mirror/maigret
1
0
Fork 0
mirror of https://github.com/soxoj/maigret.git synced 2026-05-07 06:24:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

tried to fix merge conflicts

Browse Source
This commit is contained in:
kustermariocoding
2022-02-28 11:41:38 +01:00
parent ea6fd30a30 364187861d
commit 54c8074e51
9 changed files with 229 additions and 121 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/python-package.yml
+1 -1
View File
@@ -2,9 +2,9 @@ name: Linting and testing
on: on:
push: push:
branches: [ main ]
pull_request: pull_request:
branches: [ main ] branches: [ main ]
types: [opened, synchronize, reopened]
jobs: jobs:
build: build:
.github/workflows/update-site-data.yml
+21 -5
View File
@@ -1,18 +1,34 @@
name: Update sites rating name: Update sites rating and statistics
on: on:
push:
branches: [ main ]
pull_request: pull_request:
branches: [ main ] branches: [ main ]
types: [opened, synchronize]
jobs: jobs:
build: build:
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
- name: checkout repo - name: Checkout repository
uses: actions/checkout@v2 uses: actions/checkout@v2.3.2
with:
ref: ${{ github.event.pull_request.head.sha }}
fetch-depth: 0 # otherwise, there would be errors pushing refs to the destination repository.
- name: build application - name: build application
run: | run: |
pip3 install . pip3 install .
python3 ./utils/update_site_data.py --empty-only python3 ./utils/update_site_data.py --empty-only
- name: Commit and push changes
run: |
git config --global user.name "Maigret autoupdate"
git config --global user.email "soxoj@protonmail.com"
echo `git name-rev ${{ github.event.pull_request.head.sha }} --name-only`
export BRANCH=`git name-rev ${{ github.event.pull_request.head.sha }} --name-only | sed 's/remotes\/origin\///'`
echo $BRANCH
git remote -v
git checkout $BRANCH
git add sites.md
git commit -m "Updated site list and statistics"
git push origin $BRANCH
docs/source/development.rst
+31
View File
@@ -3,6 +3,37 @@
Development Development
============== ==============
Testing
-------
It is recommended use Python 3.7/3.8 for test due to some conflicts in 3.9.
Install test requirements:
.. code-block:: console
pip install -r test-requirements.txt
Use the following commands to check Maigret:
.. code-block:: console
# run linter and typing checks
# order of checks%
# - critical syntax errors or undefined names
# - flake checks
# - mypy checks
make lint
# run testing with coverage html report
# current test coverage is 60%
make text
# open html report
open htmlcov/index.html
How to publish new version of Maigret How to publish new version of Maigret
------------------------------------- -------------------------------------
maigret/checking.py
+1 -1
View File
@@ -132,7 +132,7 @@ class SimpleAiohttpChecker(CheckerBase):
error = CheckError("Unexpected", str(e)) error = CheckError("Unexpected", str(e))
if error == "Invalid proxy response": if error == "Invalid proxy response":
self.logger.debug(e, exc_info=True) self.logger.debug(error, exc_info=True)
return str(html_text), status_code, error return str(html_text), status_code, error
maigret/maigret.py
+1 -1
View File
@@ -48,7 +48,7 @@ def notify_about_errors(search_results: QueryResultWrapper, query_notify):
for e in errs: for e in errs:
if not errors.is_important(e): if not errors.is_important(e):
continue continue
text = f'Too many errors of type "{e["err"]}" ({e["perc"]}%)' text = f'Too many errors of type "{e["err"]}" ({round(e["perc"],2)}%)'
solution = errors.solution_of(e['err']) solution = errors.solution_of(e['err'])
if solution: if solution:
text = '. '.join([text, solution.capitalize()]) text = '. '.join([text, solution.capitalize()])
maigret/resources/data.json
+103 -94
View File
@@ -1507,6 +1507,7 @@
"forum", "forum",
"ru" "ru"
], ],
"disabled": true,
"checkType": "message", "checkType": "message",
"absenceStrs": [ "absenceStrs": [
"\u041f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u044c \u043d\u0435 \u043d\u0430\u0439\u0434\u0435\u043d" "\u041f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u044c \u043d\u0435 \u043d\u0430\u0439\u0434\u0435\u043d"
@@ -1947,6 +1948,7 @@
"pk", "pk",
"us" "us"
], ],
"disabled": true,
"checkType": "status_code", "checkType": "status_code",
"alexaRank": 522588, "alexaRank": 522588,
"urlMain": "https://bethepro.com", "urlMain": "https://bethepro.com",
@@ -1961,7 +1963,7 @@
], ],
"checkType": "message", "checkType": "message",
"absenceStrs": [ "absenceStrs": [
"\u041f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u044f \u0441 \u0442\u0430\u043a\u0438\u043c \u0438\u043c\u0435\u043d\u0435\u043c \u043d\u0435 \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0443\u0435\u0442!" "\u041e\u0448\u0438\u0431\u043a\u0430 / \u041f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u044f \u0441 \u0442\u0430\u043a\u0438\u043c \u0438\u043c\u0435\u043d\u0435\u043c \u043d\u0435 \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0443\u0435\u0442"
], ],
"alexaRank": 2303903, "alexaRank": 2303903,
"urlMain": "https://bgforum.ru", "urlMain": "https://bgforum.ru",
@@ -3823,6 +3825,7 @@
"tags": [ "tags": [
"ru" "ru"
], ],
"disabled": true,
"checkType": "status_code", "checkType": "status_code",
"urlMain": "https://dinsk.su", "urlMain": "https://dinsk.su",
"url": "https://dinsk.su/user/{username}", "url": "https://dinsk.su/user/{username}",
@@ -4922,6 +4925,7 @@
"tags": [ "tags": [
"ru" "ru"
], ],
"disabled": true,
"checkType": "status_code", "checkType": "status_code",
"alexaRank": 1225740, "alexaRank": 1225740,
"urlMain": "https://favera.ru", "urlMain": "https://favera.ru",
@@ -5554,11 +5558,14 @@
], ],
"checkType": "message", "checkType": "message",
"presenceStrs": [ "presenceStrs": [
"userStatsTitle" "<meta content=\"name=Profile"
],
"absenceStrs": [
"<title>Foursquare "
], ],
"alexaRank": 3413, "alexaRank": 3413,
"urlMain": "https://ru.foursquare.com/", "urlMain": "https://foursquare.com/",
"url": "https://ru.foursquare.com/{username}", "url": "https://foursquare.com/{username}",
"usernameClaimed": "adam", "usernameClaimed": "adam",
"usernameUnclaimed": "noonewouldeverusethis7" "usernameUnclaimed": "noonewouldeverusethis7"
}, },
@@ -6685,7 +6692,10 @@
], ],
"checkType": "message", "checkType": "message",
"absenceStrs": [ "absenceStrs": [
"Page not found." "Page not found"
],
"presenseStrs": [
"title=\"Gumroad\""
], ],
"alexaRank": 4728, "alexaRank": 4728,
"urlMain": "https://www.gumroad.com/", "urlMain": "https://www.gumroad.com/",
@@ -8255,6 +8265,7 @@
"tags": [ "tags": [
"coding" "coding"
], ],
"disabled": true,
"checkType": "status_code", "checkType": "status_code",
"alexaRank": 1859, "alexaRank": 1859,
"urlMain": "https://leetcode.com/", "urlMain": "https://leetcode.com/",
@@ -9034,6 +9045,7 @@
"tags": [ "tags": [
"forum" "forum"
], ],
"disabled": true,
"checkType": "message", "checkType": "message",
"absenceStrs": [ "absenceStrs": [
"The specified member cannot be found" "The specified member cannot be found"
@@ -9351,7 +9363,10 @@
], ],
