diff --git a/src/Content/OEmbed.php b/src/Content/OEmbed.php index bf3c113b71..45e352c152 100644 --- a/src/Content/OEmbed.php +++ b/src/Content/OEmbed.php @@ -151,7 +151,7 @@ class OEmbed // Improve the OEmbed data with data from OpenGraph, Twitter cards and other sources if ($use_parseurl) { - $data = ParseUrl::getSiteinfoCached($embedurl, true, false); + $data = ParseUrl::getSiteinfoCached($embedurl, false); if (($oembed->type == 'error') && empty($data['title']) && empty($data['text'])) { return $oembed; diff --git a/src/Content/PageInfo.php b/src/Content/PageInfo.php index 776dc15df5..3cfab3769d 100644 --- a/src/Content/PageInfo.php +++ b/src/Content/PageInfo.php @@ -187,7 +187,7 @@ class PageInfo */ public static function queryUrl(string $url, string $photo = '', bool $keywords = false, string $keyword_denylist = '') { - $data = ParseUrl::getSiteinfoCached($url, true); + $data = ParseUrl::getSiteinfoCached($url); if ($photo != '') { $data['images'][0]['src'] = $photo; diff --git a/src/Content/Text/BBCode.php b/src/Content/Text/BBCode.php index 6101f5479c..eaa5e16405 100644 --- a/src/Content/Text/BBCode.php +++ b/src/Content/Text/BBCode.php @@ -322,14 +322,14 @@ class BBCode $data = ['url' => $url, 'type' => 'photo']; } else { // Checking, if the link goes to a picture - $data = ParseUrl::getSiteinfoCached($pictures[0][1], true); + $data = ParseUrl::getSiteinfoCached($pictures[0][1]); } // Workaround: // Sometimes photo posts to the own album are not detected at the start. // So we seem to cannot use the cache for these cases. That's strange. if (($data['type'] != 'photo') && strstr($pictures[0][1], "/photos/")) { - $data = ParseUrl::getSiteinfo($pictures[0][1], true); + $data = ParseUrl::getSiteinfo($pictures[0][1]); } if ($data['type'] == 'photo') { @@ -416,7 +416,7 @@ class BBCode $post['text'] = trim($body); } } elseif (isset($post['url']) && ($post['type'] == 'video')) { - $data = ParseUrl::getSiteinfoCached($post['url'], true); + $data = ParseUrl::getSiteinfoCached($post['url']); if (isset($data['images'][0])) { $post['image'] = $data['images'][0]['src']; diff --git a/src/Protocol/Feed.php b/src/Protocol/Feed.php index 196d7c04f3..afa0d9a232 100644 --- a/src/Protocol/Feed.php +++ b/src/Protocol/Feed.php @@ -484,7 +484,7 @@ class Feed $item["body"] = trim($item["title"]); } - $data = ParseUrl::getSiteinfoCached($item['plink'], true); + $data = ParseUrl::getSiteinfoCached($item['plink']); if (!empty($data['text']) && !empty($data['title']) && (mb_strlen($item['body']) < mb_strlen($data['text']))) { // When the fetched page info text is longer than the body, we do try to enhance the body if (!empty($item['body']) && (strpos($data['title'], $item['body']) === false) && (strpos($data['text'], $item['body']) === false)) { diff --git a/src/Util/ParseUrl.php b/src/Util/ParseUrl.php index cca158c26a..e57be2412f 100644 --- a/src/Util/ParseUrl.php +++ b/src/Util/ParseUrl.php @@ -75,8 +75,6 @@ class ParseUrl * Search for chached embeddable data of an url otherwise fetch it * * @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 * @@ -85,7 +83,7 @@ class ParseUrl * string 'type' => Content type * string 'title' => (optional) The title of the content * string 'text' => (optional) The description for the content - * string 'image' => (optional) A preview image of the content (only available if $no_geuessing = false) + * string 'image' => (optional) A preview image of the content * array 'images' => (optional) Array of preview pictures * string 'keywords' => (optional) The tags which belong to the content * @@ -93,7 +91,7 @@ class ParseUrl * @see ParseUrl::getSiteinfo() for more information about scraping * embeddable content */ - public static function getSiteinfoCached($url, $no_guessing = false, $do_oembed = true): array + public static function getSiteinfoCached($url, $do_oembed = true): array { if (empty($url)) { return [ @@ -105,14 +103,14 @@ class ParseUrl $urlHash = hash('sha256', $url); $parsed_url = DBA::selectFirst('parsed_url', ['content'], - ['url_hash' => $urlHash, 'guessing' => !$no_guessing, 'oembed' => $do_oembed] + ['url_hash' => $urlHash, 'oembed' => $do_oembed] ); if (!empty($parsed_url['content'])) { $data = unserialize($parsed_url['content']); return $data; } - $data = self::getSiteinfo($url, $no_guessing, $do_oembed); + $data = self::getSiteinfo($url, $do_oembed); $expires = $data['expires']; @@ -122,7 +120,6 @@ class ParseUrl 'parsed_url', [ 'url_hash' => $urlHash, - 'guessing' => !$no_guessing, 'oembed' => $do_oembed, 'url' => $url, 'content' => serialize($data), @@ -146,8 +143,6 @@ class ParseUrl * \ * * @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 * @param int $count Internal counter to avoid endless loops @@ -157,7 +152,7 @@ class ParseUrl * string 'type' => Content type (error, link, photo, image, audio, video) * string 'title' => (optional) The title of the content * string 'text' => (optional) The description for the content - * string 'image' => (optional) A preview image of the content (only available if $no_guessing = false) + * string 'image' => (optional) A preview image of the content * array 'images' => (optional) Array of preview pictures * string 'keywords' => (optional) The tags which belong to the content * @@ -175,7 +170,7 @@ class ParseUrl * * @endverbatim */ - public static function getSiteinfo($url, $no_guessing = false, $do_oembed = true, $count = 1) + public static function getSiteinfo($url, $do_oembed = true, $count = 1) { if (empty($url)) { return [ @@ -343,7 +338,7 @@ class ParseUrl } } if ($content != '') { - $siteinfo = self::getSiteinfo($content, $no_guessing, $do_oembed, ++$count); + $siteinfo = self::getSiteinfo($content, $do_oembed, ++$count); return $siteinfo; } }