From 6323ac88409c374c7e9d115679487056eba110ee Mon Sep 17 00:00:00 2001 From: Joachim Nickel Date: Thu, 22 Oct 2020 12:16:55 +0200 Subject: [PATCH 1/4] Adding 5 new Crawlers --- src/Fixtures/Crawlers.php | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/src/Fixtures/Crawlers.php b/src/Fixtures/Crawlers.php index 59ec81c..06abba2 100644 --- a/src/Fixtures/Crawlers.php +++ b/src/Fixtures/Crawlers.php @@ -539,6 +539,7 @@ class Crawlers extends AbstractProvider 'httrack', 'huaweisymantec', 'HubSpot ', + 'HubSpot-Link-Resolver', 'Humanlinks', 'i2kconnect\/', 'Iblog', @@ -925,6 +926,7 @@ class Crawlers extends AbstractProvider 'Quora Link Preview', 'Qwantify', 'Radian6', + 'Railgun\/', 'RankActive', 'RankFlex', 'RankSonicSiteAuditor', @@ -952,6 +954,7 @@ class Crawlers extends AbstractProvider 'ROI Hunter', 'RPT-HTTPClient', 'RSSOwl', + 'RSSMix\/', 'RyowlEngine', 'safe-agent-scanner', 'SalesIntelligent', @@ -981,6 +984,7 @@ class Crawlers extends AbstractProvider 'Searchestate', 'SearchExpress', 'SearchSight', + 'SearchWP', 'Seeker', 'semanticdiscovery', 'semanticjuice', @@ -1083,6 +1087,7 @@ class Crawlers extends AbstractProvider 'StatusCake', 'Steeler', 'Stratagems Kumo', + 'Stripe\/', 'Stroke\.cz', 'StudioFACA', 'StumbleUpon', @@ -1342,6 +1347,7 @@ class Crawlers extends AbstractProvider 'ZnajdzFoto', 'ZnHTTP', 'Zombie\.js', + 'ZoominfoBot', 'Zoom\.Mac', 'ZoteroTranslationServer', 'ZyBorg', From a10d72039be663c70d96eefdc088e8c15b122488 Mon Sep 17 00:00:00 2001 From: Joachim Nickel Date: Thu, 22 Oct 2020 15:16:32 +0200 Subject: [PATCH 2/4] Adding 3 more Crawlers and Tests vor my last submission --- src/Fixtures/Crawlers.php | 3 +++ tests/crawlers.txt | 13 ++++++++++++- 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/src/Fixtures/Crawlers.php b/src/Fixtures/Crawlers.php index 06abba2..5105dc7 100644 --- a/src/Fixtures/Crawlers.php +++ b/src/Fixtures/Crawlers.php @@ -124,6 +124,7 @@ class Crawlers extends AbstractProvider 'aria2', 'Arukereso', 'asafaweb', + 'Asana/', 'AskQuickly', 'Ask Jeeves', 'ASPSeek', @@ -697,6 +698,7 @@ class Crawlers extends AbstractProvider 'Mass Downloader', 'masscan\/', 'Mata Hari', + 'mattermost', 'Mediametric', 'Mediapartners-Google', 'mediawords', @@ -1295,6 +1297,7 @@ class Crawlers extends AbstractProvider 'WordupinfoSearch', 'wotbox', 'WP Engine Install Performance API', + 'WP Rocket', 'wpif', 'wprecon\.com survey', 'WPScan', diff --git a/tests/crawlers.txt b/tests/crawlers.txt index fca812b..1b383bd 100644 --- a/tests/crawlers.txt +++ b/tests/crawlers.txt @@ -2608,6 +2608,7 @@ Mozilla/5.0 [en] (X11, U; OpenVAS 7.0.10) JetBrains Omea Reader 1.0.x (http://www.jetbrains.com/omea_reader/) JetBrains Omea Reader 2.0 Release Candidate 1 (http://www.jetbrains.com/omea_reader/) okhttp/2.5.0 +okhttp/4.9.0 oegp v. 1.3.0 Nuzzel Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.134 Safari/537.36 http://notifyninja.com/monitoring @@ -3564,5 +3565,15 @@ Florienzh/1.0 BKCTwitterUnshortener/0.1 (Contact: systems@cyber.harvard.edu) Syndirella/0.91pre PodcastAddict/v2 - Dalvik/2.1.0 (Linux; U; Android 6.0.1; SM-G920F Build/MMB29K) +PodcastAddict/v5 (+https://podcastaddict.com/; Android podcast app) PDF24 URL To PDF -MacOutlook/16.41.20091302 (Intelx64 Mac OS X 10.14.4 (Build 18E226)) \ No newline at end of file +MacOutlook/16.41.20091302 (Intelx64 Mac OS X 10.14.4 (Build 18E226)) +HubSpot-Link-Resolver +Railgun/5.3.3 +RSSMix/3.0 +SearchWP +Stripe/1.0 (+https://stripe.com/docs/webhooks) +ZoominfoBot (zoominfobot at zoominfo dot com) +Asana/1.4.0 WebsiteMetadataRetriever +mattermost-5.19.0 +WP Rocket/Homepage Preload From 2300c6516ce8c541d06687383eb4920ad18d399c Mon Sep 17 00:00:00 2001 From: Joachim Nickel Date: Thu, 22 Oct 2020 17:23:39 +0200 Subject: [PATCH 3/4] Crawler Detection String updated --- src/Fixtures/Crawlers.php | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/Fixtures/Crawlers.php b/src/Fixtures/Crawlers.php index 5105dc7..ed73039 100644 --- a/src/Fixtures/Crawlers.php +++ b/src/Fixtures/Crawlers.php @@ -124,7 +124,7 @@ class Crawlers extends AbstractProvider 'aria2', 'Arukereso', 'asafaweb', - 'Asana/', + 'Asana\/', 'AskQuickly', 'Ask Jeeves', 'ASPSeek', From 847edd09d9acdd9d85ed40a37adfaed772f044f4 Mon Sep 17 00:00:00 2001 From: Joachim Nickel Date: Thu, 22 Oct 2020 20:49:44 +0200 Subject: [PATCH 4/4] Remove ZoominfoBot --- src/Fixtures/Crawlers.php | 1 - 1 file changed, 1 deletion(-) diff --git a/src/Fixtures/Crawlers.php b/src/Fixtures/Crawlers.php index ed73039..f067037 100644 --- a/src/Fixtures/Crawlers.php +++ b/src/Fixtures/Crawlers.php @@ -1350,7 +1350,6 @@ class Crawlers extends AbstractProvider 'ZnajdzFoto', 'ZnHTTP', 'Zombie\.js', - 'ZoominfoBot', 'Zoom\.Mac', 'ZoteroTranslationServer', 'ZyBorg',