Projects STRLCPY maigret Commits bc787cdf
🤬
  • Fix false positives (#370)

    * Fixed several false positives, improved statistics info
    
    * Disabled some sites, fixed fp percent count method
    
    * Updated site list and statistics
  • Loading...
  • Soxoj committed with GitHub 3 years ago
    bc787cdf
    1 parent dcf5181e
Revision indexing in progress... (symbol navigation in revisions will be accurate after indexed)
  • ■ ■ ■ ■ ■ ■
    maigret/resources/data.json
    skipped 1879 lines
    1880 1880   ],
    1881 1881   "checkType": "message",
    1882 1882   "absenceStrs": [
    1883  - "\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!"
     1883 + "\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"
    1884 1884   ],
    1885 1885   "alexaRank": 2303903,
    1886 1886   "urlMain": "https://bgforum.ru",
    skipped 1711 lines
    3598 3598   "tags": [
    3599 3599   "ru"
    3600 3600   ],
     3601 + "disabled": true,
    3601 3602   "checkType": "status_code",
    3602 3603   "urlMain": "https://dinsk.su",
    3603 3604   "url": "https://dinsk.su/user/{username}",
    skipped 967 lines
    4571 4572   "tags": [
    4572 4573   "ru"
    4573 4574   ],
     4575 + "disabled": true,
    4574 4576   "checkType": "status_code",
    4575 4577   "alexaRank": 1225740,
    4576 4578   "urlMain": "https://favera.ru",
    skipped 3969 lines
    8546 8548   "tags": [
    8547 8549   "forum"
    8548 8550   ],
     8551 + "disabled": true,
    8549 8552   "checkType": "message",
    8550 8553   "absenceStrs": [
    8551 8554   "The specified member cannot be found"
    skipped 530 lines
    9082 9085   },
    9083 9086   "Movescount": {
    9084 9087   "tags": [
    9085  - "es",
    9086  - "in",
    9087  - "pk",
    9088  - "ru",
    9089  - "us"
     9088 + "maps"
    9090 9089   ],
     9090 + "disabled": true,
    9091 9091   "checkType": "message",
    9092 9092   "absenceStrs": [
    9093 9093   "error=4&"
    skipped 3797 lines
    12891 12891   },
    12892 12892   "Snooth": {
    12893 12893   "tags": [
    12894  - "in"
     12894 + "news"
    12895 12895   ],
    12896 12896   "checkType": "message",
    12897 12897   "absenceStrs": [
    12898  - "<title>Profiles on Snooth</title>"
     12898 + "<title>Page not found"
     12899 + ],
     12900 + "presenseStrs": [
     12901 + "content=\"https://www.snooth.com/author/"
    12899 12902   ],
    12900 12903   "alexaRank": 4088489,
    12901 12904   "urlMain": "https://www.snooth.com/",
    12902  - "url": "https://www.snooth.com/profiles/{username}/",
    12903  - "usernameClaimed": "GregT",
     12905 + "url": "https://www.snooth.com/author/{username}/",
     12906 + "usernameClaimed": "joshua",
    12904 12907   "usernameUnclaimed": "noonewouldeverusethis7"
    12905 12908   },
    12906 12909   "SocialLibremOne": {
    skipped 2082 lines
    14989 14992   "video"
    14990 14993   ],
    14991 14994   "headers": {
    14992  - "Authorization": "jwt eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJleHAiOjE2NDU4Nzg1NDAsInVzZXJfaWQiOm51bGwsImFwcF9pZCI6NTg0NzksInNjb3BlcyI6InB1YmxpYyIsInRlYW1fdXNlcl9pZCI6bnVsbH0.Bs6VBcKPsl-5dqoThdAImBIex1mas1UcyG2pSnIYqYk"
     14995 + "Authorization": "jwt eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJleHAiOjE2NDU4Nzk3NDAsInVzZXJfaWQiOm51bGwsImFwcF9pZCI6NTg0NzksInNjb3BlcyI6InB1YmxpYyIsInRlYW1fdXNlcl9pZCI6bnVsbH0.T8E8Vrx0sO-9WP4RdZGNQZw2EB1hYTIXbIguXIZbfNQ"
    14993 14996   },
    14994 14997   "activation": {
    14995 14998   "url": "https://vimeo.com/_rv/viewer",
    skipped 9837 lines
    24833 24836   "usernameClaimed": "alex",
    24834 24837   "usernameUnclaimed": "noonewouldeverusethis7"
    24835 24838   },
    24836  - "hashnode.com": {
     24839 + "hashnode": {
    24837 24840   "tags": [
    24838 24841   "in"
    24839 24842   ],
    skipped 6 lines
    24846 24849   " name="
    24847 24850   ],
    24848 24851   "absenceStrs": [
    24849  - "></title><meta name="
     24852 + "We can\u2019t find the page you\u2019re looking for!"
