From 2aa1ea39a03627ccf938d88d9e49c5d0da17893c Mon Sep 17 00:00:00 2001 From: Soxoj <31013580+soxoj@users.noreply.github.com> Date: Fri, 6 Dec 2024 14:27:38 +0100 Subject: [PATCH] Site fixes (#1940) --- maigret/resources/data.json | 19 +++++++++---------- sites.md | 16 ++++++++-------- 2 files changed, 17 insertions(+), 18 deletions(-) diff --git a/maigret/resources/data.json b/maigret/resources/data.json index 79513ee..7e0c92e 100644 --- a/maigret/resources/data.json +++ b/maigret/resources/data.json @@ -5350,11 +5350,7 @@ "tags": [ "wiki" ], - "checkType": "message", - "absenceStrs": [ - "does not exist", - "This user has not filled out their profile page yet." - ], + "checkType": "status_code", "alexaRank": 80, "urlMain": "https://community.fandom.com", "url": "https://community.fandom.com/wiki/User:{username}", @@ -9323,7 +9319,7 @@ "alexaRank": 67, "urlMain": "https://www.livejasmin.com/", "url": "https://www.livejasmin.com/en/girls/#!chat/{username}", - "usernameClaimed": "test", + "usernameClaimed": "Dolce", "usernameUnclaimed": "noonewouldeverusethis7" }, "Livemaster": { @@ -10017,7 +10013,8 @@ "urlMain": "https://medium.com/", "url": "https://medium.com/@{username}", "usernameClaimed": "blue", - "usernameUnclaimed": "noonewouldeverusethis7" + "usernameUnclaimed": "noonewouldeverusethis7", + "disabled": true }, "Medyczka.pl": { "checkType": "message", @@ -16505,10 +16502,10 @@ ], "checkType": "message", "presenseStrs": [ - "tv-profile__name-text" + "tv-profile" ], "absenceStrs": [ - "Sorry, that page doesn't exist!" + "Page not found \u2014 TradingView" ], "alexaRank": 61, "urlMain": "https://www.tradingview.com/", @@ -16857,7 +16854,8 @@ "urlMain": "https://nitter.net/", "url": "{urlMain}{username}", "usernameClaimed": "blue", - "usernameUnclaimed": "noonewould123" + "usernameUnclaimed": "noonewould123", + "disabled": true }, "Twitter": { "tags": [ @@ -18544,6 +18542,7 @@ "music", "ru" ], + "ignore403": true, "headers": { "Referer": "https://music.yandex.ru/users/test/playlists" }, diff --git a/sites.md b/sites.md index f0f0594..2c7cec4 100644 --- a/sites.md +++ b/sites.md @@ -19,7 +19,7 @@ Rank data fetched from Alexa by domains. 1. ![](https://www.google.com/s2/favicons?domain=https://gist.github.com) [GitHubGist (https://gist.github.com)](https://gist.github.com)*: top 50, coding, sharing* 1. ![](https://www.google.com/s2/favicons?domain=https://vk.com/) [VK (https://vk.com/)](https://vk.com/)*: top 50, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://vk.com/) [VK (by id) (https://vk.com/)](https://vk.com/)*: top 50, ru* -1. ![](https://www.google.com/s2/favicons?domain=https://pt.bongacams.com) [BongaCams (https://pt.bongacams.com)](https://pt.bongacams.com)*: top 50, cz, webcam* +1. ![](https://www.google.com/s2/favicons?domain=https://sbongacams.com) [BongaCams (https://sbongacams.com)](https://sbongacams.com)*: top 50, cz, webcam* 1. ![](https://www.google.com/s2/favicons?domain=https://www.instagram.com/) [Instagram (https://www.instagram.com/)](https://www.instagram.com/)*: top 50, photo*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=https://www.twitch.tv/) [Twitch (https://www.twitch.tv/)](https://www.twitch.tv/)*: top 50, streaming, us* 1. ![](https://www.google.com/s2/favicons?domain=https://yandex.ru/collections/) [YandexCollections API (https://yandex.ru/collections/)](https://yandex.ru/collections/)*: top 50, ru, sharing*, search is disabled @@ -28,7 +28,7 @@ Rank data fetched from Alexa by domains. 