULT_EXPIRATION_FAILURE),
|
2020-07-17 23:18:27 +00:00
|
|
|
];
|
|
|
|
|
2016-11-24 00:11:22 +00:00
|
|
|
if ($count > 10) {
|
2018-10-30 13:58:45 +00:00
|
|
|
Logger::log('Endless loop detected for ' . $url, Logger::DEBUG);
|
2018-09-02 21:35:55 +00:00
|
|
|
return $siteinfo;
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
|
2021-03-13 07:03:26 +00:00
|
|
|
$type = self::getContentType($url);
|
2021-03-13 13:17:42 +00:00
|
|
|
Logger::info('Got content-type', ['content-type' => $type, 'url' => $url]);
|
|
|
|
if (!empty($type) && in_array($type[0], ['image', 'video', 'audio'])) {
|
|
|
|
$siteinfo['type'] = $type[0];
|
|
|
|
return $siteinfo;
|
|
|
|
}
|
|
|
|
|
|
|
|
if ((count($type) >= 2) && (($type[0] != 'text') || ($type[1] != 'html'))) {
|
|
|
|
Logger::info('Unparseable content-type, quitting here, ', ['content-type' => $type, 'url' => $url]);
|
2021-03-13 07:03:26 +00:00
|
|
|
return $siteinfo;
|
|
|
|
}
|
|
|
|
|
2020-10-11 21:25:47 +00:00
|
|
|
$curlResult = DI::httpRequest()->get($url);
|
2018-10-10 19:08:43 +00:00
|
|
|
if (!$curlResult->isSuccess()) {
|
2018-09-02 21:35:55 +00:00
|
|
|
return $siteinfo;
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
|
2021-02-16 15:16:04 +00:00
|
|
|
$siteinfo['expires'] = DateTimeFormat::utc(self::DEFAULT_EXPIRATION_SUCCESS);
|
|
|
|
|
2020-10-11 21:25:47 +00:00
|
|
|
// If the file is too large then exit
|
|
|
|
if (($curlResult->getInfo()['download_content_length'] ?? 0) > 1000000) {
|
|
|
|
return $siteinfo;
|
|
|
|
}
|
|
|
|
|
2021-02-16 15:16:04 +00:00
|
|
|
if ($cacheControlHeader = $curlResult->getHeader('Cache-Control')) {
|
|
|
|
if (preg_match('/max-age=([0-9]+)/i', $cacheControlHeader, $matches)) {
|
|
|
|
$maxAge = max(86400, (int)array_pop($matches));
|
|
|
|
$siteinfo['expires'] = DateTimeFormat::utc("now + $maxAge seconds");
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-10-11 21:26:03 +00:00
|
|
|
$header = $curlResult->getHeader();
|
2018-10-10 19:08:43 +00:00
|
|
|
$body = $curlResult->getBody();
|
2017-10-15 19:29:58 +00:00
|
|
|
|
2016-11-24 00:11:22 +00:00
|
|
|
if ($do_oembed) {
|
2021-03-16 07:04:16 +00:00
|
|
|
$oembed_data = OEmbed::fetchURL($url, false, false);
|
2016-11-24 00:11:22 +00:00
|
|
|
|
2018-07-10 12:27:56 +00:00
|
|
|
if (!empty($oembed_data->type)) {
|
2021-03-13 07:03:26 +00:00
|
|
|
if (!in_array($oembed_data->type, ['error', 'rich', 'image', 'video', 'audio', ''])) {
|
2018-09-02 21:35:55 +00:00
|
|
|
$siteinfo['type'] = $oembed_data->type;
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
2018-07-10 12:27:56 +00:00
|
|
|
|
2018-09-16 13:18:31 +00:00
|
|
|
// See https://github.com/friendica/friendica/pull/5763#discussion_r217913178
|
|
|
|
if ($siteinfo['type'] != 'photo') {
|
2021-03-16 07:04:16 +00:00
|
|
|
if (!empty($oembed_data->title)) {
|
2018-09-02 21:35:55 +00:00
|
|
|
$siteinfo['title'] = trim($oembed_data->title);
|
2018-07-10 12:27:56 +00:00
|
|
|
}
|
2021-03-16 07:04:16 +00:00
|
|
|
if (!empty($oembed_data->description)) {
|
2018-09-02 21:35:55 +00:00
|
|
|
$siteinfo['text'] = trim($oembed_data->description);
|
2018-07-10 12:27:56 +00:00
|
|
|
}
|
2021-03-16 07:04:16 +00:00
|
|
|
if (!empty($oembed_data->author_name)) {
|
|
|
|
$siteinfo['author_name'] = trim($oembed_data->author_name);
|
|
|
|
}
|
|
|
|
if (!empty($oembed_data->author_url)) {
|
|
|
|
$siteinfo['author_url'] = trim($oembed_data->author_url);
|
|
|
|
}
|
|
|
|
if (!empty($oembed_data->provider_name)) {
|
|
|
|
$siteinfo['publisher_name'] = trim($oembed_data->provider_name);
|
|
|
|
}
|
|
|
|
if (!empty($oembed_data->provider_url)) {
|
|
|
|
$siteinfo['publisher_url'] = trim($oembed_data->provider_url);
|
|
|
|
}
|
|
|
|
if (!empty($oembed_data->thumbnail_url)) {
|
2018-09-02 21:35:55 +00:00
|
|
|
$siteinfo['image'] = $oembed_data->thumbnail_url;
|
2018-07-10 12:27:56 +00:00
|
|
|
}
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-09-02 21:35:55 +00:00
|
|
|
$charset = '';
|
2020-09-23 00:35:08 +00:00
|
|
|
// Look for a charset, first in headers
|
|
|
|
// Expected form: Content-Type: text/html; charset=ISO-8859-4
|
2020-10-11 21:26:03 +00:00
|
|
|
if (preg_match('/charset=([a-z0-9-_.\/]+)/i', $header, $matches)) {
|
2020-10-11 21:25:40 +00:00
|
|
|
$charset = trim(trim(trim(array_pop($matches)), ';,'));
|
2020-09-23 00:35:08 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
// Then in body that gets precedence
|
|
|
|
// Expected forms:
|
|
|
|
// - <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
|
|
|
|
// - <meta charset="utf-8">
|
2020-09-25 15:36:04 +00:00
|
|
|
// - <meta charset=utf-8>
|
|
|
|
// - <meta charSet="utf-8">
|
2020-09-25 10:55:52 +00:00
|
|
|
// We escape <style> and <script> tags since they can contain irrelevant charset information
|
|
|
|
// (see https://github.com/friendica/friendica/issues/9251#issuecomment-698636806)
|
|
|
|
