device_detector 1.0.1 → 1.0.5
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.rubocop.yml +49 -0
- data/.ruby-version +1 -0
- data/.travis.yml +5 -10
- data/CHANGELOG.md +14 -1
- data/README.md +6 -6
- data/Rakefile +20 -13
- data/device_detector.gemspec +1 -0
- data/lib/device_detector.rb +30 -26
- data/lib/device_detector/bot.rb +2 -2
- data/lib/device_detector/client.rb +3 -2
- data/lib/device_detector/device.rb +46 -20
- data/lib/device_detector/memory_cache.rb +26 -19
- data/lib/device_detector/metadata_extractor.rb +7 -8
- data/lib/device_detector/model_extractor.rb +3 -3
- data/lib/device_detector/name_extractor.rb +2 -2
- data/lib/device_detector/os.rb +121 -111
- data/lib/device_detector/parser.rb +22 -9
- data/lib/device_detector/version.rb +3 -1
- data/lib/device_detector/version_extractor.rb +2 -3
- data/regexes/bots.yml +442 -19
- data/regexes/client/browser_engine.yml +7 -1
- data/regexes/client/browsers.yml +773 -103
- data/regexes/client/feed_readers.yml +14 -8
- data/regexes/client/libraries.yml +43 -2
- data/regexes/client/mediaplayers.yml +21 -5
- data/regexes/client/mobile_apps.yml +131 -1
- data/regexes/client/pim.yml +6 -1
- data/regexes/device/cameras.yml +1 -1
- data/regexes/device/car_browsers.yml +7 -3
- data/regexes/device/consoles.yml +3 -3
- data/regexes/device/mobiles.yml +11365 -791
- data/regexes/device/notebooks.yml +114 -0
- data/regexes/device/portable_media_player.yml +2 -2
- data/regexes/device/televisions.yml +17 -3
- data/regexes/oss.yml +115 -47
- data/regexes/vendorfragments.yml +6 -2
- data/spec/device_detector/concrete_user_agent_spec.rb +16 -17
- data/spec/device_detector/detector_fixtures_spec.rb +30 -35
- data/spec/device_detector/device_spec.rb +28 -48
- data/spec/device_detector/memory_cache_spec.rb +60 -28
- data/spec/device_detector/model_extractor_spec.rb +3 -3
- data/spec/device_detector/version_extractor_spec.rb +5 -6
- data/spec/device_detector_spec.rb +49 -78
- data/spec/fixtures/client/browser.yml +1521 -406
- data/spec/fixtures/client/feed_reader.yml +39 -51
- data/spec/fixtures/client/library.yml +72 -11
- data/spec/fixtures/client/mediaplayer.yml +29 -40
- data/spec/fixtures/client/mobile_app.yml +172 -32
- data/spec/fixtures/client/pim.yml +32 -19
- data/spec/fixtures/detector/bots.yml +854 -19
- data/spec/fixtures/detector/camera.yml +22 -2
- data/spec/fixtures/detector/car_browser.yml +60 -0
- data/spec/fixtures/detector/console.yml +43 -3
- data/spec/fixtures/detector/desktop.yml +2860 -1527
- data/spec/fixtures/detector/feature_phone.yml +69 -1
- data/spec/fixtures/detector/feed_reader.yml +158 -130
- data/spec/fixtures/detector/mediaplayer.yml +113 -39
- data/spec/fixtures/detector/mobile_apps.yml +262 -89
- data/spec/fixtures/detector/phablet.yml +3444 -663
- data/spec/fixtures/detector/portable_media_player.yml +57 -0
- data/spec/fixtures/detector/smart_speaker.yml +55 -0
- data/spec/fixtures/detector/smartphone-1.yml +4739 -4765
- data/spec/fixtures/detector/smartphone-10.yml +9973 -0
- data/spec/fixtures/detector/smartphone-11.yml +10015 -0
- data/spec/fixtures/detector/smartphone-12.yml +9897 -0
- data/spec/fixtures/detector/smartphone-13.yml +9912 -0
- data/spec/fixtures/detector/smartphone-14.yml +9935 -0
- data/spec/fixtures/detector/smartphone-15.yml +6595 -0
- data/spec/fixtures/detector/smartphone-16.yml +10021 -0
- data/spec/fixtures/detector/smartphone-17.yml +9408 -0
- data/spec/fixtures/detector/smartphone-2.yml +4265 -4238
- data/spec/fixtures/detector/smartphone-3.yml +4487 -4391
- data/spec/fixtures/detector/smartphone-4.yml +4210 -4179
- data/spec/fixtures/detector/smartphone-5.yml +5794 -2901
- data/spec/fixtures/detector/smartphone-6.yml +10114 -0
- data/spec/fixtures/detector/smartphone-7.yml +9975 -0
- data/spec/fixtures/detector/smartphone-8.yml +9897 -0
- data/spec/fixtures/detector/smartphone-9.yml +9880 -0
- data/spec/fixtures/detector/smartphone.yml +4152 -4048