"checkType": "message", "checkType": "message",
"absenceStrs": [ "absenceStrs": [
"\u0417\u0434\u0435\u0441\u044c \u043f\u043e\u043a\u0430 \u043d\u0438\u0447\u0435\u0433\u043e \u043d\u0435\u0442" "\u041f\u043e \u0412\u0430\u0448\u0435\u043c\u0443 \u0437\u0430\u043f\u0440\u043e\u0441\u0443 \u043d\u0438\u0447\u0435\u0433\u043e \u043d\u0435 \u043d\u0430\u0439\u0434\u0435\u043d\u043e"
],
"presenseStrs": [
"<span>\u041b\u044e\u0434\u0438</span>"
], ],
"alexaRank": 6409, "alexaRank": 6409,
"urlMain": "https://mirtesen.ru", "urlMain": "https://mirtesen.ru",
@@ -9567,12 +9582,9 @@
}, },
"Movescount": { "Movescount": {
"tags": [ "tags": [
"es", "maps"
"in",
"pk",
"ru",
"us"
], ],
"disabled": true,
"checkType": "message", "checkType": "message",
"absenceStrs": [ "absenceStrs": [
"error=4&amp;" "error=4&amp;"
@@ -10206,12 +10218,15 @@
}, },
"Netvibes": { "Netvibes": {
"tags": [ "tags": [
"de", "business",
"fr", "fr"
"jp"
], ],
"disabled": true,
"checkType": "status_code", "checkType": "status_code",
"alexaRank": 5730, "alexaRank": 5730,
"headers": {
"User-Agent": "curl/7.64.1"
},
"urlMain": "https://www.netvibes.com", "urlMain": "https://www.netvibes.com",
"url": "https://www.netvibes.com/{username}#General", "url": "https://www.netvibes.com/{username}#General",
"usernameClaimed": "blue", "usernameClaimed": "blue",
@@ -10657,10 +10672,7 @@
"tags": [ "tags": [
"ru" "ru"
], ],
"checkType": "message", "checkType": "status_code",
"absenceStrs": [
"404 - Not Found"
],
"alexaRank": 25200, "alexaRank": 25200,
"urlMain": "https://overclockers.ru", "urlMain": "https://overclockers.ru",
"url": "https://overclockers.ru/cpubase/user/{username}", "url": "https://overclockers.ru/cpubase/user/{username}",
@@ -11205,7 +11217,11 @@
"checkType": "message", "checkType": "message",
"absenceStrs": [ "absenceStrs": [
"Hmm, it seems that you've come across an invalid username", "Hmm, it seems that you've come across an invalid username",
"404 Not Found" "404 Not Found",
"Member Not Found"
],
"presenseStrs": [
"profile on Planet Minecraft to see their public Minecraft community activity"
], ],
"alexaRank": 9050, "alexaRank": 9050,
"urlMain": "https://www.planetminecraft.com", "urlMain": "https://www.planetminecraft.com",
@@ -13342,7 +13358,13 @@
"tags": [ "tags": [
"music" "music"
], ],
"checkType": "status_code", "checkType": "message",
"presenseStrs": [
"Profile: "
],
"absenceStrs": [
"Smule | Page Not Found (404)"
],
"alexaRank": 11742, "alexaRank": 11742,
"urlMain": "https://www.smule.com/", "urlMain": "https://www.smule.com/",
"url": "https://www.smule.com/{username}", "url": "https://www.smule.com/{username}",
@@ -13366,16 +13388,19 @@
}, },
"Snooth": { "Snooth": {
"tags": [ "tags": [
"in" "news"
], ],
"checkType": "message", "checkType": "message",
"absenceStrs": [ "absenceStrs": [
"<title>Profiles on Snooth</title>" "<title>Page not found"
],
"presenseStrs": [
"content=\"https://www.snooth.com/author/"
], ],
"alexaRank": 4088489, "alexaRank": 4088489,
"urlMain": "https://www.snooth.com/", "urlMain": "https://www.snooth.com/",
"url": "https://www.snooth.com/profiles/{username}/", "url": "https://www.snooth.com/author/{username}/",
"usernameClaimed": "GregT", "usernameClaimed": "joshua",
"usernameUnclaimed": "noonewouldeverusethis7" "usernameUnclaimed": "noonewouldeverusethis7"
}, },
"SocialLibremOne": { "SocialLibremOne": {
@@ -13608,7 +13633,7 @@
"us" "us"
], ],
"headers": { "headers": {
"authorization": "Bearer BQBLyPSs0y1FzkCHjMKD70dV9w93fNraURmQAzR9xTuDyzbQWBAVnGecE1lELz54ZjRnJI8jEMlZ4tuhC8s" "authorization": "Bearer BQBFTijjpshGAhX7n9-sO46wb8zJIkhu6TT3Ss7b-0V1dw_jXZhcff1agUpqRgbhznOG8pSIRlHtJAtd2TU"
}, },
"errors": { "errors": {
"Spotify is currently not available in your country.": "Access denied in your country, use proxy/vpn" "Spotify is currently not available in your country.": "Access denied in your country, use proxy/vpn"
@@ -15464,7 +15489,7 @@
"video" "video"
], ],
"headers": { "headers": {
"Authorization": "jwt eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJleHAiOjE2NDQzOTg0MDAsInVzZXJfaWQiOm51bGwsImFwcF9pZCI6NTg0NzksInNjb3BlcyI6InB1YmxpYyIsInRlYW1fdXNlcl9pZCI6bnVsbH0.RbupVlEMlatBOdlII3XdUAQkjuCRa1BAI_7ssJx9B3o" "Authorization": "jwt eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJleHAiOjE2NDU4Nzk3NDAsInVzZXJfaWQiOm51bGwsImFwcF9pZCI6NTg0NzksInNjb3BlcyI6InB1YmxpYyIsInRlYW1fdXNlcl9pZCI6bnVsbH0.T8E8Vrx0sO-9WP4RdZGNQZw2EB1hYTIXbIguXIZbfNQ"
}, },
"activation": { "activation": {
"url": "https://vimeo.com/_rv/viewer", "url": "https://vimeo.com/_rv/viewer",
@@ -16013,7 +16038,8 @@
], ],
"checkType": "message", "checkType": "message",
"absenceStrs": [ "absenceStrs": [
"is not registered" "is not registered",
"Wikipedia does not have a"
], ],
"alexaRank": 12, "alexaRank": 12,
"urlMain": "https://www.wikipedia.org/", "urlMain": "https://www.wikipedia.org/",
@@ -17069,12 +17095,7 @@
"br", "br",
"us" "us"
], ],
"checkType": "message", "engine": "op.gg",
"presenseStrs": "common.SummonerHistory.Favorite",
"absenceStrs": [
"SummonerNotFoundLayout"
],
"alexaRank": 331,
"urlMain": "https://br.op.gg/", "urlMain": "https://br.op.gg/",
"url": "https://br.op.gg/summoner/userName={username}", "url": "https://br.op.gg/summoner/userName={username}",
"usernameClaimed": "adam", "usernameClaimed": "adam",
@@ -17615,12 +17636,7 @@
"gaming", "gaming",
"us" "us"
], ],
"checkType": "message", "engine": "op.gg",
"presenseStrs": "common.SummonerHistory.Favorite",
"absenceStrs": [
"SummonerNotFoundLayout"
],
"alexaRank": 331,
"urlMain": "https://eune.op.gg/", "urlMain": "https://eune.op.gg/",
"url": "https://eune.op.gg/summoner/userName={username}", "url": "https://eune.op.gg/summoner/userName={username}",
"usernameClaimed": "adam", "usernameClaimed": "adam",
@@ -17631,12 +17647,7 @@
"gaming", "gaming",
"us" "us"
], ],
"checkType": "message", "engine": "op.gg",
"presenseStrs": "common.SummonerHistory.Favorite",
"absenceStrs": [
"SummonerNotFoundLayout"
],
"alexaRank": 331,
"urlMain": "https://euw.op.gg/", "urlMain": "https://euw.op.gg/",
"url": "https://euw.op.gg/summoner/userName={username}", "url": "https://euw.op.gg/summoner/userName={username}",
"usernameClaimed": "blue", "usernameClaimed": "blue",
@@ -18575,12 +18586,7 @@
"tags": [ "tags": [
"us" "us"
], ],
"checkType": "message", "engine": "op.gg",
"presenseStrs": "common.SummonerHistory.Favorite",
"absenceStrs": [
"SummonerNotFoundLayout"
],
"alexaRank": 331,
"urlMain": "https://lan.op.gg/", "urlMain": "https://lan.op.gg/",
"url": "https://lan.op.gg/summoner/userName={username}", "url": "https://lan.op.gg/summoner/userName={username}",
"usernameClaimed": "adam", "usernameClaimed": "adam",
@@ -18591,12 +18597,7 @@
"gaming", "gaming",
"us" "us"
], ],
"checkType": "message", "engine": "op.gg",
"presenseStrs": "common.SummonerHistory.Favorite",
"absenceStrs": [
"SummonerNotFoundLayout"
],
"alexaRank": 331,
"urlMain": "https://las.op.gg/", "urlMain": "https://las.op.gg/",
"url": "https://las.op.gg/summoner/userName={username}", "url": "https://las.op.gg/summoner/userName={username}",