Strings::performWithEscapedBlocks($body, '#<(?:style|script).*?</(?:style|script)>#ism', function ($body) use (&$charset) {
|
2020-09-25 15:36:04 +00:00
|
|
|
if (preg_match('/charset=["\']?([a-z0-9-_.\/]+)/i', $body, $matches)) {
|
2020-09-25 10:55:52 +00:00
|
|
|
$charset = trim(trim(trim(array_pop($matches)), ';,'));
|
|
|
|
}
|
|
|
|
});
|
2016-11-24 00:11:22 +00:00
|
|
|
|
2020-09-25 15:36:04 +00:00
|
|
|
$siteinfo['charset'] = $charset;
|
|
|
|
|
2018-09-04 14:52:17 +00:00
|
|
|
if ($charset && strtoupper($charset) != 'UTF-8') {
|
|
|
|
// See https://github.com/friendica/friendica/issues/5470#issuecomment-418351211
|
|
|
|
$charset = str_ireplace('latin-1', 'latin1', $charset);
|
2016-11-24 00:11:22 +00:00
|
|
|
|
2018-10-30 13:58:45 +00:00
|
|
|
Logger::log('detected charset ' . $charset, Logger::DEBUG);
|
2018-09-02 21:35:55 +00:00
|
|
|
$body = iconv($charset, 'UTF-8//TRANSLIT', $body);
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
|
2018-09-02 21:35:55 +00:00
|
|
|
$body = mb_convert_encoding($body, 'HTML-ENTITIES', 'UTF-8');
|
2016-11-24 00:11:22 +00:00
|
|
|
|
2017-05-11 15:53:04 +00:00
|
|
|
$doc = new DOMDocument();
|
2016-11-24 00:11:22 +00:00
|
|
|
@$doc->loadHTML($body);
|
|
|
|
|
2018-09-02 21:35:55 +00:00
|
|
|
XML::deleteNode($doc, 'style');
|
|
|
|
XML::deleteNode($doc, 'option');
|
|
|
|
XML::deleteNode($doc, 'h1');
|
|
|
|
XML::deleteNode($doc, 'h2');
|
|
|
|
XML::deleteNode($doc, 'h3');
|
|
|
|
XML::deleteNode($doc, 'h4');
|
|
|
|
XML::deleteNode($doc, 'h5');
|
|
|
|
XML::deleteNode($doc, 'h6');
|
|
|
|
XML::deleteNode($doc, 'ol');
|
|
|
|
XML::deleteNode($doc, 'ul');
|
2017-05-11 15:53:04 +00:00
|
|
|
|
2017-12-17 20:24:57 +00:00
|
|
|
$xpath = new DOMXPath($doc);
|
2016-11-24 00:11:22 +00:00
|
|
|
|
2018-09-02 21:35:55 +00:00
|
|
|
$list = $xpath->query('//meta[@content]');
|
2016-11-24 00:11:22 +00:00
|
|
|
foreach ($list as $node) {
|
2018-09-02 21:35:55 +00:00
|
|
|
$meta_tag = [];
|
2016-11-24 00:11:22 +00:00
|
|
|
if ($node->attributes->length) {
|
|
|
|
foreach ($node->attributes as $attribute) {
|
2018-09-02 21:35:55 +00:00
|
|
|
$meta_tag[$attribute->name] = $attribute->value;
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-09-02 21:35:55 +00:00
|
|
|
if (@$meta_tag['http-equiv'] == 'refresh') {
|
|
|
|
$path = $meta_tag['content'];
|
|
|
|
$pathinfo = explode(';', $path);
|
|
|
|
$content = '';
|
2016-11-24 00:11:22 +00:00
|
|
|
foreach ($pathinfo as $value) {
|
2018-09-02 21:35:55 +00:00
|
|
|
if (substr(strtolower($value), 0, 4) == 'url=') {
|
2016-11-24 00:11:22 +00:00
|
|
|
$content = substr($value, 4);
|
|
|
|
}
|
|
|
|
}
|
2018-09-02 21:35:55 +00:00
|
|
|
if ($content != '') {
|
2021-03-16 07:15:20 +00:00
|
|
|
$siteinfo = self::getSiteinfo($content, $do_oembed, ++$count);
|
2018-09-02 21:35:55 +00:00
|
|
|
return $siteinfo;
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-09-02 21:35:55 +00:00
|
|
|
$list = $xpath->query('//title');
|
2016-11-24 00:11:22 +00:00
|
|
|
if ($list->length > 0) {
|
2018-09-02 21:35:55 +00:00
|
|
|
$siteinfo['title'] = trim($list->item(0)->nodeValue);
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
|
2018-09-02 21:35:55 +00:00
|
|
|
$list = $xpath->query('//meta[@name]');
|
2016-11-24 00:11:22 +00:00
|
|
|
foreach ($list as $node) {
|
2018-09-02 21:35:55 +00:00
|
|
|
$meta_tag = [];
|
2016-11-24 00:11:22 +00:00
|
|
|
if ($node->attributes->length) {
|
|
|
|
foreach ($node->attributes as $attribute) {
|
2018-09-02 21:35:55 +00:00
|
|
|
$meta_tag[$attribute->name] = $attribute->value;
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-09-02 21:50:27 +00:00
|
|
|
if (empty($meta_tag['content'])) {
|
|
|
|
continue;
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
2018-09-02 21:50:27 +00:00
|
|
|
|
|
|
|
$meta_tag['content'] = trim(html_entity_decode($meta_tag['content'], ENT_QUOTES, 'UTF-8'));
|
|
|
|
|
|
|
|
switch (strtolower($meta_tag['name'])) {
|
|
|
|
case 'fulltitle':
|
|
|
|
$siteinfo['title'] = trim($meta_tag['content']);
|
|
|
|
break;
|
|
|
|
case 'description':
|
|
|
|
$siteinfo['text'] = trim($meta_tag['content']);
|
|
|
|
break;
|
|
|
|
case 'thumbnail':
|
|
|
|
$siteinfo['image'] = $meta_tag['content'];
|
|
|
|
break;
|
|
|
|
case 'twitter:image':
|
|
|
|
$siteinfo['image'] = $meta_tag['content'];
|
|
|
|
break;
|
|
|
|
case 'twitter:image:src':
|
|
|
|
$siteinfo['image'] = $meta_tag['content'];
|
|
|
|
break;
|
|
|
|
case 'twitter:card':
|
2018-09-06 20:30:16 +00:00
|
|
|
// Detect photo pages
|
2018-09-06 04:24:34 +00:00
|
|
|
if ($meta_tag['content'] == 'summary_large_image') {
|
|
|
|
$siteinfo['type'] = 'photo';
|
2018-09-02 21:50:27 +00:00
|
|
|
}
|
|
|
|
break;
|
|
|
|
case 'twitter:description':
|
|
|
|
$siteinfo['text'] = trim($meta_tag['content']);
|
|
|
|
break;
|
|
|
|
case 'twitter:title':
|
|
|
|
$siteinfo['title'] = trim($meta_tag['content']);
|
|
|
|
break;
|
|
|
|
case 'dc.title':
|
|
|
|