- data/spec/fixtures/detector/tablet-1.yml +3997 -3991
- data/spec/fixtures/detector/tablet-2.yml +6820 -1935
- data/spec/fixtures/detector/tablet-3.yml +9968 -0
- data/spec/fixtures/detector/tablet-4.yml +7113 -0
- data/spec/fixtures/detector/tablet.yml +3789 -3804
- data/spec/fixtures/detector/tv.yml +3889 -1495
- data/spec/fixtures/detector/unknown.yml +45 -179
- data/spec/fixtures/detector/wearable.yml +61 -0
- data/spec/fixtures/device/camera.yml +4 -3
- data/spec/fixtures/device/car_browser.yml +9 -2
- data/spec/fixtures/device/console.yml +15 -14
- data/spec/fixtures/device/notebook.yml +7 -0
- data/spec/fixtures/parser/oss.yml +177 -0
- data/spec/fixtures/parser/vendorfragments.yml +6 -0
- metadata +57 -7
data/regexes/bots.yml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
###############
|
2
2
|
# Device Detector - The Universal Device Detection library for parsing User Agents
|
3
3
|
#
|
4
|
-
# @link
|
4
|
+
# @link https://matomo.org
|
5
5
|
# @license http://www.gnu.org/licenses/lgpl.html LGPL v3 or later
|
6
6
|
###############
|
7
7
|
|
@@ -53,6 +53,21 @@
|
|
53
53
|
name: 'Alexa Internet'
|
54
54
|
url: 'http://www.alexa.com'
|
55
55
|
|
56
|
+
- regex: 'alexa site audit'
|
57
|
+
name: 'Alexa Site Audit'
|
58
|
+
category: 'Site Monitor'
|
59
|
+
url: 'http://www.alexa.com/help/webmasters'
|
60
|
+
producer:
|
61
|
+
name: 'Alexa Internet'
|
62
|
+
url: 'http://www.alexa.com'
|
63
|
+
|
64
|
+
- regex: 'Amazon[ -]Route ?53[ -]Health[ -]Check[ -]Service'
|
65
|
+
name: 'Amazon Route53 Health Check'
|
66
|
+
category: 'Service Agent'
|
67
|
+
producer:
|
68
|
+
name: 'Amazon Web Services'
|
69
|
+
url: 'https://aws.amazon.com/'
|
70
|
+
|
56
71
|
- regex: 'AmorankSpider'
|
57
72
|
name: 'Amorank Spider'
|
58
73
|
category: 'Crawler'
|
@@ -77,6 +92,22 @@
|
|
77
92
|
name: 'Apple Inc'
|
78
93
|
url: 'http://www.apple.com'
|
79
94
|
|
95
|
+
- regex: 'Arachni'
|
96
|
+
name: 'Arachni'
|
97
|
+
category: 'Security Checker'
|
98
|
+
url: 'http://www.arachni-scanner.com'
|
99
|
+
producer:
|
100
|
+
name: 'Sarosys LLC'
|
101
|
+
url: 'http://www.sarosys.com/'
|
102
|
+
|
103
|
+
- regex: 'AspiegelBot'
|
104
|
+
name: 'AspiegelBot'
|
105
|
+
category: 'Crawler'
|
106
|
+
url: 'https://aspiegel.com/'
|
107
|
+
producer:
|
108
|
+
name: 'Huawei'
|
109
|
+
url: 'https://www.huawei.com/'
|
110
|
+
|
80
111
|
- regex: 'Castro 2, Episode Duration Lookup'
|
81
112
|
name: 'Castro 2'
|
82
113
|
category: 'Service Agent'
|
@@ -181,6 +212,13 @@
|
|
181
212
|
name: 'Blogtrottr Ltd'
|
182
213
|
url: 'https://blogtrottr.com/'
|
183
214
|
|
215
|
+
- regex: 'BoardReader Blog Indexer'
|
216
|
+
name: 'BoardReader Blog Indexer'
|
217
|
+
category: 'Crawler'
|
218
|
+
producer:
|
219
|
+
name: 'BoardReader'
|
220
|
+
url: 'http://boardreader.com/'
|
221
|
+
|
184
222
|
- regex: 'BountiiBot'
|
185
223
|
name: 'Bountii Bot'
|
186
224
|
category: 'Search bot'
|
@@ -253,13 +291,13 @@
|
|
253
291
|
name: 'CloudFlare'
|
254
292
|
url: 'http://www.cloudflare.com'
|
255
293
|
|
256
|
-
- regex: 'coccoc
|
294
|
+
- regex: 'coccoc|coccocbot(-ads|-fast|-image|-shopping|-web)?'
|
257
295
|
name: 'Cốc Cốc Bot'
|
258
|
-
url: '
|
296
|
+
url: 'https://help.coccoc.com/en/search-engine/coccoc-robots'
|
259
297
|
category: 'Search bot'
|
260
298
|
producer:
|
261
299
|
name: 'Cốc Cốc'
|
262
|
-
url: '
|
300
|
+
url: 'https://coccoc.com/'
|
263
301
|
|
264
302
|
- regex: 'collectd'
|
265
303
|
name: 'Collectd'
|
@@ -293,6 +331,15 @@
|
|
293
331
|
name: 'Datadog'
|
294
332
|
url: 'https://www.datadoghq.com/'
|
295
333
|
|
334
|
+
- regex: 'Datanyze'
|
335
|
+
name: 'Datanyze'
|
336
|
+
url: ''
|
337
|
+
category: 'Crawler'
|
338
|
+
producer:
|
339
|
+
name: 'Datanyze'
|
340
|
+
url: 'https://www.datanyze.com'
|
341
|
+
|
342
|
+
|
296
343
|
- regex: 'Dataprovider'
|
297
344
|
name: 'Dataprovider'
|
298
345
|
category: 'Crawler'
|
@@ -341,7 +388,7 @@
|
|
341
388
|
name: 'SEOmoz, Inc.'