"usernameClaimed": "adam", "usernameClaimed": "adam",
@@ -18641,6 +18642,7 @@
"tags": [ "tags": [
"ru" "ru"
], ],
"disabled": true,
"checkType": "status_code", "checkType": "status_code",
"alexaRank": 6054365, "alexaRank": 6054365,
"urlMain": "http://linuxmint.info", "urlMain": "http://linuxmint.info",
@@ -18980,12 +18982,7 @@
"tags": [ "tags": [
"gaming" "gaming"
], ],
"checkType": "message", "engine": "op.gg",
"presenseStrs": "common.SummonerHistory.Favorite",
"absenceStrs": [
"SummonerNotFoundLayout"
],
"alexaRank": 331,
"urlMain": "https://na.op.gg/", "urlMain": "https://na.op.gg/",
"url": "https://na.op.gg/summoner/userName={username}", "url": "https://na.op.gg/summoner/userName={username}",
"usernameClaimed": "adam", "usernameClaimed": "adam",
@@ -19165,12 +19162,7 @@
"gaming", "gaming",
"us" "us"
], ],
"checkType": "message", "engine": "op.gg",
"presenseStrs": "common.SummonerHistory.Favorite",
"absenceStrs": [
"SummonerNotFoundLayout"
],
"alexaRank": 331,
"urlMain": "https://oce.op.gg/", "urlMain": "https://oce.op.gg/",
"url": "https://oce.op.gg/summoner/userName={username}", "url": "https://oce.op.gg/summoner/userName={username}",
"usernameClaimed": "adam", "usernameClaimed": "adam",
@@ -19637,12 +19629,7 @@
"ru", "ru",
"us" "us"
], ],
"checkType": "message", "engine": "op.gg",
"presenseStrs": "common.SummonerHistory.Favorite",
"absenceStrs": [
"SummonerNotFoundLayout"
],
"alexaRank": 331,
"urlMain": "https://ru.op.gg/", "urlMain": "https://ru.op.gg/",
"url": "https://ru.op.gg/summoner/userName={username}", "url": "https://ru.op.gg/summoner/userName={username}",
"usernameClaimed": "adam", "usernameClaimed": "adam",
@@ -20189,12 +20176,7 @@
"tr", "tr",
"us" "us"
], ],
"checkType": "message", "engine": "op.gg",
"presenseStrs": "common.SummonerHistory.Favorite",
"absenceStrs": [
"SummonerNotFoundLayout"
],
"alexaRank": 331,
"urlMain": "https://tr.op.gg/", "urlMain": "https://tr.op.gg/",
"url": "https://tr.op.gg/summoner/userName={username}", "url": "https://tr.op.gg/summoner/userName={username}",
"usernameClaimed": "adam", "usernameClaimed": "adam",
@@ -25003,23 +24985,35 @@
}, },
"thoughts.com": { "thoughts.com": {
"tags": [ "tags": [
"in" "blog"
],
"checkType": "message",
"absenceStrs": [
"<title>Start a Blog"
],
"presenseStrs": [
"&#8211; Thoughts.com</title>"
], ],
"engine": "engine404get",
"urlMain": "http://thoughts.com", "urlMain": "http://thoughts.com",
"url": "http://thoughts.com/profile/{username}", "url": "http://thoughts.com/members/{username}",
"usernameUnclaimed": "noonewouldeverusethis7", "usernameUnclaimed": "noonewouldeverusethis7",
"usernameClaimed": "red" "usernameClaimed": "alicia12"
}, },
"hackernoon.com": { "hackernoon.com": {
"tags": [ "tags": [
"in", "us",
"us" "news"
],
"checkType": "message",
"absenceStrs": [
"<title>HackerNoon"
],
"presenseStrs": [
" | HackerNoon</title>"
], ],
"engine": "engine404message",
"urlMain": "https://hackernoon.com", "urlMain": "https://hackernoon.com",
"url": "https://hackernoon.com/u/{username}", "url": "https://hackernoon.com/u/{username}",
"usernameUnclaimed": "noonewouldeverusethis7", "usernameUnclaimed": "noonewouldeverusethis71",
"usernameClaimed": "god" "usernameClaimed": "god"
}, },
"Intigriti": { "Intigriti": {
@@ -25352,7 +25346,7 @@
"usernameClaimed": "alex", "usernameClaimed": "alex",
"usernameUnclaimed": "noonewouldeverusethis7" "usernameUnclaimed": "noonewouldeverusethis7"
}, },
"hashnode.com": { "hashnode": {
"tags": [ "tags": [
"in" "in"
], ],
@@ -25365,7 +25359,7 @@
" name=" " name="
], ],
"absenceStrs": [ "absenceStrs": [
"></title><meta name=" "We can\u2019t find the page you\u2019re looking for!"
], ],
"urlMain": "https://hashnode.com", "urlMain": "https://hashnode.com",
"url": "https://hashnode.com/@{username}", "url": "https://hashnode.com/@{username}",
@@ -27466,6 +27460,9 @@
}, },
"forum.rastrnet.ru": { "forum.rastrnet.ru": {
"urlMain": "http://forum.rastrnet.ru", "urlMain": "http://forum.rastrnet.ru",
"errors": {
"\u0418\u0437\u0432\u0438\u043d\u0438\u0442\u0435, \u043f\u0440\u043e\u0432\u043e\u0434\u044f\u0442\u0441\u044f \u0442\u0435\u0445\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u0440\u0430\u0431\u043e\u0442\u044b.": "Site error"
},
"engine": "vBulletin", "engine": "vBulletin",
"usernameClaimed": "alex", "usernameClaimed": "alex",
"usernameUnclaimed": "noonewouldeverusethis7", "usernameUnclaimed": "noonewouldeverusethis7",
@@ -28992,10 +28989,9 @@
}, },
"photoshop-kopona.com": { "photoshop-kopona.com": {
"absenceStrs": [ "absenceStrs": [
"<title>noonewouldeverusethis7 &raquo; \u0420\u0435\u0441\u0443\u0440\u0441\u044b \u0434\u043b\u044f \u0424\u043e\u0442\u043e\u0448\u043e\u043f\u0430</title>" "<div id='dle-content'></div></div></main></div></div><footer class=\"footer\">"
], ],
"presenseStrs": [ "presenseStrs": [
"offline",
"uspusertitle" "uspusertitle"
], ],
"url": "https://photoshop-kopona.com/ru/user/{username}/", "url": "https://photoshop-kopona.com/ru/user/{username}/",
@@ -29158,7 +29154,7 @@
}, },
"coder.social": { "coder.social": {
"absenceStrs": [ "absenceStrs": [
"Not Found in Githubhelp" "<title>Coder Social Home</title>"
], ],
"presenseStrs": [ "presenseStrs": [
"nofollow" "nofollow"
@@ -29549,6 +29545,19 @@
"404" "404"
] ]
} }
},
"op.gg": {
"name": "op.gg",
"site": {
"checkType": "message",
"presenseStrs": [
"<div class=\"profile-icon\">"
],
"absenceStrs": [
"<h2 class=\"header__title\">This summoner is not registered"
],
"alexaRank": 331
}
} }
}, },
"tags": [ "tags": [
maigret/sites.py
+6 -3
View File
@@ -438,7 +438,7 @@ class MaigretDatabase:
url_type = site.get_url_template() url_type = site.get_url_template()
urls[url_type] = urls.get(url_type, 0) + 1 urls[url_type] = urls.get(url_type, 0) + 1
if site.check_type == 'message': if site.check_type == 'message' and not site.disabled:
message_checks += 1 message_checks += 1
if site.absence_strs and site.presense_strs: if site.absence_strs and site.presense_strs:
continue continue
@@ -450,8 +450,11 @@ class MaigretDatabase:
for tag in filter(lambda x: not is_country_tag(x), site.tags): for tag in filter(lambda x: not is_country_tag(x), site.tags):
tags[tag] = tags.get(tag, 0) + 1 tags[tag] = tags.get(tag, 0) + 1
output += f"Enabled/total sites: {total_count - disabled_count}/{total_count}\n\n" enabled_perc = round(100*(total_count-disabled_count)/total_count, 2)
output += f"Incomplete checks: {message_checks_one_factor}/{message_checks} (false positive risks)\n\n" output += f"Enabled/total sites: {total_count - disabled_count}/{total_count} = {enabled_perc}%\n\n"
checks_perc = round(100*message_checks_one_factor/message_checks, 2)
output += f"Incomplete checks: {message_checks_one_factor}/{message_checks} = {checks_perc}% (false positive risks)\n\n"
top_urls_count = 20 top_urls_count = 20
output += f"Top {top_urls_count} profile URLs:\n" output += f"Top {top_urls_count} profile URLs:\n"
sites.md
+64 -15
View File
@@ -197,7 +197,7 @@ Rank data fetched from Alexa by domains.