$siteinfo['title'] = trim($meta_tag['content']);
|
|
|
|
break;
|
|
|
|
case 'dc.description':
|
|
|
|
$siteinfo['text'] = trim($meta_tag['content']);
|
|
|
|
break;
|
2021-03-15 22:02:21 +00:00
|
|
|
case 'dc.creator':
|
2021-03-16 06:37:43 +00:00
|
|
|
$siteinfo['publisher_name'] = trim($meta_tag['content']);
|
2021-03-15 22:02:21 +00:00
|
|
|
break;
|
2018-09-02 21:50:27 +00:00
|
|
|
case 'keywords':
|
|
|
|
$keywords = explode(',', $meta_tag['content']);
|
|
|
|
break;
|
|
|
|
case 'news_keywords':
|
|
|
|
$keywords = explode(',', $meta_tag['content']);
|
|
|
|
break;
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (isset($keywords)) {
|
2018-09-02 21:35:55 +00:00
|
|
|
$siteinfo['keywords'] = [];
|
2016-11-24 00:11:22 +00:00
|
|
|
foreach ($keywords as $keyword) {
|
2018-09-02 21:35:55 +00:00
|
|
|
if (!in_array(trim($keyword), $siteinfo['keywords'])) {
|
|
|
|
$siteinfo['keywords'][] = trim($keyword);
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-09-02 21:35:55 +00:00
|
|
|
$list = $xpath->query('//meta[@property]');
|
2016-11-24 00:11:22 +00:00
|
|
|
foreach ($list as $node) {
|
2018-09-02 21:35:55 +00:00
|
|
|
$meta_tag = [];
|
2016-11-24 00:11:22 +00:00
|
|
|
if ($node->attributes->length) {
|
|
|
|
foreach ($node->attributes as $attribute) {
|
2018-09-02 21:35:55 +00:00
|
|
|
$meta_tag[$attribute->name] = $attribute->value;
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-09-02 21:35:55 +00:00
|
|
|
if (!empty($meta_tag['content'])) {
|
|
|
|
$meta_tag['content'] = trim(html_entity_decode($meta_tag['content'], ENT_QUOTES, 'UTF-8'));
|
2016-11-24 00:11:22 +00:00
|
|
|
|
2018-09-02 21:35:55 +00:00
|
|
|
switch (strtolower($meta_tag['property'])) {
|
|
|
|
case 'og:image':
|
|
|
|
$siteinfo['image'] = $meta_tag['content'];
|
2016-11-24 00:11:22 +00:00
|
|
|
break;
|
2021-03-15 22:02:21 +00:00
|
|
|
case 'og:image:url':
|
|
|
|
$siteinfo['image'] = $meta_tag['content'];
|
|
|
|
break;
|
|
|
|
case 'og:image:secure_url':
|
|
|
|
$siteinfo['image'] = $meta_tag['content'];
|
|
|
|
break;
|
2018-09-02 21:35:55 +00:00
|
|
|
case 'og:title':
|
|
|
|
$siteinfo['title'] = trim($meta_tag['content']);
|
2016-11-24 00:11:22 +00:00
|
|
|
break;
|
2018-09-02 21:35:55 +00:00
|
|
|
case 'og:description':
|
|
|
|
$siteinfo['text'] = trim($meta_tag['content']);
|
2016-11-24 00:11:22 +00:00
|
|
|
break;
|
2021-03-15 22:02:21 +00:00
|
|
|
case 'og:site_name':
|
2021-03-16 06:37:43 +00:00
|
|
|
$siteinfo['publisher_name'] = trim($meta_tag['content']);
|
2021-03-15 22:02:21 +00:00
|
|
|
break;
|
|
|
|
case 'twitter:description':
|
|
|
|
$siteinfo['text'] = trim($meta_tag['content']);
|
|
|
|
break;
|
|
|
|
case 'twitter:title':
|
|
|
|
$siteinfo['title'] = trim($meta_tag['content']);
|
|
|
|
break;
|
|
|
|
case 'twitter:image':
|
|
|
|
$siteinfo['image'] = $meta_tag['content'];
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
$list = $xpath->query("//script[@type='application/ld+json']");
|
|
|
|
foreach ($list as $node) {
|
|
|
|
if (!empty($node->nodeValue)) {
|
2021-03-22 06:47:04 +00:00
|
|
|
if ($jsonld = json_decode($node->nodeValue, true)) {
|
2021-03-16 22:57:24 +00:00
|
|
|
$siteinfo = self::parseParts($siteinfo, $jsonld);
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-09-06 20:30:16 +00:00
|
|
|
// Prevent to have a photo type without an image
|
2018-09-07 06:10:33 +00:00
|
|
|
if ((empty($siteinfo['image']) || !empty($siteinfo['text'])) && ($siteinfo['type'] == 'photo')) {
|
2018-09-06 20:30:16 +00:00
|
|
|
$siteinfo['type'] = 'link';
|
|
|
|
}
|
|
|
|
|
2021-03-21 14:24:42 +00:00
|
|
|
if (!empty($siteinfo['image'])) {
|
|
|
|
$siteinfo['images'] = $siteinfo['images'] ?? [];
|
|
|
|
array_unshift($siteinfo['images'], ['url' => $siteinfo['image']]);
|
2018-09-02 21:35:55 +00:00
|
|
|
unset($siteinfo['image']);
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
|
2021-03-21 14:24:42 +00:00
|
|
|
$siteinfo = self::checkMedia($url, $siteinfo);
|
|
|
|
|
2019-11-15 13:28:42 +00:00
|
|
|
if (!empty($siteinfo['text']) && mb_strlen($siteinfo['text']) > self::MAX_DESC_COUNT) {
|
|
|
|
$siteinfo['text'] = mb_substr($siteinfo['text'], 0, self::MAX_DESC_COUNT) . '…';
|
|
|
|
$pos = mb_strrpos($siteinfo['text'], '.');
|
|
|
|
if ($pos > self::MIN_DESC_COUNT) {
|
|
|
|
$siteinfo['text'] = mb_substr($siteinfo['text'], 0, $pos + 1);
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2019-11-15 13:28:42 +00:00
|
|
|
Logger::info('Siteinfo fetched', ['url' => $url, 'siteinfo' => $siteinfo]);
|
2016-11-24 00:11:22 +00:00
|
|
|
|
2018-12-26 06:06:24 +00:00
|
|
|
Hook::callAll('getsiteinfo', $siteinfo);
|
2016-11-24 00:11:22 +00:00
|
|
|
|
2018-09-02 21:35:55 +00:00
|
|
|
return $siteinfo;
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|
|
|
|
|
2021-03-21 14:24:42 +00:00
|
|
|
/**
|
|
|
|
* Check the attached media elements.
|
|
|
|
* Fix existing data and add missing data.