|
342
389
|
url: 'http://moz.com/'
|
343
390
|
|
344
|
-
- regex: 'DuckDuck'
|
391
|
+
- regex: 'DuckDuck(?:Go-Favicons-)?Bot'
|
345
392
|
name: 'DuckDuckGo Bot'
|
346
393
|
category: 'Search bot'
|
347
394
|
url: 'https://duckduckgo.com/duckduckbot'
|
@@ -357,6 +404,13 @@
|
|
357
404
|
name: 'easou ICP'
|
358
405
|
url: 'http://www.easou.com'
|
359
406
|
|
407
|
+
- regex: 'eCairn-Grabber'
|
408
|
+
name: 'eCairn-Grabber'
|
409
|
+
category: 'Crawler'
|
410
|
+
producer:
|
411
|
+
name: 'eCairn'
|
412
|
+
url: 'https://ecairn.com'
|
413
|
+
|
360
414
|
- regex: 'EMail Exractor'
|
361
415
|
name: 'EMail Exractor'
|
362
416
|
category: 'Crawler'
|
@@ -397,7 +451,7 @@
|
|
397
451
|
name: 'SEOmoz, Inc.'
|
398
452
|
url: 'http://moz.com/'
|
399
453
|
|
400
|
-
- regex: 'facebookexternalhit|facebookplatform'
|
454
|
+
- regex: 'facebookexternalhit|facebookplatform|facebookexternalua'
|
401
455
|
name: 'Facebook External Hit'
|
402
456
|
category: 'Social Media Agent'
|
403
457
|
url: 'https://www.facebook.com/externalhit_uatext.php'
|
@@ -466,6 +520,11 @@
|
|
466
520
|
category: 'Crawler'
|
467
521
|
url: 'http://www.findxbot.com'
|
468
522
|
|
523
|
+
- regex: 'FreshRSS'
|
524
|
+
name: 'FreshRSS'
|
525
|
+
category: 'Feed Fetcher'
|
526
|
+
url: 'https://freshrss.org/'
|
527
|
+
|
469
528
|
- regex: 'Genieo'
|
470
529
|
name: 'Genieo Web filter'
|
471
530
|
category: ''
|
@@ -498,6 +557,18 @@
|
|
498
557
|
name: 'NTT Resonant'
|
499
558
|
url: 'http://goo.ne.jp'
|
500
559
|
|
560
|
+
- regex: 'Google Favicon'
|
561
|
+
name: 'Google Favicon'
|
562
|
+
category: 'Crawler'
|
563
|
+
|
564
|
+
- regex: 'Google Search Console'
|
565
|
+
name: 'Google Search Console'
|
566
|
+
category: 'Crawler'
|
567
|
+
url: 'https://search.google.com/search-console/about'
|
568
|
+
producer:
|
569
|
+
name: 'Google Inc.'
|
570
|
+
url: 'http://www.google.com'
|
571
|
+
|
501
572
|
- regex: 'Google Page Speed Insights'
|
502
573
|
name: 'Google PageSpeed Insights'
|
503
574
|
category: 'Site Monitor'
|
@@ -514,6 +585,14 @@
|
|
514
585
|
name: 'Google Inc.'
|
515
586
|
url: 'http://www.google.com'
|
516
587
|
|
588
|
+
- regex: 'Google-Cloud-Scheduler'
|
589
|
+
name: 'Google Cloud Scheduler'
|
590
|
+
category: 'Crawler'
|
591
|
+
url: 'https://cloud.google.com/scheduler'
|
592
|
+
producer:
|
593
|
+
name: 'Google Inc.'
|
594
|
+
url: 'https://www.google.com'
|
595
|
+
|
517
596
|
- regex: 'Google-Structured-Data-Testing-Tool'
|
518
597
|
name: 'Google Structured Data Testing Tool'
|
519
598
|
category: 'Validator'
|
@@ -522,6 +601,14 @@
|
|
522
601
|
name: 'Google Inc.'
|
523
602
|
url: 'http://www.google.com'
|
524
603
|
|
604
|
+
- regex: 'GoogleStackdriverMonitoring'
|
605
|
+
name: 'Google Stackdriver Monitoring'
|
606
|
+
category: 'Site Monitor'
|
607
|
+
url: 'https://cloud.google.com/monitoring'
|
608
|
+
producer:
|
609
|
+
name: 'Google Inc.'
|
610
|
+
url: 'https://www.google.com'
|
611
|
+
|
525
612
|
- regex: 'via ggpht\.com GoogleImageProxy'
|
526
613
|
name: 'Gmail Image Proxy'
|
527
614
|
category: 'Crawler'
|
@@ -529,7 +616,7 @@
|
|
529
616
|
producer:
|
530
617
|
name: 'Google Inc.'
