From fea1c6b5529b9a4ca708ef828814932c5271a612 Mon Sep 17 00:00:00 2001 From: fen0s <37670363+fen0s@users.noreply.github.com> Date: Tue, 8 Nov 2022 09:47:21 +0300 Subject: [PATCH] disable not working sites (#739) * Update data.json * Update sites.md Co-authored-by: Soxoj <31013580+soxoj@users.noreply.github.com> --- maigret/resources/data.json | 9 ++++++++- sites.md | 24 ++++++++++++------------ 2 files changed, 20 insertions(+), 13 deletions(-) diff --git a/maigret/resources/data.json b/maigret/resources/data.json index 9db21ce..afc86cc 100644 --- a/maigret/resources/data.json +++ b/maigret/resources/data.json @@ -1458,6 +1458,7 @@ "usernameUnclaimed": "noonewouldeverusethis7" }, "Askvoprosy": { + "disabled": true, "tags": [ "coding" ], @@ -4275,6 +4276,7 @@ "usernameUnclaimed": "noonewouldeverusethis7" }, "Dota2": { + "disabled": true, "tags": [ "gaming", "ru" @@ -4282,7 +4284,8 @@ "checkType": "message", "absenceStrs": [ "\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u044b \u043e\u0442\u0441\u0443\u0442\u0441\u0442\u0432\u0443\u044e\u0442", - "\u041f\u043e\u0438\u0441\u043a \u0432\u0440\u0435\u043c\u0435\u043d\u043d\u043e \u043e\u0442\u043a\u043b\u044e\u0447\u0435\u043d" + "\u041f\u043e\u0438\u0441\u043a \u0432\u0440\u0435\u043c\u0435\u043d\u043d\u043e \u043e\u0442\u043a\u043b\u044e\u0447\u0435\u043d", + "

Поиск временно отключен

" ], "alexaRank": 54365, "urlMain": "https://dota2.ru/", @@ -29651,6 +29654,7 @@ "alexaRank": 4645861 }, "Yelp": { + "disabled": true, "absenceStrs": [ "viewName", " dropdown_user-name" @@ -31399,6 +31403,7 @@ ] }, "coder.social": { + "disabled": true, "absenceStrs": [ "Coder Social Home" ], @@ -32060,6 +32065,7 @@ "url": "https://forum.cfx.re/u/{username}" }, "forum.cockroachlabs.com": { + "disabled": true, "checkType": "status_code", "usernameClaimed": "adam", "usernameUnclaimed": "noonewouldeverusethis7", @@ -33766,6 +33772,7 @@ ] }, "stripchat.global": { + "disabled": true, "presenseStrs": [ "profile email", "setVersionName", diff --git a/sites.md b/sites.md index 2b5ddeb..dbbb4ce 100644 --- a/sites.md +++ b/sites.md @@ -109,7 +109,7 @@ Rank data fetched from Alexa by domains. 1. ![](https://www.google.com/s2/favicons?domain=https://opensea.io) [opensea.io (https://opensea.io)](https://opensea.io)*: top 500, us* 1. ![](https://www.google.com/s2/favicons?domain=https://www.dailymotion.com/) [DailyMotion (https://www.dailymotion.com/)](https://www.dailymotion.com/)*: top 500, us, video* 1. ![](https://www.google.com/s2/favicons?domain=https://www.behance.net/) [Behance (https://www.behance.net/)](https://www.behance.net/)*: top 500, business* -1. ![](https://www.google.com/s2/favicons?domain=http://www.yelp.com) [Yelp (http://www.yelp.com)](http://www.yelp.com)*: top 500, review* +1. ![](https://www.google.com/s2/favicons?domain=http://www.yelp.com) [Yelp (http://www.yelp.com)](http://www.yelp.com)*: top 500, review*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=https://www.yelp.com) [Yelp (by id) (https://www.yelp.com)](https://www.yelp.com)*: top 500, review* 1. ![](https://www.google.com/s2/favicons?domain=https://www.blogger.com/) [Blogger (https://www.blogger.com/)](https://www.blogger.com/)*: top 500, blog* 1. ![](https://www.google.com/s2/favicons?domain=https://www.patreon.com/) [Patreon (https://www.patreon.com/)](https://www.patreon.com/)*: top 500, finance* @@ -780,7 +780,7 @@ Rank data fetched from Alexa by domains. 