    24850 24853   ],
    24851 24854   "urlMain": "https://hashnode.com",
    24852 24855   "url": "https://hashnode.com/@{username}",
    skipped 2094 lines
    26947 26950   },
    26948 26951   "forum.rastrnet.ru": {
    26949 26952   "urlMain": "http://forum.rastrnet.ru",
     26953 + "errors": {
     26954 + "\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"
     26955 + },
    26950 26956   "engine": "vBulletin",
    26951 26957   "usernameClaimed": "alex",
    26952 26958   "usernameUnclaimed": "noonewouldeverusethis7",
    skipped 2154 lines
  • ■ ■ ■ ■
    maigret/sites.py
    skipped 437 lines
    438 438   url_type = site.get_url_template()
    439 439   urls[url_type] = urls.get(url_type, 0) + 1
    440 440   
    441  - if site.check_type == 'message':
     441 + if site.check_type == 'message' and not site.disabled:
    442 442   message_checks += 1
    443 443   if site.absence_strs and site.presense_strs:
    444 444   continue
    skipped 31 lines
  • ■ ■ ■ ■ ■ ■
    sites.md
    skipped 811 lines
    812 812  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
    813 813  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*
    814 814  1. ![](https://www.google.com/s2/favicons?domain=https://moikrug.ru/) [MoiKrug (https://moikrug.ru/)](https://moikrug.ru/)*: top 10M, career, us*
    815  -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*
     815 +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
    816 816  1. ![](https://www.google.com/s2/favicons?domain=https://tamtam.chat/) [TamTam (https://tamtam.chat/)](https://tamtam.chat/)*: top 10M, ru*
    817 817  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*
    818 818  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*
    skipped 380 lines
    1199 1199  1. ![](https://www.google.com/s2/favicons?domain=https://mastodon.xyz/) [mastodon.xyz (https://mastodon.xyz/)](https://mastodon.xyz/)*: top 10M, th*
    1200 1200  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
    1201 1201  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*
    1202  -1. ![](https://www.google.com/s2/favicons?domain=https://favera.ru) [Favera (https://favera.ru)](https://favera.ru)*: top 10M, ru*
     1202 +1. ![](https://www.google.com/s2/favicons?domain=https://favera.ru) [Favera (https://favera.ru)](https://favera.ru)*: top 10M, ru*, search is disabled
    1203 1203  1. ![](https://www.google.com/s2/favicons?domain=https://soylentnews.org) [soylentnews (https://soylentnews.org)](https://soylentnews.org)*: top 10M, us*
    1204 1204  1. ![](https://www.google.com/s2/favicons?domain=http://chan4chan.com/) [Chan4chan (http://chan4chan.com/)](http://chan4chan.com/)*: top 10M, hu*
    1205 1205  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*
    skipped 184 lines
    1390 1390  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*
    1391 1391  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*
    1392 1392  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*
    1393  -1. ![](https://www.google.com/s2/favicons?domain=https://www.snooth.com/) [Snooth (https://www.snooth.com/)](https://www.snooth.com/)*: top 10M, in*
     1393 +1. ![](https://www.google.com/s2/favicons?domain=https://www.snooth.com/) [Snooth (https://www.snooth.com/)](https://www.snooth.com/)*: top 10M, news*
    1394 1394  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*
    1395 1395  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*
    1396 1396  1. ![](https://www.google.com/s2/favicons?domain=http://gorodanapa.ru/) [Gorodanapa (http://gorodanapa.ru/)](http://gorodanapa.ru/)*: top 10M, ru*, search is disabled
    skipped 162 lines
    1559 1559  1. ![](https://www.google.com/s2/favicons?domain=https://cyberclock.cc) [Cyberclock (https://cyberclock.cc)](https://cyberclock.cc)*: top 100M, ru*
    1560 1560  1. ![](https://www.google.com/s2/favicons?domain=http://www.cydak.ru) [Cydak (http://www.cydak.ru)](http://www.cydak.ru)*: top 100M, ru*
    1561 1561  1. ![](https://www.google.com/s2/favicons?domain=https://www.designspiration.net/) [Designspiration (https://www.designspiration.net/)](https://www.designspiration.net/)*: top 100M*
    1562  -1. ![](https://www.google.com/s2/favicons?domain=https://dinsk.su) [Dinsk (https://dinsk.su)](https://dinsk.su)*: top 100M, ru*
     1562 +1. ![](https://www.google.com/s2/favicons?domain=https://dinsk.su) [Dinsk (https://dinsk.su)](https://dinsk.su)*: top 100M, ru*, search is disabled
    1563 1563  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*
    1564 1564  1. ![](https://www.google.com/s2/favicons?domain=https://www.dublikat.shop) [Dublikat (https://www.dublikat.shop)](https://www.dublikat.shop)*: top 100M, ru*