1. ![](https://www.google.com/s2/favicons?domain=https://www.polygon.com/) [Polygon (https://www.polygon.com/)](https://www.polygon.com/)*: top 5K, us* 1. ![](https://www.google.com/s2/favicons?domain=https://www.polygon.com/) [Polygon (https://www.polygon.com/)](https://www.polygon.com/)*: top 5K, us*
1. ![](https://www.google.com/s2/favicons?domain=https://otzovik.com/) [Otzovik (https://otzovik.com/)](https://otzovik.com/)*: top 5K, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://otzovik.com/) [Otzovik (https://otzovik.com/)](https://otzovik.com/)*: top 5K, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://www.liveinternet.ru) [LiveInternet (https://www.liveinternet.ru)](https://www.liveinternet.ru)*: top 5K, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://www.liveinternet.ru) [LiveInternet (https://www.liveinternet.ru)](https://www.liveinternet.ru)*: top 5K, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://leetcode.com/) [LeetCode (https://leetcode.com/)](https://leetcode.com/)*: top 5K, coding* 1. ![](https://www.google.com/s2/favicons?domain=https://leetcode.com/) [LeetCode (https://leetcode.com/)](https://leetcode.com/)*: top 5K, coding*, search is disabled
1. ![](https://www.google.com/s2/favicons?domain=https://www.kaggle.com/) [Kaggle (https://www.kaggle.com/)](https://www.kaggle.com/)*: top 5K, tech* 1. ![](https://www.google.com/s2/favicons?domain=https://www.kaggle.com/) [Kaggle (https://www.kaggle.com/)](https://www.kaggle.com/)*: top 5K, tech*
1. ![](https://www.google.com/s2/favicons?domain=https://codepen.io/) [Codepen (https://codepen.io/)](https://codepen.io/)*: top 5K, coding, in* 1. ![](https://www.google.com/s2/favicons?domain=https://codepen.io/) [Codepen (https://codepen.io/)](https://codepen.io/)*: top 5K, coding, in*
1. ![](https://www.google.com/s2/favicons?domain=https://www.rajce.idnes.cz/) [Rajce.net (https://www.rajce.idnes.cz/)](https://www.rajce.idnes.cz/)*: top 5K, cz* 1. ![](https://www.google.com/s2/favicons?domain=https://www.rajce.idnes.cz/) [Rajce.net (https://www.rajce.idnes.cz/)](https://www.rajce.idnes.cz/)*: top 5K, cz*
@@ -249,7 +249,7 @@ Rank data fetched from Alexa by domains.
1. ![](https://www.google.com/s2/favicons?domain=https://forum.xda-developers.com) [XDA (https://forum.xda-developers.com)](https://forum.xda-developers.com)*: top 5K, apps, forum*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=https://forum.xda-developers.com) [XDA (https://forum.xda-developers.com)](https://forum.xda-developers.com)*: top 5K, apps, forum*, search is disabled
1. ![](https://www.google.com/s2/favicons?domain=https://i.thechive.com/) [Thechive (https://i.thechive.com/)](https://i.thechive.com/)*: top 5K, us* 1. ![](https://www.google.com/s2/favicons?domain=https://i.thechive.com/) [Thechive (https://i.thechive.com/)](https://i.thechive.com/)*: top 5K, us*
1. ![](https://www.google.com/s2/favicons?domain=https://999.md) [999.md (https://999.md)](https://999.md)*: top 5K, freelance, md, shopping* 1. ![](https://www.google.com/s2/favicons?domain=https://999.md) [999.md (https://999.md)](https://999.md)*: top 5K, freelance, md, shopping*
1. ![](https://www.google.com/s2/favicons?domain=https://ru.foursquare.com/) [Foursquare (https://ru.foursquare.com/)](https://ru.foursquare.com/)*: top 5K, geosocial, in* 1. ![](https://www.google.com/s2/favicons?domain=https://foursquare.com/) [Foursquare (https://foursquare.com/)](https://foursquare.com/)*: top 5K, geosocial, in*
1. ![](https://www.google.com/s2/favicons?domain=https://4pda.ru/) [4pda (https://4pda.ru/)](https://4pda.ru/)*: top 5K, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://4pda.ru/) [4pda (https://4pda.ru/)](https://4pda.ru/)*: top 5K, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://www.weforum.org) [Weforum (https://www.weforum.org)](https://www.weforum.org)*: top 5K, forum, us* 1. ![](https://www.google.com/s2/favicons?domain=https://www.weforum.org) [Weforum (https://www.weforum.org)](https://www.weforum.org)*: top 5K, forum, us*
1. ![](https://www.google.com/s2/favicons?domain=http://www.techspot.com/community/) [techspot.com (http://www.techspot.com/community/)](http://www.techspot.com/community/)*: top 5K, forum, us* 1. ![](https://www.google.com/s2/favicons?domain=http://www.techspot.com/community/) [techspot.com (http://www.techspot.com/community/)](http://www.techspot.com/community/)*: top 5K, forum, us*
@@ -300,7 +300,7 @@ Rank data fetched from Alexa by domains.