1. ![](https://www.google.com/s2/favicons?domain=https://proglib.io) [Proglib (https://proglib.io)](https://proglib.io)*: top 100K, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://www.7cups.com/) [7Cups (https://www.7cups.com/)](https://www.7cups.com/)*: top 100K, medicine* 1. ![](https://www.google.com/s2/favicons?domain=https://www.bookcrossing.com/) [Bookcrossing (https://www.bookcrossing.com/)](https://www.bookcrossing.com/)*: top 100K, in* -1. ![](https://www.google.com/s2/favicons?domain=https://dota2.ru/) [Dota2 (https://dota2.ru/)](https://dota2.ru/)*: top 100K, gaming, ru* +1. ![](https://www.google.com/s2/favicons?domain=https://dota2.ru/) [Dota2 (https://dota2.ru/)](https://dota2.ru/)*: top 100K, gaming, ru*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=https://fancy.com) [fancy.com (https://fancy.com)](https://fancy.com)*: top 100K, shopping* 1. ![](https://www.google.com/s2/favicons?domain=https://goodgame.ru) [goodgame.ru (https://goodgame.ru)](https://goodgame.ru)*: top 100K, ru, streaming* 1. ![](https://www.google.com/s2/favicons?domain=https://forum.questionablequesting.com) [QuestionableQuesting (https://forum.questionablequesting.com)](https://forum.questionablequesting.com)*: top 100K, forum, gb, jp, us*, search is disabled @@ -952,7 +952,7 @@ Rank data fetched from Alexa by domains. 1. ![](https://www.google.com/s2/favicons?domain=https://www.stratege.ru) [Stratege (https://www.stratege.ru)](https://www.stratege.ru)*: top 10M, forum, gaming, news, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://boominfo.org) [boominfo.org (https://boominfo.org)](https://boominfo.org)*: top 10M, forum, us* 1. ![](https://www.google.com/s2/favicons?domain=http://collegy.ucoz.ru) [collegy.ucoz.ru (http://collegy.ucoz.ru)](http://collegy.ucoz.ru)*: top 10M, kz* -1. ![](https://www.google.com/s2/favicons?domain=https://stripchat.global) [stripchat.global (https://stripchat.global)](https://stripchat.global)*: top 10M, webcam* +1. ![](https://www.google.com/s2/favicons?domain=https://stripchat.global) [stripchat.global (https://stripchat.global)](https://stripchat.global)*: top 10M, webcam*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=https://www.quibblo.com/) [Quibblo (https://www.quibblo.com/)](https://www.quibblo.com/)*: top 10M, in*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=http://forums.riftgame.com) [Riftgame (http://forums.riftgame.com)](http://forums.riftgame.com)*: top 10M, cr, forum, us* 1. ![](https://www.google.com/s2/favicons?domain=https://forumodua.com) [ForumOdUa (https://forumodua.com)](https://forumodua.com)*: top 10M, forum, ro, ua*, search is disabled @@ -1391,7 +1391,7 @@ Rank data fetched from Alexa by domains. 1. ![](https://www.google.com/s2/favicons?domain=https://gg-izi.ru/) [GGIZI (https://gg-izi.ru/)](https://gg-izi.ru/)*: top 10M, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://www.thefirearmsforum.com) [Thefirearmsforum (https://www.thefirearmsforum.com)](https://www.thefirearmsforum.com)*: top 10M, forum, us* 1. ![](https://www.google.com/s2/favicons?domain=https://forums.animeuknews.net/) [AnimeUKNews (https://forums.animeuknews.net/)](https://forums.animeuknews.net/)*: top 10M, forum, pk* -1. ![](https://www.google.com/s2/favicons?domain=https://askvoprosy.com/) [Askvoprosy (https://askvoprosy.com/)](https://askvoprosy.com/)*: top 10M, coding* +1. ![](https://www.google.com/s2/favicons?domain=https://askvoprosy.com/) [Askvoprosy (https://askvoprosy.com/)](https://askvoprosy.com/)*: top 10M, coding*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=https://www.movie-list.com) [Movie-list (https://www.movie-list.com)](https://www.movie-list.com)*: top 10M, ca, forum, in, pk* 1. ![](https://www.google.com/s2/favicons?domain=https://s-forum.biz) [S-forum (https://s-forum.biz)](https://s-forum.biz)*: top 10M, forum* 1. ![](https://www.google.com/s2/favicons?domain=http://crown6.org) [crown6.org (http://crown6.org)](http://crown6.org)*: top 10M* @@ -1677,7 +1677,7 @@ Rank data fetched from Alexa by domains. 