|
|
|
|
*
|
|
|
|
* @param string $page_url
|
|
|
|
* @param array $siteinfo
|
|
|
|
* @return void
|
|
|
|
*/
|
|
|
|
private static function checkMedia(string $page_url, array $siteinfo)
|
|
|
|
{
|
|
|
|
if (!empty($siteinfo['images'])) {
|
|
|
|
array_walk($siteinfo['images'], function (&$image) use ($page_url) {
|
2021-03-23 20:03:08 +00:00
|
|
|
$image = [];
|
2021-03-21 14:24:42 +00:00
|
|
|
// According to the specifications someone could place a picture url into the content field as well.
|
|
|
|
// But this doesn't seem to happen in the wild, so we don't cover it here.
|
2021-03-23 20:03:08 +00:00
|
|
|
if (!empty($image['url'])) {
|
|
|
|
$image['url'] = self::completeUrl($image['url'], $page_url);
|
|
|
|
$photodata = Images::getInfoFromURLCached($image['url']);
|
|
|
|
if (!empty($photodata) && ($photodata[0] > 50) && ($photodata[1] > 50)) {
|
|
|
|
$image['src'] = $image['url'];
|
|
|
|
$image['width'] = $photodata[0];
|
|
|
|
$image['height'] = $photodata[1];
|
|
|
|
$image['contenttype'] = $photodata['mime'];
|
|
|
|
unset($image['url']);
|
|
|
|
ksort($image);
|
|
|
|
}
|
2021-03-21 14:24:42 +00:00
|
|
|
}
|
|
|
|
});
|
|
|
|
|
|
|
|
$siteinfo['images'] = array_values(array_filter($siteinfo['images']));
|
|
|
|
}
|
|
|
|
|
|
|
|
foreach (['audio', 'video'] as $element) {
|
|
|
|
if (!empty($siteinfo[$element])) {
|
|
|
|
array_walk($siteinfo[$element], function (&$media) use ($page_url, &$siteinfo) {
|
|
|
|
$url = '';
|
|
|
|
$embed = '';
|
|
|
|
$content = '';
|
|
|
|
$contenttype = '';
|
|
|
|
foreach (['embed', 'content', 'url'] as $field) {
|
|
|
|
if (!empty($media[$field])) {
|
|
|
|
$media[$field] = self::completeUrl($media[$field], $page_url);
|
|
|
|
$type = self::getContentType($media[$field]);
|
2021-03-23 20:03:08 +00:00
|
|
|
if (($type[0] ?? '') == 'text') {
|
2021-03-21 14:24:42 +00:00
|
|
|
if ($field == 'embed') {
|
|
|
|
$embed = $media[$field];
|
|
|
|
} else {
|
|
|
|
$url = $media[$field];
|
|
|
|
}
|
|
|
|
} elseif (!empty($type[0])) {
|
|
|
|
$content = $media[$field];
|
|
|
|
$contenttype = implode('/', $type);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
unset($media[$field]);
|
|
|
|
}
|
|
|
|
|
|
|
|
foreach (['image', 'preview'] as $field) {
|
|
|
|
if (!empty($media[$field])) {
|
|
|
|
$media[$field] = self::completeUrl($media[$field], $page_url);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!empty($url)) {
|
|
|
|
$media['url'] = $url;
|
|
|
|
}
|
|
|
|
if (!empty($embed)) {
|
|
|
|
$media['embed'] = $embed;
|
|
|
|
if (!empty($media['main'])) {
|
|
|
|
$siteinfo['embed'] = $embed;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (!empty($content)) {
|
|
|
|
$media['src'] = $content;
|
|
|
|
}
|
|
|
|
if (!empty($contenttype)) {
|
|
|
|
$media['contenttype'] = $contenttype;
|
|
|
|
}
|
|
|
|
if (empty($url) && empty($content) && empty($embed)) {
|
|
|
|
$media = [];
|
|
|
|
}
|
|
|
|
ksort($media);
|
|
|
|
});
|
|
|
|
|
|
|
|
$siteinfo[$element] = array_values(array_filter($siteinfo[$element]));
|
|
|
|
}
|
|
|
|
if (empty($siteinfo[$element])) {
|
|
|
|
unset($siteinfo[$element]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return $siteinfo;
|
|
|
|
}
|
|
|
|
|
2021-03-16 22:57:24 +00:00
|
|
|
/**
|
2021-03-17 22:29:12 +00:00
|
|
|
* Convert tags from CSV to an array
|
|
|
|
*
|
|
|
|
* @param string $string Tags
|
|
|
|
* @return array with formatted Hashtags
|
|
|
|
*/
|
|
|
|
public static function convertTagsToArray($string)
|
|
|
|
{
|
|
|
|
$arr_tags = str_getcsv($string);
|
|
|
|
if (count($arr_tags)) {
|
|
|
|
// add the # sign to every tag
|
|
|
|
array_walk($arr_tags, ["self", "arrAddHashes"]);
|
|
|
|
|
|
|
|
return $arr_tags;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Add a hasht sign to a string
|
|
|
|
*
|
|
|
|
* This method is used as callback function
|
|
|
|
*
|
|
|
|
* @param string $tag The pure tag name
|
|
|
|
* @param int $k Counter for internal use
|
|
|
|
* @return void
|
|
|
|
*/
|
|
|
|
private static function arrAddHashes(&$tag, $k)
|
|
|
|
{
|
|
|
|
$tag = "#" . $tag;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Add a scheme to an url
|
2021-03-16 22:57:24 +00:00
|
|
|
*
|
2021-03-17 22:29:12 +00:00
|
|
|
* The src attribute of some html elements (e.g. images)
|
|
|
|
* can miss the scheme so we need to add the correct
|
|
|
|
* scheme
|
|
|
|
*
|
|
|
|
* @param string $url The url which possibly does have
|
|
|
|
* a missing scheme (a link to an image)
|
|
|
|
* @param string $scheme The url with a correct scheme
|
|
|
|
* (e.g. the url from the webpage which does contain the image)
|
|
|
|
*
|
|
|
|
* @return string The url with a scheme
|
|
|
|
*/
|
|
|
|
private static function completeUrl($url, $scheme)
|
|
|
|
{
|
|
|
|
$urlarr = parse_url($url);
|
|
|
|
|
|
|
|
// If the url does allready have an scheme
|
|
|
|
// we can stop the process here
|
|
|
|
if (isset($urlarr["scheme"])) {
|
|
|
|
return($url);
|
|
|
|
}
|
|
|
|
|
|
|
|
$schemearr = parse_url($scheme);
|
|
|
|
|
|
|
|
$complete = $schemearr["scheme"]."://".$schemearr["host"];
|
|
|
|
|
|
|
|
if (!empty($schemearr["port"])) {
|
|
|
|
$complete .= ":".$schemearr["port"];
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!empty($urlarr["path"])) {
|
|
|
|
if (strpos($urlarr["path"], "/") !== 0) {
|
|
|
|
$complete .= "/";
|
|
|
|
}
|
|
|
|
|
|
|
|
$complete .= $urlarr["path"];
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!empty($urlarr["query"])) {
|
|
|
|
$complete .= "?".$urlarr["query"];
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!empty($urlarr["fragment"])) {