1. ![](https://www.google.com/s2/favicons?domain=https://naver.com) [Naver (https://naver.com)](https://naver.com)*: top 50, kr* 1. ![](https://www.google.com/s2/favicons?domain=https://developer.apple.com/forums) [AppleDeveloper (https://developer.apple.com/forums)](https://developer.apple.com/forums)*: top 50, forum, us* 1. ![](https://www.google.com/s2/favicons?domain=https://discussions.apple.com/) [AppleDiscussions (https://discussions.apple.com/)](https://discussions.apple.com/)*: top 50, us* -1. ![](https://www.google.com/s2/favicons?domain=https://nitter.net/) [Nitter (https://nitter.net/)](https://nitter.net/)*: top 50, messaging* +1. ![](https://www.google.com/s2/favicons?domain=https://nitter.net/) [Nitter (https://nitter.net/)](https://nitter.net/)*: top 50, messaging*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=https://www.twitter.com/) [Twitter (https://www.twitter.com/)](https://www.twitter.com/)*: top 50, messaging* 1. ![](https://www.google.com/s2/favicons?domain=https://allods.mail.ru) [Allods (https://allods.mail.ru)](https://allods.mail.ru)*: top 50, forum, gaming, ru*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=https://aa.mail.ru) [ArcheAge (https://aa.mail.ru)](https://aa.mail.ru)*: top 50, forum, gaming, ru*, search is disabled @@ -63,7 +63,7 @@ Rank data fetched from Alexa by domains. 1. ![](https://www.google.com/s2/favicons?domain=https://www.tradingview.com/) [TradingView (https://www.tradingview.com/)](https://www.tradingview.com/)*: top 100, trading, us* 1. ![](https://www.google.com/s2/favicons?domain=https://www.aparat.com) [Aparat (https://www.aparat.com)](https://www.aparat.com)*: top 100, ir, video* 1. ![](https://www.google.com/s2/favicons?domain=https://chaturbate.com) [ChaturBate (https://chaturbate.com)](https://chaturbate.com)*: top 100, us* -1. ![](https://www.google.com/s2/favicons?domain=https://medium.com/) [Medium (https://medium.com/)](https://medium.com/)*: top 100, blog, us* +1. ![](https://www.google.com/s2/favicons?domain=https://medium.com/) [Medium (https://medium.com/)](https://medium.com/)*: top 100, blog, us*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=https://www.livejasmin.com/) [Livejasmin (https://www.livejasmin.com/)](https://www.livejasmin.com/)*: top 100, us, webcam* 1. ![](https://www.google.com/s2/favicons?domain=https://pornhub.com/) [Pornhub (https://pornhub.com/)](https://pornhub.com/)*: top 100, porn* 1. ![](https://www.google.com/s2/favicons?domain=https://imgur.com) [Imgur (https://imgur.com)](https://imgur.com)*: top 100, photo* @@ -3133,13 +3133,13 @@ Rank data fetched from Alexa by domains. The list was updated at (2024-12-06) ## Statistics -Enabled/total sites: 2691/3126 = 86.08% +Enabled/total sites: 2689/3126 = 86.02% -Incomplete message checks: 405/2691 = 15.05% (false positive risks) +Incomplete message checks: 404/2689 = 15.02% (false positive risks) -Status code checks: 719/2691 = 26.72% (false positive risks) +Status code checks: 720/2689 = 26.78% (false positive risks) -False positive risk (total): 41.77% +False positive risk (total): 41.80% Top 20 profile URLs: - (796) `{urlMain}/index/8-0-{username} (uCoz)` @@ -3169,7 +3169,7 @@ Top 20 tags: - (50) `gaming` - (26) `coding` - (21) `photo` -- (20) `blog` +- (21) `blog` - (19) `news` - (15) `music` - (14) `tech`