|
531
618
|
url: 'http://www.google.com'
|
532
|
-
|
619
|
+
|
533
620
|
- regex: 'SeznamEmailProxy'
|
534
621
|
name: 'Seznam Email Proxy'
|
535
622
|
category: 'Crawler'
|
@@ -562,7 +649,7 @@
|
|
562
649
|
name: 'Visual Meta'
|
563
650
|
url: 'https://www.shopalike.cz/'
|
564
651
|
|
565
|
-
- regex: '
|
652
|
+
- regex: 'AdsBot-Google(-Mobile)?|Adwords-(DisplayAds|Express|Instant)|Google Web Preview|Google[ -]Publisher[ -]Plugin|Google-(Adwords|AMPHTML|Assess|HotelAdsVerifier|Read-Aloud|Shopping-Quality|Site-Verification|speakr|Test|Youtube-Links)|(APIs|DuplexWeb|Feedfetcher|Mediapartners)-Google|Googlebot(-Mobile|-Image|-Video|-News)?|GoogleProducer|Google.*/\+/web/snippet'
|
566
653
|
name: 'Googlebot'
|
567
654
|
category: 'Search bot'
|
568
655
|
url: 'http://www.google.com/bot.html'
|
@@ -602,6 +689,11 @@
|
|
602
689
|
name: ''
|
603
690
|
url: ''
|
604
691
|
|
692
|
+
- regex: 'inoreader.com'
|
693
|
+
name: 'inoreader'
|
694
|
+
category: 'Feed Reader'
|
695
|
+
url: 'https://www.inoreader.com'
|
696
|
+
|
605
697
|
- regex: 'iisbot'
|
606
698
|
name: 'IIS Site Analysis'
|
607
699
|
category: 'Crawler'
|
@@ -704,6 +796,10 @@
|
|
704
796
|
name: 'Robert Graham'
|
705
797
|
url: 'https://github.com/robertdavidgraham'
|
706
798
|
|
799
|
+
- regex: 'Mastodon/'
|
800
|
+
name: 'Mastodon Bot'
|
801
|
+
category: 'Social Media Agent'
|
802
|
+
|
707
803
|
- regex: 'meanpathbot'
|
708
804
|
name: 'Meanpath Bot'
|
709
805
|
category: 'Search bot'
|
@@ -780,6 +876,10 @@
|
|
780
876
|
name: 'Nagios Plugins Development Team'
|
781
877
|
url: 'https://nagios.org'
|
782
878
|
|
879
|
+
- regex: 'nbertaupete95\(at\)gmail.com'
|
880
|
+
name: 'nbertaupete95'
|
881
|
+
category: 'Crawler'
|
882
|
+
|
783
883
|
- regex: 'Netcraft( Web Server Survey| SSL Server Survey|SurveyAgent)'
|
784
884
|
name: 'Netcraft Survey Bot'
|
785
885
|
category: 'Search bot'
|
@@ -790,7 +890,7 @@
|
|
790
890
|
|
791
891
|
- regex: 'netEstate NE Crawler'
|
792
892
|
name: 'netEstate'
|
793
|
-
category: '
|
893
|
+
category: 'Crawler'
|
794
894
|
url: 'http://www.website-datenbank.de/Impressum'
|
795
895
|
producer:
|
796
896
|
name: 'netEstate GmbH'
|
@@ -836,10 +936,17 @@
|
|
836
936
|
name: 'Nmap'
|
837
937
|
url: 'https://nmap.org/'
|
838
938
|
|
939
|
+
- regex: 'Nuzzel'
|
940
|
+
name: 'Nuzzel'
|
941
|
+
category: 'Crawler'
|
942
|
+
producer:
|
943
|
+
name: 'Nuzzel'
|
944
|
+
url: https://www.nuzzel.com/
|
945
|
+
|
839
946
|
- regex: 'Octopus [0-9]'
|
840
947
|
name: 'Octopus'
|
841
948
|
|
842
|
-
- regex: '
|
949
|
+
- regex: 'omgili(?:bot)?'
|
843
950
|
name: 'Omgili bot'
|
844
951
|
category: 'Search bot'
|
845
952
|
url: 'http://www.omgili.com/Crawler.html'
|
@@ -931,7 +1038,15 @@
|
|
931
1038
|
producer:
|
932
1039
|
name: 'Pingdom AB'
|
933
1040
|
url: 'https://www.pingdom.com'
|
934
|
-
|
1041
|
+
|
1042
|
+
- regex: 'Quora Link Preview'
|
1043
|
+
name: 'Quora Link Preview'
|
1044
|
+
category: 'Crawler'
|
1045
|
+
url: ''
|
1046
|
+
producer:
|
1047
|
+
name: 'Quora'
|
1048
|
+
url: 'http://www.quora.com'
|
1049
|
+
|
935
1050
|
- regex: 'RamblerMail'
|
936
1051
|
name: 'RamblerMail Image Proxy'
|
937
1052
|
category: 'Crawler'
|
@@ -1075,6 +1190,14 @@
|
|
1075
1190
|
name: 'Seznam.cz, a.s.'