1. ![](https://www.google.com/s2/favicons?domain=https://forums.digitalspy.com/) [Digitalspy (https://forums.digitalspy.com/)](https://forums.digitalspy.com/)*: top 10K, forum, gb, us* 1. ![](https://www.google.com/s2/favicons?domain=https://forums.digitalspy.com/) [Digitalspy (https://forums.digitalspy.com/)](https://forums.digitalspy.com/)*: top 10K, forum, gb, us*
1. ![](https://www.google.com/s2/favicons?domain=https://www.bibsonomy.org) [Bibsonomy (https://www.bibsonomy.org)](https://www.bibsonomy.org)*: top 10K, in* 1. ![](https://www.google.com/s2/favicons?domain=https://www.bibsonomy.org) [Bibsonomy (https://www.bibsonomy.org)](https://www.bibsonomy.org)*: top 10K, in*
1. ![](https://www.google.com/s2/favicons?domain=https://slashdot.org) [Slashdot (https://slashdot.org)](https://slashdot.org)*: top 10K, news* 1. ![](https://www.google.com/s2/favicons?domain=https://slashdot.org) [Slashdot (https://slashdot.org)](https://slashdot.org)*: top 10K, news*
1. ![](https://www.google.com/s2/favicons?domain=https://www.netvibes.com) [Netvibes (https://www.netvibes.com)](https://www.netvibes.com)*: top 10K, de, fr, jp* 1. ![](https://www.google.com/s2/favicons?domain=https://www.netvibes.com) [Netvibes (https://www.netvibes.com)](https://www.netvibes.com)*: top 10K, business, fr*, search is disabled
1. ![](https://www.google.com/s2/favicons?domain=https://opensource.com/) [opensource (https://opensource.com/)](https://opensource.com/)*: top 10K, in, us* 1. ![](https://www.google.com/s2/favicons?domain=https://opensource.com/) [opensource (https://opensource.com/)](https://opensource.com/)*: top 10K, in, us*
1. ![](https://www.google.com/s2/favicons?domain=https://discuss.elastic.co/) [Discuss.Elastic.co (https://discuss.elastic.co/)](https://discuss.elastic.co/)*: top 10K, forum, tech, us* 1. ![](https://www.google.com/s2/favicons?domain=https://discuss.elastic.co/) [Discuss.Elastic.co (https://discuss.elastic.co/)](https://discuss.elastic.co/)*: top 10K, forum, tech, us*
1. ![](https://www.google.com/s2/favicons?domain=https://www.baby.ru/) [Baby.ru (https://www.baby.ru/)](https://www.baby.ru/)*: top 10K, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://www.baby.ru/) [Baby.ru (https://www.baby.ru/)](https://www.baby.ru/)*: top 10K, ru*
@@ -812,7 +812,7 @@ Rank data fetched from Alexa by domains.
1. ![](https://www.google.com/s2/favicons?domain=https://bbs.huami.com) [bbs.huami.com (https://bbs.huami.com)](https://bbs.huami.com)*: top 10M, cn, in, ir, ru, us*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=https://bbs.huami.com) [bbs.huami.com (https://bbs.huami.com)](https://bbs.huami.com)*: top 10M, cn, in, ir, ru, us*, search is disabled
1. ![](https://www.google.com/s2/favicons?domain=https://amazfitwatchfaces.com) [AmazfitWatchFaces (https://amazfitwatchfaces.com)](https://amazfitwatchfaces.com)*: top 10M, ae, es, forum, gr, id, ir, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://amazfitwatchfaces.com) [AmazfitWatchFaces (https://amazfitwatchfaces.com)](https://amazfitwatchfaces.com)*: top 10M, ae, es, forum, gr, id, ir, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://moikrug.ru/) [MoiKrug (https://moikrug.ru/)](https://moikrug.ru/)*: top 10M, career, us* 1. ![](https://www.google.com/s2/favicons?domain=https://moikrug.ru/) [MoiKrug (https://moikrug.ru/)](https://moikrug.ru/)*: top 10M, career, us*
1. ![](https://www.google.com/s2/favicons?domain=http://www.movescount.com) [Movescount (http://www.movescount.com)](http://www.movescount.com)*: top 10M, es, in, pk, ru, us* 1. ![](https://www.google.com/s2/favicons?domain=http://www.movescount.com) [Movescount (http://www.movescount.com)](http://www.movescount.com)*: top 10M, maps*, search is disabled
1. ![](https://www.google.com/s2/favicons?domain=https://tamtam.chat/) [TamTam (https://tamtam.chat/)](https://tamtam.chat/)*: top 10M, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://tamtam.chat/) [TamTam (https://tamtam.chat/)](https://tamtam.chat/)*: top 10M, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://forum.velomania.ru/) [Velomania (https://forum.velomania.ru/)](https://forum.velomania.ru/)*: top 10M, forum, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://forum.velomania.ru/) [Velomania (https://forum.velomania.ru/)](https://forum.velomania.ru/)*: top 10M, forum, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://forum.itvdn.com) [ITVDN Forum (https://forum.itvdn.com)](https://forum.itvdn.com)*: top 10M, forum, ru, ua* 1. ![](https://www.google.com/s2/favicons?domain=https://forum.itvdn.com) [ITVDN Forum (https://forum.itvdn.com)](https://forum.itvdn.com)*: top 10M, forum, ru, ua*
@@ -1056,7 +1056,7 @@ Rank data fetched from Alexa by domains.
1. ![](https://www.google.com/s2/favicons?domain=https://forum.swiftbook.ru) [swiftbook (https://forum.swiftbook.ru)](https://forum.swiftbook.ru)*: top 10M, forum, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://forum.swiftbook.ru) [swiftbook (https://forum.swiftbook.ru)](https://forum.swiftbook.ru)*: top 10M, forum, ru*
1. ![](https://www.google.com/s2/favicons?domain=http://ladies.zp.ua) [Ladies (http://ladies.zp.ua)](http://ladies.zp.ua)*: top 10M, forum, ua* 1. ![](https://www.google.com/s2/favicons?domain=http://ladies.zp.ua) [Ladies (http://ladies.zp.ua)](http://ladies.zp.ua)*: top 10M, forum, ua*
1. ![](https://www.google.com/s2/favicons?domain=https://archlinux.org.ru) [Archlinux (https://archlinux.org.ru)](https://archlinux.org.ru)*: top 10M, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://archlinux.org.ru) [Archlinux (https://archlinux.org.ru)](https://archlinux.org.ru)*: top 10M, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://bethepro.com) [Bethepro (https://bethepro.com)](https://bethepro.com)*: top 10M, pk, us* 1. ![](https://www.google.com/s2/favicons?domain=https://bethepro.com) [Bethepro (https://bethepro.com)](https://bethepro.com)*: top 10M, pk, us*, search is disabled
1. ![](https://www.google.com/s2/favicons?domain=https://forum.mapillary.com) [Mapillary Forum (https://forum.mapillary.com)](https://forum.mapillary.com)*: top 10M, forum, us* 1. ![](https://www.google.com/s2/favicons?domain=https://forum.mapillary.com) [Mapillary Forum (https://forum.mapillary.com)](https://forum.mapillary.com)*: top 10M, forum, us*
1. ![](https://www.google.com/s2/favicons?domain=https://www.firearmstalk.com) [Firearmstalk (https://www.firearmstalk.com)](https://www.firearmstalk.com)*: top 10M, us* 1. ![](https://www.google.com/s2/favicons?domain=https://www.firearmstalk.com) [Firearmstalk (https://www.firearmstalk.com)](https://www.firearmstalk.com)*: top 10M, us*
1. ![](https://www.google.com/s2/favicons?domain=https://www.houserepairtalk.com) [Houserepairtalk (https://www.houserepairtalk.com)](https://www.houserepairtalk.com)*: top 10M, forum, in, us* 1. ![](https://www.google.com/s2/favicons?domain=https://www.houserepairtalk.com) [Houserepairtalk (https://www.houserepairtalk.com)](https://www.houserepairtalk.com)*: top 10M, forum, in, us*
@@ -1199,7 +1199,7 @@ Rank data fetched from Alexa by domains.