|
|
|
|
$complete .= "#".$urlarr["fragment"];
|
|
|
|
}
|
|
|
|
|
|
|
|
return($complete);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Parse the Json-Ld parts of a web page
|
|
|
|
*
|
|
|
|
* @param array $siteinfo
|
|
|
|
* @param array $jsonld
|
2021-03-16 22:57:24 +00:00
|
|
|
* @return array siteinfo
|
|
|
|
*/
|
|
|
|
private static function parseParts(array $siteinfo, array $jsonld)
|
|
|
|
{
|
|
|
|
if (!empty($jsonld['@graph']) && is_array($jsonld['@graph'])) {
|
|
|
|
foreach ($jsonld['@graph'] as $part) {
|
2021-03-23 20:03:08 +00:00
|
|
|
if (!empty($part)) {
|
|
|
|
$siteinfo = self::parseParts($siteinfo, $part);
|
|
|
|
}
|
2021-03-16 22:57:24 +00:00
|
|
|
}
|
|
|
|
} elseif (!empty($jsonld['@type'])) {
|
|
|
|
$siteinfo = self::parseJsonLd($siteinfo, $jsonld);
|
|
|
|
} elseif (!empty($jsonld)) {
|
|
|
|
$keys = array_keys($jsonld);
|
|
|
|
$numeric_keys = true;
|
|
|
|
foreach ($keys as $key) {
|
|
|
|
if (!is_int($key)) {
|
|
|
|
$numeric_keys = false;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if ($numeric_keys) {
|
|
|
|
foreach ($jsonld as $part) {
|
2021-03-23 20:03:08 +00:00
|
|
|
if (!empty($part)) {
|
|
|
|
$siteinfo = self::parseParts($siteinfo, $part);
|
|
|
|
}
|
2021-03-22 06:47:04 +00:00
|
|
|
}
|
2021-03-16 22:57:24 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2021-03-22 06:47:04 +00:00
|
|
|
array_walk_recursive($siteinfo, function (&$element) {
|
|
|
|
if (is_string($element)) {
|
|
|
|
$element = html_entity_decode($element, ENT_COMPAT, 'UTF-8');
|
|
|
|
}
|
|
|
|
});
|
|
|
|
|
2021-03-16 22:57:24 +00:00
|
|
|
return $siteinfo;
|
|
|
|
}
|
|
|
|
|
2021-03-15 22:02:21 +00:00
|
|
|
/**
|
|
|
|
* Improve the siteinfo with information from the provided JSON-LD information
|
|
|
|
* @see https://jsonld.com/
|
2021-03-17 22:29:12 +00:00
|
|
|
* @see https://schema.org/
|
2021-03-15 22:02:21 +00:00
|
|
|
*
|
|
|
|
* @param array $siteinfo
|
|
|
|
* @param array $jsonld
|
|
|
|
* @return array siteinfo
|
|
|
|
*/
|
|
|
|
private static function parseJsonLd(array $siteinfo, array $jsonld)
|
|
|
|
{
|
|
|
|
$type = JsonLD::fetchElement($jsonld, '@type');
|
2021-03-16 22:57:24 +00:00
|
|
|
if (empty($type)) {
|
|
|
|
Logger::info('Empty type', ['url' => $siteinfo['url']]);
|
|
|
|
return $siteinfo;
|
|
|
|
}
|
2021-03-15 22:02:21 +00:00
|
|
|
|
2021-03-17 17:11:50 +00:00
|
|
|
// Silently ignore some types that aren't processed
|
2021-03-17 22:29:12 +00:00
|
|
|
if (in_array($type, ['SiteNavigationElement', 'JobPosting', 'CreativeWork', 'MusicAlbum',
|
2021-03-18 08:04:52 +00:00
|
|
|
'WPHeader', 'WPSideBar', 'WPFooter', 'LegalService', 'MusicRecording',
|
2021-03-17 17:11:50 +00:00
|
|
|
'ItemList', 'BreadcrumbList', 'Blog', 'Dataset', 'Product'])) {
|
|
|
|
return $siteinfo;
|
|
|
|
}
|
|
|
|
|
2021-03-15 22:02:21 +00:00
|
|
|
switch ($type) {
|
|
|
|
case 'Article':
|
2021-03-17 17:11:50 +00:00
|
|
|
case 'AdvertiserContentArticle':
|
2021-03-15 22:02:21 +00:00
|
|
|
case 'NewsArticle':
|
2021-03-17 17:11:50 +00:00
|
|
|
case 'Report':
|
|
|
|
case 'SatiricalArticle':
|
2021-03-16 22:57:24 +00:00
|
|
|
case 'ScholarlyArticle':
|
2021-03-17 17:11:50 +00:00
|
|
|
case 'SocialMediaPosting':
|
|
|
|
case 'TechArticle':
|
2021-03-16 22:57:24 +00:00
|
|
|
case 'ReportageNewsArticle':
|
2021-03-17 07:36:16 +00:00
|
|
|
case 'SocialMediaPosting':
|
|
|
|
case 'BlogPosting':
|
2021-03-17 17:11:50 +00:00
|
|
|
case 'LiveBlogPosting':
|
2021-03-17 07:36:16 +00:00
|
|
|
case 'DiscussionForumPosting':
|
2021-03-15 22:02:21 +00:00
|
|
|
return self::parseJsonLdArticle($siteinfo, $jsonld);
|
|
|
|
case 'WebPage':
|
2021-03-17 17:11:50 +00:00
|
|
|
case 'AboutPage':
|
|
|
|
case 'CheckoutPage':
|
2021-03-17 07:36:16 +00:00
|
|
|
case 'CollectionPage':
|
2021-03-17 17:11:50 +00:00
|
|
|
case 'ContactPage':
|
|
|
|
case 'FAQPage':
|
|
|
|
case 'ItemPage':
|
|
|
|
case 'MedicalWebPage':
|
|
|
|
case 'ProfilePage':
|
|
|
|
case 'QAPage':
|
|
|
|
case 'RealEstateListing':
|
|
|
|
case 'SearchResultsPage':
|
|
|
|
case 'MediaGallery':
|
2021-03-17 07:36:16 +00:00
|
|
|
case 'ImageGallery':
|
2021-03-17 17:11:50 +00:00
|
|
|
case 'VideoGallery':
|
2021-03-16 22:57:24 +00:00
|
|
|
case 'RadioEpisode':
|
|
|
|
case 'Event':
|
2021-03-15 22:02:21 +00:00
|
|
|
return self::parseJsonLdWebPage($siteinfo, $jsonld);
|
|
|
|
case 'WebSite':
|
|
|
|
return self::parseJsonLdWebSite($siteinfo, $jsonld);
|
|
|
|
case 'Organization':
|
2021-03-17 17:11:50 +00:00
|
|
|
case 'Airline':
|
|
|
|
case 'Consortium':
|
|
|
|
case 'Corporation':
|
|
|
|
case 'EducationalOrganization':
|
|
|
|
case 'FundingScheme':
|
|
|
|
case 'GovernmentOrganization':
|
|
|
|
case 'LibrarySystem':
|
2021-03-16 22:57:24 +00:00
|
|
|
case 'LocalBusiness':
|
2021-03-17 17:11:50 +00:00
|
|
|
case 'MedicalOrganization':
|
|
|
|
case 'NGO':
|
|
|
|
case 'NewsMediaOrganization':
|
|
|
|
case 'Project':
|
|
|
|
case 'SportsOrganization':
|
|
|
|
case 'WorkersUnion':
|
2021-03-17 07:36:16 +00:00
|
|
|
return self::parseJsonLdWebOrganization($siteinfo, $jsonld);
|
2021-03-15 22:02:21 +00:00
|
|
|
case 'Person':
|
2021-03-17 17:11:50 +00:00
|
|
|
case 'Patient':
|
2021-03-17 22:29:12 +00:00
|
|
|
case 'PerformingGroup':
|
2021-03-17 17:11:50 +00:00
|
|
|
case 'DanceGroup';
|
|
|
|
case 'MusicGroup':
|
|
|
|
case 'TheaterGroup':
|
2021-03-15 22:02:21 +00:00
|
|
|
return self::parseJsonLdWebPerson($siteinfo, $jsonld);
|
2021-03-16 22:57:24 +00:00
|
|
|
case 'AudioObject':
|
2021-03-17 07:36:16 +00:00
|
|
|
case 'Audio':
|
|
|
|
