From 0a83546411bac7b3bef33284b8574e4e2014f4e8 Mon Sep 17 00:00:00 2001 From: Brian Huisman Date: Mon, 19 Jun 2023 11:51:57 -0400 Subject: [PATCH] Update crawler.php Make sure regexp lines in require and ignore URL fields are actually treated as regexps. --- orcinus/crawler.php | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/orcinus/crawler.php b/orcinus/crawler.php index 873a271..975a65c 100644 --- a/orcinus/crawler.php +++ b/orcinus/crawler.php @@ -116,7 +116,7 @@ function OS_filterURL($_, $base) { $foundRequired = false; foreach ($_RDATA['sp_require_url'] as $requireURL) { if ($requireURL[0] == '*') { - if (preg_match('/'.preg_quote(substr($requireURL, 1), '/').'/', $_)) + if (preg_match('/'.str_replace('/', '\/', substr($requireURL, 1)).'/', $_)) $foundRequired = true; } else if (strpos($_, $requireURL) !== false) $foundRequired = true; @@ -128,7 +128,7 @@ function OS_filterURL($_, $base) { // Ignore URL matches foreach ($_RDATA['sp_ignore_url'] as $ignoreURL) { if ($ignoreURL[0] == '*') { - if (preg_match('/'.preg_quote(substr($ignoreURL, 1), '/').'/', $_)) + if (preg_match('/'.str_replace('/', '\/', substr($ignoreURL, 1)).'/', $_)) return $_RDATA['sp_filter'][$_] = 'ignore-url'; } else if (strpos($_, $ignoreURL) !== false) return $_RDATA['sp_filter'][$_] = 'ignore-url';