1. ![](https://www.google.com/s2/favicons?domain=https://mastodon.xyz/) [mastodon.xyz (https://mastodon.xyz/)](https://mastodon.xyz/)*: top 10M, th* 1. ![](https://www.google.com/s2/favicons?domain=https://mastodon.xyz/) [mastodon.xyz (https://mastodon.xyz/)](https://mastodon.xyz/)*: top 10M, th*
1. ![](https://www.google.com/s2/favicons?domain=https://www.gays.com) [Gays (https://www.gays.com)](https://www.gays.com)*: top 10M, in*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=https://www.gays.com) [Gays (https://www.gays.com)](https://www.gays.com)*: top 10M, in*, search is disabled
1. ![](https://www.google.com/s2/favicons?domain=http://transit-club.com) [transit-club.com (http://transit-club.com)](http://transit-club.com)*: top 10M, ru* 1. ![](https://www.google.com/s2/favicons?domain=http://transit-club.com) [transit-club.com (http://transit-club.com)](http://transit-club.com)*: top 10M, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://favera.ru) [Favera (https://favera.ru)](https://favera.ru)*: top 10M, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://favera.ru) [Favera (https://favera.ru)](https://favera.ru)*: top 10M, ru*, search is disabled
1. ![](https://www.google.com/s2/favicons?domain=https://soylentnews.org) [soylentnews (https://soylentnews.org)](https://soylentnews.org)*: top 10M, us* 1. ![](https://www.google.com/s2/favicons?domain=https://soylentnews.org) [soylentnews (https://soylentnews.org)](https://soylentnews.org)*: top 10M, us*
1. ![](https://www.google.com/s2/favicons?domain=http://chan4chan.com/) [Chan4chan (http://chan4chan.com/)](http://chan4chan.com/)*: top 10M, hu* 1. ![](https://www.google.com/s2/favicons?domain=http://chan4chan.com/) [Chan4chan (http://chan4chan.com/)](http://chan4chan.com/)*: top 10M, hu*
1. ![](https://www.google.com/s2/favicons?domain=http://the-mainboard.com/index.php) [the-mainboard.com (http://the-mainboard.com/index.php)](http://the-mainboard.com/index.php)*: top 10M, forum, us* 1. ![](https://www.google.com/s2/favicons?domain=http://the-mainboard.com/index.php) [the-mainboard.com (http://the-mainboard.com/index.php)](http://the-mainboard.com/index.php)*: top 10M, forum, us*
@@ -1390,7 +1390,7 @@ Rank data fetched from Alexa by domains.
1. ![](https://www.google.com/s2/favicons?domain=https://uaksu.forum24.ru/) [Uaksu (https://uaksu.forum24.ru/)](https://uaksu.forum24.ru/)*: top 10M, forum, ru, ua* 1. ![](https://www.google.com/s2/favicons?domain=https://uaksu.forum24.ru/) [Uaksu (https://uaksu.forum24.ru/)](https://uaksu.forum24.ru/)*: top 10M, forum, ru, ua*
1. ![](https://www.google.com/s2/favicons?domain=http://0-3.ru) [0-3.RU (http://0-3.ru)](http://0-3.ru)*: top 10M, forum, ru* 1. ![](https://www.google.com/s2/favicons?domain=http://0-3.ru) [0-3.RU (http://0-3.ru)](http://0-3.ru)*: top 10M, forum, ru*
1. ![](https://www.google.com/s2/favicons?domain=http://www.forumsi.org) [Forumsi (http://www.forumsi.org)](http://www.forumsi.org)*: top 10M, forum, ru* 1. ![](https://www.google.com/s2/favicons?domain=http://www.forumsi.org) [Forumsi (http://www.forumsi.org)](http://www.forumsi.org)*: top 10M, forum, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://www.snooth.com/) [Snooth (https://www.snooth.com/)](https://www.snooth.com/)*: top 10M, in* 1. ![](https://www.google.com/s2/favicons?domain=https://www.snooth.com/) [Snooth (https://www.snooth.com/)](https://www.snooth.com/)*: top 10M, news*
1. ![](https://www.google.com/s2/favicons?domain=http://soft-deniz.ucoz.ru) [soft-deniz.ucoz.ru (http://soft-deniz.ucoz.ru)](http://soft-deniz.ucoz.ru)*: top 10M* 1. ![](https://www.google.com/s2/favicons?domain=http://soft-deniz.ucoz.ru) [soft-deniz.ucoz.ru (http://soft-deniz.ucoz.ru)](http://soft-deniz.ucoz.ru)*: top 10M*
1. ![](https://www.google.com/s2/favicons?domain=http://oih.at.ua) [oih.at.ua (http://oih.at.ua)](http://oih.at.ua)*: top 10M, ua* 1. ![](https://www.google.com/s2/favicons?domain=http://oih.at.ua) [oih.at.ua (http://oih.at.ua)](http://oih.at.ua)*: top 10M, ua*
1. ![](https://www.google.com/s2/favicons?domain=http://gorodanapa.ru/) [Gorodanapa (http://gorodanapa.ru/)](http://gorodanapa.ru/)*: top 10M, ru*, search is disabled 1. ![](https://www.google.com/s2/favicons?domain=http://gorodanapa.ru/) [Gorodanapa (http://gorodanapa.ru/)](http://gorodanapa.ru/)*: top 10M, ru*, search is disabled
@@ -1442,7 +1442,7 @@ Rank data fetched from Alexa by domains.
1. ![](https://www.google.com/s2/favicons?domain=http://rodobozhie.ru) [rodobozhie.ru (http://rodobozhie.ru)](http://rodobozhie.ru)*: top 10M, ru* 1. ![](https://www.google.com/s2/favicons?domain=http://rodobozhie.ru) [rodobozhie.ru (http://rodobozhie.ru)](http://rodobozhie.ru)*: top 10M, ru*
1. ![](https://www.google.com/s2/favicons?domain=http://satwarez.ru) [satwarez.ru (http://satwarez.ru)](http://satwarez.ru)*: top 10M* 1. ![](https://www.google.com/s2/favicons?domain=http://satwarez.ru) [satwarez.ru (http://satwarez.ru)](http://satwarez.ru)*: top 10M*
1. ![](https://www.google.com/s2/favicons?domain=http://nf-club.ru) [nf-club.ru (http://nf-club.ru)](http://nf-club.ru)*: top 10M* 1. ![](https://www.google.com/s2/favicons?domain=http://nf-club.ru) [nf-club.ru (http://nf-club.ru)](http://nf-club.ru)*: top 10M*
1. ![](https://www.google.com/s2/favicons?domain=http://linuxmint.info) [linuxmint.info (http://linuxmint.info)](http://linuxmint.info)*: top 10M, ru* 1. ![](https://www.google.com/s2/favicons?domain=http://linuxmint.info) [linuxmint.info (http://linuxmint.info)](http://linuxmint.info)*: top 10M, ru*, search is disabled
1. ![](https://www.google.com/s2/favicons?domain=http://kiabongo.info) [kiabongo.info (http://kiabongo.info)](http://kiabongo.info)*: top 10M* 1. ![](https://www.google.com/s2/favicons?domain=http://kiabongo.info) [kiabongo.info (http://kiabongo.info)](http://kiabongo.info)*: top 10M*
1. ![](https://www.google.com/s2/favicons?domain=http://koshtoris.at.ua) [koshtoris.at.ua (http://koshtoris.at.ua)](http://koshtoris.at.ua)*: top 10M* 1. ![](https://www.google.com/s2/favicons?domain=http://koshtoris.at.ua) [koshtoris.at.ua (http://koshtoris.at.ua)](http://koshtoris.at.ua)*: top 10M*
1. ![](https://www.google.com/s2/favicons?domain=http://xn--90anbhklk.xn--p1ai) [xn--90anbhklk.xn--p1ai (http://xn--90anbhklk.xn--p1ai)](http://xn--90anbhklk.xn--p1ai)*: top 10M* 1. ![](https://www.google.com/s2/favicons?domain=http://xn--90anbhklk.xn--p1ai) [xn--90anbhklk.xn--p1ai (http://xn--90anbhklk.xn--p1ai)](http://xn--90anbhklk.xn--p1ai)*: top 10M*
@@ -1469,7 +1469,7 @@ Rank data fetched from Alexa by domains.