|
1076
1191
|
url: 'http://www.seznam.cz/'
|
1077
1192
|
|
1193
|
+
- regex: 'shopify-partner-homepage-scraper'
|
1194
|
+
name: 'Shopify Partner'
|
1195
|
+
category: 'Crawler'
|
1196
|
+
url: 'https://www.shopify.com/partners'
|
1197
|
+
producer:
|
1198
|
+
name: 'Shopify'
|
1199
|
+
url: 'https://www.shopify.com/'
|
1200
|
+
|
1078
1201
|
- regex: 'ShopWiki'
|
1079
1202
|
name: 'ShopWiki'
|
1080
1203
|
category: 'Search tools'
|
@@ -1107,6 +1230,14 @@
|
|
1107
1230
|
name: 'SISTRIX GmbH'
|
1108
1231
|
url: 'http://www.sistrix.de'
|
1109
1232
|
|
1233
|
+
- regex: 'compatible; (?:SISTRIX )?Optimizer'
|
1234
|
+
name: 'SISTRIX Optimizer'
|
1235
|
+
category: 'Crawler'
|
1236
|
+
url: 'https://optimizer.sistrix.com'
|
1237
|
+
producer:
|
1238
|
+
name: 'SISTRIX GmbH'
|
1239
|
+
url: 'http://www.sistrix.de'
|
1240
|
+
|
1110
1241
|
- regex: 'SiteSucker'
|
1111
1242
|
name: 'SiteSucker'
|
1112
1243
|
category: 'Crawler'
|
@@ -1211,7 +1342,7 @@
|
|
1211
1342
|
category: 'Search bot'
|
1212
1343
|
|
1213
1344
|
- regex: 'TelegramBot'
|
1214
|
-
name: '
|
1345
|
+
name: 'TelegramBot'
|
1215
1346
|
url: 'https://telegram.org/blog/bot-revolution'
|
1216
1347
|
|
1217
1348
|
- regex: 'TLSProbe'
|
@@ -1238,6 +1369,11 @@
|
|
1238
1369
|
name: ''
|
1239
1370
|
url: ''
|
1240
1371
|
|
1372
|
+
- regex: 'theoldreader.com'
|
1373
|
+
name: 'theoldreader'
|
1374
|
+
category: 'Feed Reader'
|
1375
|
+
url: 'https://theoldreader.com'
|
1376
|
+
|
1241
1377
|
- regex: 'trendictionbot'
|
1242
1378
|
name: 'Trendiction Bot'
|
1243
1379
|
category: 'Crawler'
|
@@ -1270,6 +1406,13 @@
|
|
1270
1406
|
name: 'Mediasift'
|
1271
1407
|
url: ''
|
1272
1408
|
|
1409
|
+
- regex: 'Twingly Recon'
|
1410
|
+
name: 'Twingly Recon'
|
1411
|
+
category: 'Crawler'
|
1412
|
+
producer:
|
1413
|
+
name: 'Twingly'
|
1414
|
+
url: 'https://www.twingly.com'
|
1415
|
+
|
1273
1416
|
- regex: 'Twitterbot'
|
1274
1417
|
name: 'Twitterbot'
|
1275
1418
|
category: 'Social Media Agent'
|
@@ -1326,6 +1469,14 @@
|
|
1326
1469
|
name: 'WiseGuys'
|
1327
1470
|
url: 'http://www.wise-guys.nl/'
|
1328
1471
|
|
1472
|
+
- regex: 'vkShare; '
|
1473
|
+
name: 'VK Share Button'
|
1474
|
+
category: 'Crawler'
|
1475
|
+
url: 'http://vk.com/dev/Share'
|
1476
|
+
producer:
|
1477
|
+
name: 'VK'
|
1478
|
+
url: 'http://vk.com/'
|
1479
|
+
|
1329
1480
|
- regex: 'VSMCrawler'
|
1330
1481
|
name: 'Visual Site Mapper Crawler'
|
1331
1482
|
category: 'Crawler'
|
@@ -1389,6 +1540,11 @@
|
|
1389
1540
|
name: 'AliasIO'
|
1390
1541
|
url: 'https://github.com/AliasIO'
|
1391
1542
|
|
1543
|
+
- regex: 'PTST/'
|
1544
|
+
name: 'WebPageTest'
|
1545
|
+
category: 'Site Monitor'
|
1546
|
+
url: 'https://www.webpagetest.org'
|
1547
|
+
|
1392
1548
|
- regex: 'WeSEE(:Search)?'
|
1393
1549
|
name: 'WeSEE:Search'
|
1394
1550
|
category: 'Search bot'
|
@@ -1429,6 +1585,14 @@
|
|
1429
1585
|
name: 'Wotbox'
|
1430
1586
|
url: 'http://www.wotbox.com'
|
1431
1587
|
|
1588
|
+
- regex: 'XenForo'
|
1589
|
+
name: 'XenForo'
|
1590
|
+
category: 'Service Agent'
|
1591
|
+
url: 'https://xenforo.com/'
|
1592
|
+
producer:
|
1593
|
+
name: 'XenForo Ltd.'
|
1594
|
+
url: 'https://xenforo.com/'
|
1595
|
+
|
1432
1596
|
- regex: 'yacybot'
|
1433
1597
|
name: 'YaCy'
|
1434
1598
|
category: 'Search bot'
|
@@ -1461,7 +1625,15 @@
|
|
1461
1625
|
name: 'Yahoo! Inc.'
|
1462
1626
|
url: 'http://www.yahoo.com'
|
1463
1627
|
|
1464
|
-
- regex: '
|
1628
|
+
- regex: 'Y!J-BRW'
|
1629
|
+
name: 'Yahoo! Japan BRW'
|
1630
|
+
category: 'Crawler'
|
1631
|
+
url: 'https://www.yahoo-help.jp/app/answers/detail/p/595/a_id/42716/~/ウェブページにアクセスするシステムのユーザーエージェントについて'
|
1632
|
+
producer:
|
1633
|
+
name: 'Yahoo! Japan Corp.'