return self::parseJsonLdMediaObject($siteinfo, $jsonld, 'audio');
|
2021-03-15 22:02:21 +00:00
|
|
|
case 'VideoObject':
|
2021-03-17 07:36:16 +00:00
|
|
|
return self::parseJsonLdMediaObject($siteinfo, $jsonld, 'video');
|
2021-03-15 22:02:21 +00:00
|
|
|
case 'ImageObject':
|
2021-03-17 07:36:16 +00:00
|
|
|
return self::parseJsonLdMediaObject($siteinfo, $jsonld, 'images');
|
2021-03-15 22:02:21 +00:00
|
|
|
default:
|
2021-03-17 17:11:50 +00:00
|
|
|
Logger::info('Unknown type', ['type' => $type, 'url' => $siteinfo['url']]);
|
2021-03-15 22:02:21 +00:00
|
|
|
return $siteinfo;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2021-03-17 22:29:12 +00:00
|
|
|
* Fetch author and publisher data
|
2021-03-15 22:02:21 +00:00
|
|
|
*
|
|
|
|
* @param array $siteinfo
|
|
|
|
* @param array $jsonld
|
|
|
|
* @return array siteinfo
|
|
|
|
*/
|
|
|
|
private static function parseJsonLdAuthor(array $siteinfo, array $jsonld)
|
|
|
|
{
|
|
|
|
$jsonldinfo = [];
|
|
|
|
|
2021-03-16 06:37:43 +00:00
|
|
|
if (!empty($jsonld['publisher']) && is_array($jsonld['publisher'])) {
|
2021-03-16 22:57:24 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'publisher', 'name');
|
2021-03-16 11:32:56 +00:00
|
|
|
if (!empty($content) && is_string($content)) {
|
|
|
|
$jsonldinfo['publisher_name'] = trim($content);
|
|
|
|
}
|
|
|
|
|
2021-03-16 22:57:24 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'publisher', 'url');
|
2021-03-15 22:02:21 +00:00
|
|
|
if (!empty($content) && is_string($content)) {
|
|
|
|
$jsonldinfo['publisher_url'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$brand = JsonLD::fetchElement($jsonld, 'publisher', 'brand', '@type', 'Organization');
|
2021-03-16 11:32:56 +00:00
|
|
|
if (!empty($brand) && is_array($brand)) {
|
2021-03-17 23:31:16 +00:00
|
|
|
$content = JsonLD::fetchElement($brand, 'name');
|
2021-03-15 22:02:21 +00:00
|
|
|
if (!empty($content) && is_string($content)) {
|
2021-03-16 06:37:43 +00:00
|
|
|
$jsonldinfo['publisher_name'] = trim($content);
|
2021-03-15 22:02:21 +00:00
|
|
|
}
|
2021-03-17 23:31:16 +00:00
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($brand, 'url');
|
2021-03-17 17:11:50 +00:00
|
|
|
if (!empty($content) && is_string($content)) {
|
|
|
|
$jsonldinfo['publisher_url'] = trim($content);
|
|
|
|
}
|
2021-03-17 23:31:16 +00:00
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($brand, 'logo', 'url');
|
|
|
|
if (!empty($content) && is_string($content)) {
|
|
|
|
$jsonldinfo['publisher_img'] = trim($content);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
$logo = JsonLD::fetchElement($jsonld, 'publisher', 'logo');
|
|
|
|
if (!empty($logo) && is_array($logo)) {
|
|
|
|
$content = JsonLD::fetchElement($logo, 'url');
|
|
|
|
if (!empty($content) && is_string($content)) {
|
|
|
|
$jsonldinfo['publisher_img'] = trim($content);
|
|
|
|
}
|
2021-03-15 22:02:21 +00:00
|
|
|
}
|
2021-03-16 22:57:24 +00:00
|
|
|
} elseif (!empty($jsonld['publisher']) && is_string($jsonld['publisher'])) {
|
|
|
|
$jsonldinfo['publisher_name'] = trim($jsonld['publisher']);
|
2021-03-15 22:02:21 +00:00
|
|
|
}
|
|
|
|
|
2021-03-16 06:37:43 +00:00
|
|
|
if (!empty($jsonld['author']) && is_array($jsonld['author'])) {
|
2021-03-16 22:57:24 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'author', 'name');
|
2021-03-15 22:02:21 +00:00
|
|
|
if (!empty($content) && is_string($content)) {
|
2021-03-16 11:32:56 +00:00
|
|
|
$jsonldinfo['author_name'] = trim($content);
|
2021-03-15 22:02:21 +00:00
|
|
|
}
|
|
|
|
|
2021-03-16 22:57:24 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'author', 'sameAs');
|
2021-03-15 22:02:21 +00:00
|
|
|
if (!empty($content) && is_string($content)) {
|
2021-03-16 11:32:56 +00:00
|
|
|
$jsonldinfo['author_url'] = trim($content);
|
2021-03-15 22:02:21 +00:00
|
|
|
}
|
|
|
|
|
2021-03-16 22:57:24 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'author', 'url');
|
2021-03-15 22:02:21 +00:00
|
|
|
if (!empty($content) && is_string($content)) {
|
|
|
|
$jsonldinfo['author_url'] = trim($content);
|
|
|
|
}
|
2021-03-17 23:31:16 +00:00
|
|
|
|
|
|
|
$logo = JsonLD::fetchElement($jsonld, 'author', 'logo');
|
|
|
|
if (!empty($logo) && is_array($logo)) {
|
|
|
|
$content = JsonLD::fetchElement($logo, 'url');
|
|
|
|
if (!empty($content) && is_string($content)) {
|
|
|
|
$jsonldinfo['author_img'] = trim($content);
|
|
|
|
}
|
|
|
|
}
|
2021-03-16 22:57:24 +00:00
|
|
|
} elseif (!empty($jsonld['author']) && is_string($jsonld['author'])) {
|
|
|
|
$jsonldinfo['author_name'] = trim($jsonld['author']);
|
2021-03-15 22:02:21 +00:00
|
|
|
}
|
|
|
|
|
2021-03-17 22:29:12 +00:00
|
|
|
Logger::info('Fetched Author information', ['fetched' => $jsonldinfo]);
|
2021-03-15 22:02:21 +00:00
|
|
|
|
|
|
|
return array_merge($siteinfo, $jsonldinfo);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2021-03-17 22:29:12 +00:00
|
|
|
* Fetch data from the provided JSON-LD Article type
|
2021-03-17 07:36:16 +00:00
|
|
|
* @see https://schema.org/Article
|
2021-03-15 22:02:21 +00:00
|
|
|
*
|
|
|
|
* @param array $siteinfo
|
|
|
|
* @param array $jsonld
|
|
|
|
* @return array siteinfo
|
|
|
|
*/
|
|
|
|
private static function parseJsonLdArticle(array $siteinfo, array $jsonld)
|
|
|
|
{
|
|
|
|
$jsonldinfo = [];
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'headline');
|
|
|
|
if (!empty($content) && is_string($content)) {
|
|
|
|
$jsonldinfo['title'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'alternativeHeadline');
|
2021-03-16 22:57:24 +00:00
|
|
|
if (!empty($content) && is_string($content) && (($jsonldinfo['title'] ?? '') != trim($content))) {