1. ![](https://www.google.com/s2/favicons?domain=http://wolga24.at.ua) [wolga24.at.ua (http://wolga24.at.ua)](http://wolga24.at.ua)*: top 10M* 1. ![](https://www.google.com/s2/favicons?domain=http://wolga24.at.ua) [wolga24.at.ua (http://wolga24.at.ua)](http://wolga24.at.ua)*: top 10M*
1. ![](https://www.google.com/s2/favicons?domain=http://millerovo161.ru) [millerovo161.ru (http://millerovo161.ru)](http://millerovo161.ru)*: top 10M* 1. ![](https://www.google.com/s2/favicons?domain=http://millerovo161.ru) [millerovo161.ru (http://millerovo161.ru)](http://millerovo161.ru)*: top 10M*
1. ![](https://www.google.com/s2/favicons?domain=http://videomuzon.ucoz.ru) [videomuzon.ucoz.ru (http://videomuzon.ucoz.ru)](http://videomuzon.ucoz.ru)*: top 10M* 1. ![](https://www.google.com/s2/favicons?domain=http://videomuzon.ucoz.ru) [videomuzon.ucoz.ru (http://videomuzon.ucoz.ru)](http://videomuzon.ucoz.ru)*: top 10M*
1. ![](https://www.google.com/s2/favicons?domain=https://community.autolenta.ru) [Autolenta (https://community.autolenta.ru)](https://community.autolenta.ru)*: top 10M, auto, forum, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://community.autolenta.ru) [Autolenta (https://community.autolenta.ru)](https://community.autolenta.ru)*: top 10M, auto, forum, ru*, search is disabled
1. ![](https://www.google.com/s2/favicons?domain=http://amax-sb.ru) [amax-sb.ru (http://amax-sb.ru)](http://amax-sb.ru)*: top 10M* 1. ![](https://www.google.com/s2/favicons?domain=http://amax-sb.ru) [amax-sb.ru (http://amax-sb.ru)](http://amax-sb.ru)*: top 10M*
1. ![](https://www.google.com/s2/favicons?domain=http://angelgothics.ru) [Angelgothics (http://angelgothics.ru)](http://angelgothics.ru)*: top 10M, ru* 1. ![](https://www.google.com/s2/favicons?domain=http://angelgothics.ru) [Angelgothics (http://angelgothics.ru)](http://angelgothics.ru)*: top 10M, ru*
1. ![](https://www.google.com/s2/favicons?domain=http://help-baby.org) [help-baby.org (http://help-baby.org)](http://help-baby.org)*: top 10M* 1. ![](https://www.google.com/s2/favicons?domain=http://help-baby.org) [help-baby.org (http://help-baby.org)](http://help-baby.org)*: top 10M*
@@ -1559,7 +1559,7 @@ Rank data fetched from Alexa by domains.
1. ![](https://www.google.com/s2/favicons?domain=https://cyberclock.cc) [Cyberclock (https://cyberclock.cc)](https://cyberclock.cc)*: top 100M, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://cyberclock.cc) [Cyberclock (https://cyberclock.cc)](https://cyberclock.cc)*: top 100M, ru*
1. ![](https://www.google.com/s2/favicons?domain=http://www.cydak.ru) [Cydak (http://www.cydak.ru)](http://www.cydak.ru)*: top 100M, ru* 1. ![](https://www.google.com/s2/favicons?domain=http://www.cydak.ru) [Cydak (http://www.cydak.ru)](http://www.cydak.ru)*: top 100M, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://www.designspiration.net/) [Designspiration (https://www.designspiration.net/)](https://www.designspiration.net/)*: top 100M* 1. ![](https://www.google.com/s2/favicons?domain=https://www.designspiration.net/) [Designspiration (https://www.designspiration.net/)](https://www.designspiration.net/)*: top 100M*
1. ![](https://www.google.com/s2/favicons?domain=https://dinsk.su) [Dinsk (https://dinsk.su)](https://dinsk.su)*: top 100M, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://dinsk.su) [Dinsk (https://dinsk.su)](https://dinsk.su)*: top 100M, ru*, search is disabled
1. ![](https://www.google.com/s2/favicons?domain=https://forum.djangoproject.co) [Djangoproject.co (https://forum.djangoproject.co)](https://forum.djangoproject.co)*: top 100M, coding, forum* 1. ![](https://www.google.com/s2/favicons?domain=https://forum.djangoproject.co) [Djangoproject.co (https://forum.djangoproject.co)](https://forum.djangoproject.co)*: top 100M, coding, forum*
1. ![](https://www.google.com/s2/favicons?domain=https://www.dublikat.shop) [Dublikat (https://www.dublikat.shop)](https://www.dublikat.shop)*: top 100M, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://www.dublikat.shop) [Dublikat (https://www.dublikat.shop)](https://www.dublikat.shop)*: top 100M, ru*
1. ![](https://www.google.com/s2/favicons?domain=http://eightbit.me/) [Eightbit (http://eightbit.me/)](http://eightbit.me/)*: top 100M* 1. ![](https://www.google.com/s2/favicons?domain=http://eightbit.me/) [Eightbit (http://eightbit.me/)](http://eightbit.me/)*: top 100M*
@@ -1586,7 +1586,7 @@ Rank data fetched from Alexa by domains.
1. ![](https://www.google.com/s2/favicons?domain=https://macqa.ru) [Macqa (https://macqa.ru)](https://macqa.ru)*: top 100M, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://macqa.ru) [Macqa (https://macqa.ru)](https://macqa.ru)*: top 100M, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://magiimir.com) [Magiimir (https://magiimir.com)](https://magiimir.com)*: top 100M, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://magiimir.com) [Magiimir (https://magiimir.com)](https://magiimir.com)*: top 100M, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://mamochki.by/) [Mamochki (https://mamochki.by/)](https://mamochki.by/)*: top 100M, by, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://mamochki.by/) [Mamochki (https://mamochki.by/)](https://mamochki.by/)*: top 100M, by, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://mastersofcrypto.com) [Mastersofcrypto (https://mastersofcrypto.com)](https://mastersofcrypto.com)*: top 100M, forum* 1. ![](https://www.google.com/s2/favicons?domain=https://mastersofcrypto.com) [Mastersofcrypto (https://mastersofcrypto.com)](https://mastersofcrypto.com)*: top 100M, forum*, search is disabled
1. ![](https://www.google.com/s2/favicons?domain=http:/mixlr.com/) [Mixlr (http:/mixlr.com/)](http:/mixlr.com/)*: top 100M, gb* 1. ![](https://www.google.com/s2/favicons?domain=http:/mixlr.com/) [Mixlr (http:/mixlr.com/)](http:/mixlr.com/)*: top 100M, gb*
1. ![](https://www.google.com/s2/favicons?domain=https://www.munzee.com/) [Munzee (https://www.munzee.com/)](https://www.munzee.com/)*: top 100M, gb* 1. ![](https://www.google.com/s2/favicons?domain=https://www.munzee.com/) [Munzee (https://www.munzee.com/)](https://www.munzee.com/)*: top 100M, gb*
1. ![](https://www.google.com/s2/favicons?domain=http://murmansk-life.ru) [MurmanskLife (http://murmansk-life.ru)](http://murmansk-life.ru)*: top 100M, ru* 1. ![](https://www.google.com/s2/favicons?domain=http://murmansk-life.ru) [MurmanskLife (http://murmansk-life.ru)](http://murmansk-life.ru)*: top 100M, ru*
@@ -2283,8 +2283,8 @@ Rank data fetched from Alexa by domains.