|
1634
|
+
url: 'https://www.yahoo.co.jp/'
|
1635
|
+
|
1636
|
+
- regex: 'Yandex(SpravBot|ScreenshotBot|MobileBot|AccessibilityBot|ForDomain|Vertis|Market|Catalog|Calendar|Sitelinks|AdNet|Pagechecker|Webmaster|Media|Video|Bot|Images|Antivirus|Direct|Blogs|Favicons|ImageResizer|Verticals|News(links)?|Metrika|\.Gazeta Bot)|YaDirectFetcher|YandexTurbo|YandexTracker|YandexSearchShop|YandexRCA|YandexPartner|YandexOntoDBAPI|YandexOntoDB|YandexMobileScreenShotBot'
|
1465
1637
|
name: 'Yandex Bot'
|
1466
1638
|
category: 'Search bot'
|
1467
1639
|
url: 'http://www.yandex.com/bots'
|
@@ -1469,7 +1641,7 @@
|
|
1469
1641
|
name: 'Yandex LLC'
|
1470
1642
|
url: 'http://company.yandex.com'
|
1471
1643
|
|
1472
|
-
- regex: 'Yeti'
|
1644
|
+
- regex: 'Yeti|NaverJapan'
|
1473
1645
|
name: 'Yeti/Naverbot'
|
1474
1646
|
category: 'Search bot'
|
1475
1647
|
url: 'http://help.naver.com/robots/'
|
@@ -1551,9 +1723,9 @@
|
|
1551
1723
|
name: 'HubPages'
|
1552
1724
|
url: 'http://hubpages.com/'
|
1553
1725
|
|
1554
|
-
- regex: 'Pinterest
|
1726
|
+
- regex: 'Pinterest(bot)?/\d\.\d.*www\.pinterest\.com.*'
|
1555
1727
|
name: 'Pinterest'
|
1556
|
-
url: ''
|
1728
|
+
url: 'http://www.pinterest.com/bot.html'
|
1557
1729
|
category: 'Crawler'
|
1558
1730
|
producer:
|
1559
1731
|
name: 'Pinterest'
|
@@ -1567,6 +1739,14 @@
|
|
1567
1739
|
name: 'Site24x7'
|
1568
1740
|
url: 'https://www.site24x7.com'
|
1569
1741
|
|
1742
|
+
- regex: 's~snapchat-proxy'
|
1743
|
+
name: 'Snapchat Proxy'
|
1744
|
+
category: 'Crawler'
|
1745
|
+
url: 'https://www.snapchat.com'
|
1746
|
+
producer:
|
1747
|
+
name: 'Snapchat Inc.'
|
1748
|
+
url: 'https://www.snapchat.com'
|
1749
|
+
|
1570
1750
|
- regex: "Let's Encrypt validation server"
|
1571
1751
|
name: "Let's Encrypt Validation"
|
1572
1752
|
category: 'Service Agent'
|
@@ -1662,7 +1842,10 @@
|
|
1662
1842
|
- regex: 'Server Density Service Monitoring.*'
|
1663
1843
|
name: 'Server Density'
|
1664
1844
|
|
1665
|
-
- regex: '
|
1845
|
+
- regex: 'RSSRadio \(Push Notification Scanner;support@dorada\.co\.uk\)'
|
1846
|
+
name: 'RSSRadio Bot'
|
1847
|
+
|
1848
|
+
- regex: '(A6-Indexer|nuhk|TsolCrawler|Yammybot|Openbot|Gulper Web Bot|grub-client|Download Demon|SearchExpress|Microsoft URL Control|borg|altavista|dataminr.com|tweetedtimes.com|TrendsmapResolver|teoma|blitzbot|oegp|furlbot|http%20client|polybot|htdig|mogimogi|larbin|scrubby|searchsight|seekbot|semanticdiscovery|snappy|vortex(?! Build)|zeal|fast-webcrawler|converacrawler|dataparksearch|findlinks|BrowserMob|HttpMonitor|ThumbShotsBot|URL2PNG|ZooShot|GomezA|Google SketchUp|Read%20Later|RackspaceBot|robots|SeopultContentAnalyzer|7Siters|centuryb.o.t9)'
|
1666
1849
|
name: 'Generic Bot'
|
1667
1850
|
|
1668
1851
|
- regex: '^sentry'
|
@@ -1671,7 +1854,191 @@
|
|
1671
1854
|
name: 'Sentry'
|
1672
1855
|
url: 'https://sentry.io'
|
1673
1856
|
|
1674
|
-
|
1857
|
+
- regex: '^Spotify'
|
1858
|
+
name: 'Spotify'
|
1859
|
+
producer:
|
1860
|
+
name: 'Spotify'
|
1861
|
+
url: 'https://www.spotify.com'
|
1862
|
+
|
1863
|
+
- regex: 'The Knowledge AI'
|
1864
|
+
name: 'The Knowledge AI'
|
1865
|
+
category: 'Crawler'
|
1866
|
+
|
1867
|
+
- regex: 'Embedly'
|
1868
|
+
name: 'Embedly'
|
1869
|
+
category: 'Crawler'
|
1870
|
+
url: 'https://support.embed.ly/hc/en-us'
|
1871
|
+
producer:
|
1872
|
+
name: 'A Medium, Corp.'
|
1873
|
+
url: 'https://medium.com/'
|
1874
|
+
|
1875
|
+
- regex: 'BrandVerity'
|
1876
|
+
name: 'BrandVerity'
|
1877
|
+
category: 'Crawler'
|
1878
|
+
url: 'https://www.brandverity.com/why-is-brandverity-visiting-me'
|
1879
|
+
producer:
|
1880
|
+
name: 'BrandVerity, Inc.'