|
2021-03-15 22:02:21 +00:00
|
|
|
$jsonldinfo['alternative_title'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'description');
|
|
|
|
if (!empty($content) && is_string($content)) {
|
|
|
|
$jsonldinfo['text'] = trim($content);
|
|
|
|
}
|
|
|
|
|
2021-03-16 22:57:24 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'thumbnailUrl');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$jsonldinfo['image'] = trim($content);
|
|
|
|
}
|
|
|
|
|
2021-03-15 22:02:21 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'image', 'url', '@type', 'ImageObject');
|
|
|
|
if (!empty($content) && is_string($content)) {
|
|
|
|
$jsonldinfo['image'] = trim($content);
|
|
|
|
}
|
|
|
|
|
2021-03-16 22:57:24 +00:00
|
|
|
if (!empty($jsonld['keywords']) && !is_array($jsonld['keywords'])) {
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'keywords');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$siteinfo['keywords'] = [];
|
|
|
|
$keywords = explode(',', $content);
|
|
|
|
foreach ($keywords as $keyword) {
|
|
|
|
$siteinfo['keywords'][] = trim($keyword);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
$content = JsonLD::fetchElementArray($jsonld, 'keywords');
|
|
|
|
if (!empty($content) && is_array($content)) {
|
|
|
|
$jsonldinfo['keywords'] = $content;
|
|
|
|
}
|
|
|
|
}
|
2021-03-15 22:02:21 +00:00
|
|
|
|
|
|
|
$jsonldinfo = self::parseJsonLdAuthor($jsonldinfo, $jsonld);
|
|
|
|
|
|
|
|
Logger::info('Fetched article information', ['url' => $siteinfo['url'], 'fetched' => $jsonldinfo]);
|
|
|
|
|
|
|
|
return array_merge($siteinfo, $jsonldinfo);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2021-03-17 22:29:12 +00:00
|
|
|
* Fetch data from the provided JSON-LD WebPage type
|
2021-03-17 07:36:16 +00:00
|
|
|
* @see https://schema.org/WebPage
|
2021-03-15 22:02:21 +00:00
|
|
|
*
|
|
|
|
* @param array $siteinfo
|
|
|
|
* @param array $jsonld
|
|
|
|
* @return array siteinfo
|
|
|
|
*/
|
|
|
|
private static function parseJsonLdWebPage(array $siteinfo, array $jsonld)
|
|
|
|
{
|
|
|
|
$jsonldinfo = [];
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'name');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$jsonldinfo['title'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'description');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$jsonldinfo['text'] = trim($content);
|
|
|
|
}
|
|
|
|
|
2021-03-16 22:57:24 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'image');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$jsonldinfo['image'] = trim($content);
|
|
|
|
}
|
|
|
|
|
2021-03-15 22:02:21 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'thumbnailUrl');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$jsonldinfo['image'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$jsonldinfo = self::parseJsonLdAuthor($jsonldinfo, $jsonld);
|
|
|
|
|
2021-03-17 22:29:12 +00:00
|
|
|
Logger::info('Fetched WebPage information', ['url' => $siteinfo['url'], 'fetched' => $jsonldinfo]);
|
2021-03-15 22:02:21 +00:00
|
|
|
|
|
|
|
return array_merge($siteinfo, $jsonldinfo);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2021-03-17 22:29:12 +00:00
|
|
|
* Fetch data from the provided JSON-LD WebSite type
|
2021-03-17 07:36:16 +00:00
|
|
|
* @see https://schema.org/WebSite
|
2021-03-15 22:02:21 +00:00
|
|
|
*
|
|
|
|
* @param array $siteinfo
|
|
|
|
* @param array $jsonld
|
|
|
|
* @return array siteinfo
|
|
|
|
*/
|
|
|
|
private static function parseJsonLdWebSite(array $siteinfo, array $jsonld)
|
|
|
|
{
|
|
|
|
$jsonldinfo = [];
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'name');
|
|
|
|
if (!empty($content)) {
|
2021-03-16 06:37:43 +00:00
|
|
|
$jsonldinfo['publisher_name'] = trim($content);
|
2021-03-15 22:02:21 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'description');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$jsonldinfo['publisher_description'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'url');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$jsonldinfo['publisher_url'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'thumbnailUrl');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$jsonldinfo['image'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$jsonldinfo = self::parseJsonLdAuthor($jsonldinfo, $jsonld);
|
|
|
|
|
|
|
|
Logger::info('Fetched WebSite information', ['url' => $siteinfo['url'], 'fetched' => $jsonldinfo]);
|
|
|
|
return array_merge($siteinfo, $jsonldinfo);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2021-03-17 22:29:12 +00:00
|
|
|
* Fetch data from the provided JSON-LD Organization type
|
2021-03-17 07:36:16 +00:00
|
|
|
* @see https://schema.org/Organization
|
2021-03-15 22:02:21 +00:00
|
|
|
*
|
|
|
|
* @param array $siteinfo
|
|
|
|
* @param array $jsonld
|
|
|
|
* @return array siteinfo
|
|
|
|
*/
|
|
|
|
private static function parseJsonLdWebOrganization(array $siteinfo, array $jsonld)
|
|
|
|
{
|
|
|
|
$jsonldinfo = [];
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'name');
|
|
|
|
if (!empty($content)) {
|
2021-03-16 06:37:43 +00:00
|
|
|
$jsonldinfo['publisher_name'] = trim($content);
|
2021-03-15 22:02:21 +00:00
|
|
|
}
|
|
|
|
|
2021-03-16 22:57:24 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'description');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$jsonldinfo['publisher_description'] = trim($content);
|
|
|
|
}
|
|
|
|
|