    1565 1565  1. ![](https://www.google.com/s2/favicons?domain=http://eightbit.me/) [Eightbit (http://eightbit.me/)](http://eightbit.me/)*: top 100M*
    skipped 20 lines
    1586 1586  1. ![](https://www.google.com/s2/favicons?domain=https://macqa.ru) [Macqa (https://macqa.ru)](https://macqa.ru)*: top 100M, ru*
    1587 1587  1. ![](https://www.google.com/s2/favicons?domain=https://magiimir.com) [Magiimir (https://magiimir.com)](https://magiimir.com)*: top 100M, ru*
    1588 1588  1. ![](https://www.google.com/s2/favicons?domain=https://mamochki.by/) [Mamochki (https://mamochki.by/)](https://mamochki.by/)*: top 100M, by, ru*
    1589  -1. ![](https://www.google.com/s2/favicons?domain=https://mastersofcrypto.com) [Mastersofcrypto (https://mastersofcrypto.com)](https://mastersofcrypto.com)*: top 100M, forum*
     1589 +1. ![](https://www.google.com/s2/favicons?domain=https://mastersofcrypto.com) [Mastersofcrypto (https://mastersofcrypto.com)](https://mastersofcrypto.com)*: top 100M, forum*, search is disabled
    1590 1590  1. ![](https://www.google.com/s2/favicons?domain=http:/mixlr.com/) [Mixlr (http:/mixlr.com/)](http:/mixlr.com/)*: top 100M, gb*
    1591 1591  1. ![](https://www.google.com/s2/favicons?domain=https://www.munzee.com/) [Munzee (https://www.munzee.com/)](https://www.munzee.com/)*: top 100M, gb*
    1592 1592  1. ![](https://www.google.com/s2/favicons?domain=http://murmansk-life.ru) [MurmanskLife (http://murmansk-life.ru)](http://murmansk-life.ru)*: top 100M, ru*
    skipped 720 lines
    2313 2313  1. ![](https://www.google.com/s2/favicons?domain=http://mednolit.ru) [mednolit.ru (http://mednolit.ru)](http://mednolit.ru)*: top 100M, ru*
    2314 2314  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*
    2315 2315  1. ![](https://www.google.com/s2/favicons?domain=http://mkuniverse.ru) [mkuniverse.ru (http://mkuniverse.ru)](http://mkuniverse.ru)*: top 100M*
    2316  -1. ![](https://www.google.com/s2/favicons?domain=https://hashnode.com) [hashnode.com (https://hashnode.com)](https://hashnode.com)*: top 100M, in*
     2316 +1. ![](https://www.google.com/s2/favicons?domain=https://hashnode.com) [hashnode (https://hashnode.com)](https://hashnode.com)*: top 100M, in*
    2317 2317  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*
    2318 2318  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*
    2319 2319  1. ![](https://www.google.com/s2/favicons?domain=https://localcryptosapi.com) [LocalCryptos (https://localcryptosapi.com)](https://localcryptosapi.com)*: top 100M*
    skipped 279 lines
    2599 2599  1. ![](https://www.google.com/s2/favicons?domain=https://www.hozpitality.com) [hozpitality (https://www.hozpitality.com)](https://www.hozpitality.com)*: top 100M*
    2600 2600  1. ![](https://www.google.com/s2/favicons?domain=https://kazanlashkigalab.com) [kazanlashkigalab.com (https://kazanlashkigalab.com)](https://kazanlashkigalab.com)*: top 100M, kz*
    2601 2601   
    2602  -Alexa.com rank data fetched at (2022-02-26 12:19:53.127789 UTC)
     2602 +Alexa.com rank data fetched at (2022-02-26 12:55:54.605333 UTC)
    2603 2603  ## Statistics
    2604 2604   
    2605  -Enabled/total sites: 2447/2595 = 94.3%
     2605 +Enabled/total sites: 2443/2595 = 94.14%
    2606 2606   
    2607  -Incomplete checks: 582/1978 = 29.42% (false positive risks)
     2607 +Incomplete checks: 525/1853 = 28.33% (false positive risks)
    2608 2608   
    2609 2609  Top 20 profile URLs:
    2610 2610  - (796) `{urlMain}/index/8-0-{username} (uCoz)`
    skipped 14 lines
    2625 2625  - (18) `/forum/members/?username={username}`
    2626 2626  - (18) `/forum/search.php?keywords=&terms=all&author={username}`
    2627 2627  - (17) `/search.php?keywords=&terms=all&author={username}`
    2628  -- (15) `/author/{username}`
     2628 +- (16) `/author/{username}`
    2629 2629  - (14) `/profile.php?mode=viewprofile&u={username}`
    2630 2630   
    2631 2631  Top 20 tags:
    2632  -- (255) `forum`
     2632 +- (271) `forum`
     2633 +- (79) `NO_TAGS` (non-standard)
    2633 2634  - (50) `gaming`
    2634  -- (40) `NO_TAGS` (non-standard)
     2635 +- (24) `photo`
    2635 2636  - (24) `coding`
    2636  -- (23) `photo`
    2637 2637  - (18) `news`
    2638 2638  - (18) `blog`
    2639  -- (17) `music`
     2639 +- (18) `music`
    2640 2640  - (15) `tech`
    2641 2641  - (13) `freelance`
    2642 2642  - (12) `sharing`
    skipped 2 lines
    2645 2645  - (10) `dating`
    2646 2646  - (10) `art`
    2647 2647  - (9) `hobby`
    2648  -- (8) `movies`
     2648 +- (9) `movies`
    2649 2649  - (7) `sport`
    2650 2650  - (7) `hacking`
    2651 2651  - (5) `stock`
    skipped 1 lines
Please wait...
Page is in error, reload to recover