|
1881
|
+
url: 'https://www.brandverity.com/'
|
1882
|
+
|
1883
|
+
- regex: 'Kaspersky Lab CFR link resolver'
|
1884
|
+
name: 'Kaspersky'
|
1885
|
+
category: 'Security Checker'
|
1886
|
+
url: 'https://www.kaspersky.com/'
|
1887
|
+
producer:
|
1888
|
+
name: 'AO Kaspersky Lab'
|
1889
|
+
url: 'https://www.kaspersky.com/'
|
1890
|
+
|
1891
|
+
- regex: 'eZ Publish Link Validator'
|
1892
|
+
name: 'eZ Publish Link Validator'
|
1893
|
+
category: 'Crawler'
|
1894
|
+
url: 'https://ez.no/'
|
1895
|
+
producer:
|
1896
|
+
name: 'eZ Systems AS'
|
1897
|
+
url: 'https://ez.no/'
|
1898
|
+
|
1899
|
+
- regex: 'woorankreview'
|
1900
|
+
name: 'WooRank'
|
1901
|
+
category: 'Search bot'
|
1902
|
+
url: 'https://www.woorank.com/'
|
1903
|
+
producer:
|
1904
|
+
name: 'WooRank sprl'
|
1905
|
+
url: 'https://www.woorank.com/'
|
1906
|
+
|
1907
|
+
- regex: '(Match|LinkCheck) by Siteimprove.com'
|
1908
|
+
name: 'Siteimprove'
|
1909
|
+
category: 'Search bot'
|
1910
|
+
url: 'https://siteimprove.com/'
|
1911
|
+
producer:
|
1912
|
+
name: 'Siteimprove GmbH'
|
1913
|
+
url: 'https://siteimprove.com/'
|
1914
|
+
|
1915
|
+
- regex: 'CATExplorador'
|
1916
|
+
name: 'CATExplorador'
|
1917
|
+
category: 'Search bot'
|
1918
|
+
url: 'https://fundacio.cat/ca/domini/'
|
1919
|
+
producer:
|
1920
|
+
name: 'Fundació puntCAT'
|
1921
|
+
url: 'https://fundacio.cat/ca/domini/'
|
1922
|
+
|
1923
|
+
- regex: 'Buck'
|
1924
|
+
name: 'Buck'
|
1925
|
+
category: 'Search bot'
|
1926
|
+
url: 'https://hypefactors.com/'
|
1927
|
+
producer:
|
1928
|
+
name: 'Hypefactors A/S'
|
1929
|
+
url: 'https://hypefactors.com/'
|
1930
|
+
|
1931
|
+
- regex: 'tracemyfile'
|
1932
|
+
name: 'TraceMyFile'
|
1933
|
+
category: 'Search bot'
|
1934
|
+
url: 'https://www.tracemyfile.com/'
|
1935
|
+
producer:
|
1936
|
+
name: 'Idee Inc.'
|
1937
|
+
url: 'http://ideeinc.com/'
|
1938
|
+
|
1939
|
+
- regex: 'zelist.ro feed parser'
|
1940
|
+
name: 'Ze List'
|
1941
|
+
url: 'https://www.zelist.ro/'
|
1942
|
+
category: 'Feed Fetcher'
|
1943
|
+
producer:
|
1944
|
+
name: 'Treeworks SRL'
|
1945
|
+
url: 'https://www.tree.ro/'
|
1946
|
+
|
1947
|
+
- regex: 'weborama-fetcher'
|
1948
|
+
name: 'Weborama'
|
1949
|
+
category: 'Search bot'
|
1950
|
+
url: 'https://weborama.com/'
|
1951
|
+
producer:
|
1952
|
+
name: 'Weborama SA'
|
1953
|
+
url: 'https://weborama.com/'
|
1954
|
+
|
1955
|
+
- regex: 'BoardReader Favicon Fetcher'
|
1956
|
+
name: 'BoardReader'
|
1957
|
+
category: 'Search bot'
|
1958
|
+
url: 'http://boardreader.com/'
|
1959
|
+
producer:
|
1960
|
+
name: 'Effyis Inc'
|
1961
|
+
url: 'http://boardreader.com/'
|
1962
|
+
|
1963
|
+
- regex: 'IDG/IT'
|
1964
|
+
name: 'IDG/IT'
|
1965
|
+
category: 'Search bot'
|
1966
|
+
url: 'https://spaziodati.eu/'
|
1967
|
+
producer:
|
1968
|
+
name: 'SpazioDati S.r.l.'
|
1969
|
+
url: 'https://spaziodati.eu/'
|
1970
|
+
|
1971
|
+
- regex: 'Bytespider'
|
1972
|
+
name: 'Bytespider'
|
1973
|
+
category: 'Search bot'
|
1974
|
+
url: 'https://bytedance.com/'
|
1975
|
+
producer:
|
1976
|
+
name: 'ByteDance Ltd.'
|
1977
|
+
url: 'https://bytedance.com/'
|
1978
|
+
|
1979
|
+
- regex: 'WikiDo'
|
1980
|
+
name: 'WikiDo'
|
1981
|
+
category: 'Search bot'
|
1982
|
+
url: 'https://www.wikido.com/'
|
1983
|
+
producer:
|
1984
|
+
name: 'Fotolitografie Fiorentine di Becchi Antonio s.n.c.'
|
1985
|
+
url: 'https://www.wikido.com/'
|
1986
|
+
|
1987
|
+
- regex: 'AwarioSmartBot'
|
1988
|
+
name: 'Awario'
|
1989
|
+
category: 'Search bot'
|
1990
|
+
url: 'https://awario.com/bots.html'
|
1991
|
+
producer:
|
1992
|
+
name: 'Awario'
|
1993
|
+
url: 'https://awario.com/'
|
1994
|
+
|
1995
|
+
- regex: 'AwarioRssBot'
|
1996
|
+
name: 'Awario'
|
1997
|
+
category: 'Feed Fetcher'
|
1998
|
+
url: 'https://awario.com/bots.html'
|
1999
|
+
producer:
|
2000
|
+
name: 'Awario'
|
2001
|
+
url: 'https://awario.com/'
|
2002
|
+
|
2003
|
+
- regex: 'oBot'
|
2004
|
+
name: 'oBot'
|
2005
|
+
category: 'Search bot'
|
2006
|
+
url: 'http://www.xforce-security.com/crawler/'
|
2007
|
+
producer:
|
2008
|
+
name: 'IBM Germany Research & Development GmbH'
|
2009
|
+
url: 'https://exchange.xforce.ibmcloud.com/'
|
2010
|
+
|
2011
|
+
- regex: 'SMTBot'
|
2012
|
+
name: 'SMTBot'
|
2013
|
+
category: 'Search bot'
|
2014
|
+
url: 'https://www.similartech.com/smtbot'
|
2015
|
+
producer:
|
2016
|
+
name: 'SimilarTech Ltd.'