2021-03-15 22:02:21 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'url');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$jsonldinfo['publisher_url'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'logo', 'url', '@type', 'ImageObject');
|
|
|
|
if (!empty($content)) {
|
2021-03-16 06:37:43 +00:00
|
|
|
$jsonldinfo['publisher_img'] = trim($content);
|
2021-03-15 22:02:21 +00:00
|
|
|
}
|
|
|
|
|
2021-03-17 17:11:50 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'brand', 'name', '@type', 'Organization');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$jsonldinfo['publisher_name'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'brand', 'url', '@type', 'Organization');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$jsonldinfo['publisher_url'] = trim($content);
|
|
|
|
}
|
|
|
|
|
2021-03-15 22:02:21 +00:00
|
|
|
Logger::info('Fetched Organization information', ['url' => $siteinfo['url'], 'fetched' => $jsonldinfo]);
|
|
|
|
return array_merge($siteinfo, $jsonldinfo);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2021-03-17 22:29:12 +00:00
|
|
|
* Fetch data from the provided JSON-LD Person type
|
2021-03-17 07:36:16 +00:00
|
|
|
* @see https://schema.org/Person
|
2021-03-15 22:02:21 +00:00
|
|
|
*
|
|
|
|
* @param array $siteinfo
|
|
|
|
* @param array $jsonld
|
|
|
|
* @return array siteinfo
|
|
|
|
*/
|
|
|
|
private static function parseJsonLdWebPerson(array $siteinfo, array $jsonld)
|
|
|
|
{
|
|
|
|
$jsonldinfo = [];
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'name');
|
|
|
|
if (!empty($content)) {
|
2021-03-16 06:37:43 +00:00
|
|
|
$jsonldinfo['author_name'] = trim($content);
|
2021-03-15 22:02:21 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'description');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$jsonldinfo['author_description'] = trim($content);
|
|
|
|
}
|
|
|
|
|
2021-03-17 17:11:50 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'sameAs');
|
|
|
|
if (!empty($content) && is_string($content)) {
|
|
|
|
$jsonldinfo['author_url'] = trim($content);
|
|
|
|
}
|
|
|
|
|
2021-03-15 22:02:21 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'url');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$jsonldinfo['author_url'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'image', 'url', '@type', 'ImageObject');
|
|
|
|
if (!empty($content)) {
|
2021-03-16 06:37:43 +00:00
|
|
|
$jsonldinfo['author_img'] = trim($content);
|
2021-03-15 22:02:21 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
Logger::info('Fetched Person information', ['url' => $siteinfo['url'], 'fetched' => $jsonldinfo]);
|
|
|
|
return array_merge($siteinfo, $jsonldinfo);
|
|
|
|
}
|
|
|
|
|
2021-03-16 22:57:24 +00:00
|
|
|
/**
|
2021-03-17 22:29:12 +00:00
|
|
|
* Fetch data from the provided JSON-LD MediaObject type
|
2021-03-17 07:36:16 +00:00
|
|
|
* @see https://schema.org/MediaObject
|
2021-03-16 22:57:24 +00:00
|
|
|
*
|
|
|
|
* @param array $siteinfo
|
|
|
|
* @param array $jsonld
|
|
|
|
* @return array siteinfo
|
|
|
|
*/
|
2021-03-17 07:36:16 +00:00
|
|
|
private static function parseJsonLdMediaObject(array $siteinfo, array $jsonld, string $name)
|
2021-03-16 22:57:24 +00:00
|
|
|
{
|
2021-03-17 07:36:16 +00:00
|
|
|
$media = [];
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'caption');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$media['caption'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'url');
|
|
|
|
if (!empty($content)) {
|
2021-03-21 14:24:42 +00:00
|
|
|
$media['url'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'mainEntityOfPage');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$media['main'] = Strings::compareLink($content, $siteinfo['url']);
|
2021-03-17 07:36:16 +00:00
|
|
|
}
|
2021-03-16 22:57:24 +00:00
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'description');
|
|
|
|
if (!empty($content)) {
|
2021-03-17 07:36:16 +00:00
|
|
|
$media['description'] = trim($content);
|
2021-03-16 22:57:24 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'name');
|
2021-03-17 07:36:16 +00:00
|
|
|
if (!empty($content) && (($media['description'] ?? '') != trim($content))) {
|
|
|
|
$media['name'] = trim($content);
|
2021-03-16 22:57:24 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'contentUrl');
|
|
|
|
if (!empty($content)) {
|
2021-03-17 07:36:16 +00:00
|
|
|
$media['content'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'embedUrl');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$media['embed'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'height');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$media['height'] = trim($content);
|
|
|
|
}
|
|
|
|
|
|
|
|
$content = JsonLD::fetchElement($jsonld, 'width');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$media['width'] = trim($content);
|
2021-03-16 22:57:24 +00:00
|
|
|
}
|
|
|
|
|
2021-03-17 07:36:16 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'image');
|
|
|
|
if (!empty($content)) {
|
|
|
|
$media['image'] = trim($content);
|
|
|
|
}
|
|
|
|
|
2021-03-21 14:24:42 +00:00
|
|
|
$content = JsonLD::fetchElement($jsonld, 'thumbnailUrl');
|
|
|
|
if (!empty($content) && (($media['image'] ?? '') != trim($content))) {
|
|
|
|
if (!empty($media['image'])) {
|
|
|
|
$media['preview'] = trim($content);
|
|
|
|
} else {
|
|
|
|
$media['image'] = trim($content);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2021-03-17 07:36:16 +00:00
|
|
|
Logger::info('Fetched Media information', ['url' => $siteinfo['url'], 'fetched' => $media]);
|
|
|
|
$siteinfo[$name][] = $media;
|
|
|
|
return $siteinfo;
|
2021-03-16 22:57:24 +00:00
|
|
|
}
|
2016-11-24 00:11:22 +00:00
|
|
|
}
|