1. ![](https://www.google.com/s2/favicons?domain=http://markweinguitarlessons.com/forums/) [markweinguitarlessons.com (http://markweinguitarlessons.com/forums/)](http://markweinguitarlessons.com/forums/)*: top 10M, forum, hobby* 1. ![](https://www.google.com/s2/favicons?domain=https://bgforum.ru) [Bgforum (https://bgforum.ru)](https://bgforum.ru)*: top 10M, forum, ru* 1. ![](https://www.google.com/s2/favicons?domain=http://samp-sektor.ru) [samp-sektor.ru (http://samp-sektor.ru)](http://samp-sektor.ru)*: top 10M* -1. ![](https://www.google.com/s2/favicons?domain=https://coder.social) [coder.social (https://coder.social)](https://coder.social)*: top 10M, coding* +1. ![](https://www.google.com/s2/favicons?domain=https://coder.social) [coder.social (https://coder.social)](https://coder.social)*: top 10M, coding*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=https://kuban.forum24.ru/) [KubanForum24 (https://kuban.forum24.ru/)](https://kuban.forum24.ru/)*: top 10M, forum, ru* 1. ![](https://www.google.com/s2/favicons?domain=http://www.chevrolet-cruze-club.ru) [Chevrolet-cruze-club (http://www.chevrolet-cruze-club.ru)](http://www.chevrolet-cruze-club.ru)*: top 10M, ru*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=http://mix-best.ucoz.ru) [mix-best.ucoz.ru (http://mix-best.ucoz.ru)](http://mix-best.ucoz.ru)*: top 10M, ru* @@ -2949,7 +2949,7 @@ Rank data fetched from Alexa by domains. 1. ![](https://www.google.com/s2/favicons?domain=) [forum.banana-pi.org ()]()*: top 100M* 1. ![](https://www.google.com/s2/favicons?domain=) [forum.bonsaimirai.com ()]()*: top 100M* 1. ![](https://www.google.com/s2/favicons?domain=) [forum.cfx.re ()]()*: top 100M* -1. ![](https://www.google.com/s2/favicons?domain=) [forum.cockroachlabs.com ()]()*: top 100M* +1. ![](https://www.google.com/s2/favicons?domain=) [forum.cockroachlabs.com ()]()*: top 100M*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=) [forum.core-electronics.com.au ()]()*: top 100M* 1. ![](https://www.google.com/s2/favicons?domain=) [forum.freecodecamp.org ()]()*: top 100M* 1. ![](https://www.google.com/s2/favicons?domain=) [forum.gitlab.com ()]()*: top 100M* @@ -3072,16 +3072,16 @@ Rank data fetched from Alexa by domains. 1. ![](https://www.google.com/s2/favicons?domain=https://huggingface.co/) [HuggingFace (https://huggingface.co/)](https://huggingface.co/)*: top 100M* 1. ![](https://www.google.com/s2/favicons?domain=https://manifold.markets/) [ManifoldMarkets (https://manifold.markets/)](https://manifold.markets/)*: top 100M* -The list was updated at (2022-10-16 22:15:02.996690 UTC) +The list was updated at (2022-11-07 17:56:44.287608 UTC) ## Statistics -Enabled/total sites: 2829/3068 = 92.21% +Enabled/total sites: 2822/3067 = 92.01% -Incomplete message checks: 473/2829 = 16.72% (false positive risks) +Incomplete message checks: 472/2822 = 16.73% (false positive risks) -Status code checks: 722/2829 = 25.52% (false positive risks) +Status code checks: 722/2822 = 25.58% (false positive risks) -False positive risk (total): 42.24% +False positive risk (total): 42.31% Top 20 profile URLs: - (796) `{urlMain}/index/8-0-{username} (uCoz)` @@ -3109,8 +3109,8 @@ Top 20 tags: - (301) `NO_TAGS` (non-standard) - (275) `forum` - (47) `gaming` +- (24) `coding` - (23) `photo` -- (23) `coding` - (20) `news` - (19) `blog` - (16) `music`