|
2017
|
+
url: 'https://www.similartech.com/'
|
2018
|
+
|
2019
|
+
- regex: 'LCC'
|
2020
|
+
name: 'LCC'
|
2021
|
+
category: 'Search bot'
|
2022
|
+
url: 'https://corpora.uni-leipzig.de/crawler_faq.html'
|
2023
|
+
producer:
|
2024
|
+
name: 'Universität Leipzig'
|
2025
|
+
url: 'https://www.uni-leipzig.de/'
|
2026
|
+
|
2027
|
+
- regex: 'Startpagina-Linkchecker'
|
2028
|
+
name: 'Startpagina Linkchecker'
|
2029
|
+
category: 'Search bot'
|
2030
|
+
url: 'https://www.startpagina.nl/linkchecker'
|
2031
|
+
producer:
|
2032
|
+
name: 'Startpagina B.V.'
|
2033
|
+
url: 'https://www.startpagina.nl/'
|
2034
|
+
|
2035
|
+
- regex: 'GTmetrix'
|
2036
|
+
name: 'GTmetrix'
|
2037
|
+
category: 'Crawler'
|
2038
|
+
url: 'https://gtmetrix.com/'
|
2039
|
+
producer:
|
2040
|
+
name: 'Carbon60 Operating Co. Ltd.'
|
2041
|
+
url: 'https://www.carbon60.com/'
|
1675
2042
|
|
1676
2043
|
- regex: 'Nutch'
|
1677
2044
|
name: 'Nutch-based Bot'
|
@@ -1681,5 +2048,61 @@
|
|
1681
2048
|
name: 'The Apache Software Foundation'
|
1682
2049
|
url: 'http://www.apache.org/foundation/'
|
1683
2050
|
|
1684
|
-
- regex: '
|
2051
|
+
- regex: 'Seobility'
|
2052
|
+
name: 'Seobility'
|
2053
|
+
category: 'Crawler'
|
2054
|
+
url: 'https://www.seobility.net/en/faq/?category=crawling#!aboutourbot'
|
2055
|
+
|
2056
|
+
- regex: 'Vercelbot'
|
2057
|
+
name: 'Vercel Bot'
|
2058
|
+
category: 'Service bot'
|
2059
|
+
url: 'https://vercel.com'
|
2060
|
+
|
2061
|
+
- regex: 'Grammarly'
|
2062
|
+
name: 'Grammarly'
|
2063
|
+
category: 'Service bot'
|
2064
|
+
url: 'http://www.grammarly.com'
|
2065
|
+
|
2066
|
+
- regex: 'Robozilla'
|
2067
|
+
name: 'Robozilla'
|
2068
|
+
category: 'Crawler'
|
2069
|
+
|
2070
|
+
- regex: 'Domains Project'
|
2071
|
+
name: 'Domains Project'
|
2072
|
+
category: 'Crawler'
|
2073
|
+
url: 'https://domainsproject.org'
|
2074
|
+
|
2075
|
+
- regex: 'PetalBot'
|
2076
|
+
name: 'Petal Bot'
|
2077
|
+
category: 'Crawler'
|
2078
|
+
url: 'https://aspiegel.com/petalbot'
|
2079
|
+
|
2080
|
+
- regex: 'SerendeputyBot'
|
2081
|
+
name: 'Serendeputy Bot'
|
2082
|
+
category: 'Crawler'
|
2083
|
+
url: 'http://serendeputy.com/about/serendeputy-bot'
|
2084
|
+
|
2085
|
+
- regex: 'ias-va.*admantx.*service-fetcher'
|
2086
|
+
name: 'ADmantX Service Fetcher'
|
2087
|
+
category: 'Service bot'
|
2088
|
+
url: 'https://www.admantx.com/service-fetcher.html'
|
2089
|
+
|
2090
|
+
- regex: 'SemanticScholarBot'
|
2091
|
+
name: 'Semantic Scholar Bot'
|
2092
|
+
category: 'Crawler'
|
2093
|
+
url: 'https://www.semanticscholar.org/crawler'
|
2094
|
+
|
2095
|
+
- regex: 'VelenPublicWebCrawler'
|
2096
|
+
name: 'Velen Public Web Crawler'
|
2097
|
+
category: 'Crawler'
|
2098
|
+
url: 'https://hunter.io/robot'
|
2099
|
+
|
2100
|
+
- regex: 'Barkrowler'
|
2101
|
+
name: 'Barkrowler'
|
2102
|
+
category: 'Crawler'
|
2103
|
+
url: 'http://www.exensa.com/crawl'
|
2104
|
+
|
2105
|
+
# Generic detections
|
2106
|
+
|
2107
|
+
- regex: '[a-z0-9\-_]*((?<!cu|power[ _]|m[ _])bot(?![ _]TAB|[ _]?5[0-9])|crawler|crawl|checker|archiver|transcoder|spider)([^a-z]|$)'
|
1685
2108
|
name: 'Generic Bot'
|