1. ![](https://www.google.com/s2/favicons?domain=https://freelance.ru) [freelance.ru (https://freelance.ru)](https://freelance.ru)*: top 100M, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://freelance.ru) [freelance.ru (https://freelance.ru)](https://freelance.ru)*: top 100M, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://freelansim.ru) [freelansim.ru (https://freelansim.ru)](https://freelansim.ru)*: top 100M* 1. ![](https://www.google.com/s2/favicons?domain=https://freelansim.ru) [freelansim.ru (https://freelansim.ru)](https://freelansim.ru)*: top 100M*
1. ![](https://www.google.com/s2/favicons?domain=http://fotolog.com) [fotolog.com (http://fotolog.com)](http://fotolog.com)*: top 100M, in* 1. ![](https://www.google.com/s2/favicons?domain=http://fotolog.com) [fotolog.com (http://fotolog.com)](http://fotolog.com)*: top 100M, in*
1. ![](https://www.google.com/s2/favicons?domain=http://thoughts.com) [thoughts.com (http://thoughts.com)](http://thoughts.com)*: top 100M, in* 1. ![](https://www.google.com/s2/favicons?domain=http://thoughts.com) [thoughts.com (http://thoughts.com)](http://thoughts.com)*: top 100M, blog*
1. ![](https://www.google.com/s2/favicons?domain=https://hackernoon.com) [hackernoon.com (https://hackernoon.com)](https://hackernoon.com)*: top 100M, in, us* 1. ![](https://www.google.com/s2/favicons?domain=https://hackernoon.com) [hackernoon.com (https://hackernoon.com)](https://hackernoon.com)*: top 100M, news, us*
1. ![](https://www.google.com/s2/favicons?domain=https://intigriti.com) [Intigriti (https://intigriti.com)](https://intigriti.com)*: top 100M, hacking, in* 1. ![](https://www.google.com/s2/favicons?domain=https://intigriti.com) [Intigriti (https://intigriti.com)](https://intigriti.com)*: top 100M, hacking, in*
1. ![](https://www.google.com/s2/favicons?domain=https://yamaya.ru) [yamaya.ru (https://yamaya.ru)](https://yamaya.ru)*: top 100M, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://yamaya.ru) [yamaya.ru (https://yamaya.ru)](https://yamaya.ru)*: top 100M, ru*
1. ![](https://www.google.com/s2/favicons?domain=https://www.tinkoff.ru/invest/) [Tinkoff Invest (https://www.tinkoff.ru/invest/)](https://www.tinkoff.ru/invest/)*: top 100M, ru* 1. ![](https://www.google.com/s2/favicons?domain=https://www.tinkoff.ru/invest/) [Tinkoff Invest (https://www.tinkoff.ru/invest/)](https://www.tinkoff.ru/invest/)*: top 100M, ru*
@@ -2313,7 +2313,7 @@ Rank data fetched from Alexa by domains.
1. ![](https://www.google.com/s2/favicons?domain=http://mednolit.ru) [mednolit.ru (http://mednolit.ru)](http://mednolit.ru)*: top 100M, ru* 1. ![](https://www.google.com/s2/favicons?domain=http://mednolit.ru) [mednolit.ru (http://mednolit.ru)](http://mednolit.ru)*: top 100M, ru*
1. ![](https://www.google.com/s2/favicons?domain=http://mikele-loconte.ru) [mikele-loconte.ru (http://mikele-loconte.ru)](http://mikele-loconte.ru)*: top 100M* 1. ![](https://www.google.com/s2/favicons?domain=http://mikele-loconte.ru) [mikele-loconte.ru (http://mikele-loconte.ru)](http://mikele-loconte.ru)*: top 100M*
1. ![](https://www.google.com/s2/favicons?domain=http://mkuniverse.ru) [mkuniverse.ru (http://mkuniverse.ru)](http://mkuniverse.ru)*: top 100M* 1. ![](https://www.google.com/s2/favicons?domain=http://mkuniverse.ru) [mkuniverse.ru (http://mkuniverse.ru)](http://mkuniverse.ru)*: top 100M*
1. ![](https://www.google.com/s2/favicons?domain=https://hashnode.com) [hashnode.com (https://hashnode.com)](https://hashnode.com)*: top 100M, in* 1. ![](https://www.google.com/s2/favicons?domain=https://hashnode.com) [hashnode (https://hashnode.com)](https://hashnode.com)*: top 100M, in*
1. ![](https://www.google.com/s2/favicons?domain=https://www.change.org) [www.change.org (https://www.change.org)](https://www.change.org)*: top 100M, us* 1. ![](https://www.google.com/s2/favicons?domain=https://www.change.org) [www.change.org (https://www.change.org)](https://www.change.org)*: top 100M, us*
1. ![](https://www.google.com/s2/favicons?domain=https://www.ifunny.co) [www.ifunny.co (https://www.ifunny.co)](https://www.ifunny.co)*: top 100M, us* 1. ![](https://www.google.com/s2/favicons?domain=https://www.ifunny.co) [www.ifunny.co (https://www.ifunny.co)](https://www.ifunny.co)*: top 100M, us*
1. ![](https://www.google.com/s2/favicons?domain=https://localcryptosapi.com) [LocalCryptos (https://localcryptosapi.com)](https://localcryptosapi.com)*: top 100M* 1. ![](https://www.google.com/s2/favicons?domain=https://localcryptosapi.com) [LocalCryptos (https://localcryptosapi.com)](https://localcryptosapi.com)*: top 100M*
@@ -2599,4 +2599,53 @@ Rank data fetched from Alexa by domains.
1. ![](https://www.google.com/s2/favicons?domain=https://www.hozpitality.com) [hozpitality (https://www.hozpitality.com)](https://www.hozpitality.com)*: top 100M* 1. ![](https://www.google.com/s2/favicons?domain=https://www.hozpitality.com) [hozpitality (https://www.hozpitality.com)](https://www.hozpitality.com)*: top 100M*
1. ![](https://www.google.com/s2/favicons?domain=https://kazanlashkigalab.com) [kazanlashkigalab.com (https://kazanlashkigalab.com)](https://kazanlashkigalab.com)*: top 100M, kz* 1. ![](https://www.google.com/s2/favicons?domain=https://kazanlashkigalab.com) [kazanlashkigalab.com (https://kazanlashkigalab.com)](https://kazanlashkigalab.com)*: top 100M, kz*
Alexa.com rank data fetched at (2022-01-21 21:28:53.863014 UTC) The list was updated at (2022-02-27 01:43:04.619091 UTC)
## Statistics
Enabled/total sites: 2440/2595 = 94.03%
Incomplete checks: 523/1853 = 28.22% (false positive risks)
Top 20 profile URLs:
- (796) `{urlMain}/index/8-0-{username} (uCoz)`
- (221) `{urlMain}{urlSubpath}/members/?username={username} (XenForo)`
- (221) `/{username}`
- (138) `/user/{username}`
- (134) `{urlMain}{urlSubpath}/member.php?username={username} (vBulletin)`
- (96) `/profile/{username}`
- (87) `{urlMain}/u/{username}/summary (Discourse)`
- (74) `/users/{username}`
- (44) `{urlMain}{urlSubpath}/search.php?author={username} (phpBB/Search)`
- (41) `/members/?username={username}`
- (39) `SUBDOMAIN`
- (36) `/@{username}`
- (28) `/u/{username}`
- (27) `{urlMain}{urlSubpath}/memberlist.php?username={username} (phpBB)`
- (25) `/members/{username}`
- (18) `/forum/members/?username={username}`
- (18) `/forum/search.php?keywords=&terms=all&author={username}`
- (17) `/search.php?keywords=&terms=all&author={username}`
- (16) `/author/{username}`
- (14) `/profile.php?mode=viewprofile&u={username}`
Top 20 tags:
- (271) `forum`
- (79) `NO_TAGS` (non-standard)
- (50) `gaming`
- (24) `photo`
- (24) `coding`
- (18) `news`
- (18) `blog`
- (18) `music`
- (15) `tech`
- (13) `freelance`
- (12) `sharing`
- (12) `finance`
- (11) `shopping`
- (10) `dating`
- (10) `art`
- (9) `hobby`
- (9) `movies`
- (7) `sport`
- (7) `hacking`
- (5) `stock`
utils/update_site_data.py
+1 -1
View File
@@ -137,7 +137,7 @@ Rank data fetched from Alexa by domains.
site_file.write(f'1. {favicon} [{site}]({url_main})*: top {valid_rank}{tags}*{note}\n') site_file.write(f'1. {favicon} [{site}]({url_main})*: top {valid_rank}{tags}*{note}\n')
db.update_site(site) db.update_site(site)
site_file.write(f'\nAlexa.com rank data fetched at ({datetime.utcnow()} UTC)\n') site_file.write(f'\nThe list was updated at ({datetime.utcnow()} UTC)\n')
db.save_to_file(args.base_file) db.save_to_file(args.base_file)
statistics_text = db.get_db_stats(is_markdown=True) statistics_text = db.get_db_stats(is_markdown=True)