crawler_detect 0.1.11 → 0.1.12
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.travis.yml +1 -1
- data/Gemfile.lock +81 -0
- data/lib/crawler_detect/library/crawlers.rb +32 -8
- data/lib/crawler_detect/version.rb +1 -1
- metadata +3 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: f6e03716868421dc64e5acb715b35599776fbe3951bbeb7e462892ed3a6a51d6
|
|
4
|
+
data.tar.gz: 10b00a68949482af5cb6064f538e0829f2bcb836fe5605da48b48f0af7bbad71
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: cb66a7c310ca791038ca199c68626d522f99cb4ddff57382b07ecb91b824e44292362351ccb71622051ece1d8c7a900019627fed731e46f5474507b8b20f6aaa
|
|
7
|
+
data.tar.gz: 3f4c2484f4155d975915dd21e1c62d6f8dd19ddda4023cff9530701cf628ddf94c10f5e097c3cb85ffbf3d71686bd91d9b9ac71da59cf47933549fd847d2c350
|
data/.travis.yml
CHANGED
|
@@ -8,9 +8,9 @@ env:
|
|
|
8
8
|
- "TEST_GROUP=3"
|
|
9
9
|
- "TEST_GROUP=4"
|
|
10
10
|
rvm:
|
|
11
|
-
- 2.3
|
|
12
11
|
- 2.5
|
|
13
12
|
- 2.6
|
|
13
|
+
- 2.7
|
|
14
14
|
before_install: gem install bundler
|
|
15
15
|
script:
|
|
16
16
|
- bundle exec parallel_rspec spec/ -n 4 --only-group $TEST_GROUP --group-by runtime --runtime-log spec/fixtures/parallel_runtime_rspec.log
|
data/Gemfile.lock
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
1
|
+
PATH
|
|
2
|
+
remote: .
|
|
3
|
+
specs:
|
|
4
|
+
crawler_detect (0.1.11)
|
|
5
|
+
|
|
6
|
+
GEM
|
|
7
|
+
remote: https://rubygems.org/
|
|
8
|
+
specs:
|
|
9
|
+
activesupport (5.2.4.2)
|
|
10
|
+
concurrent-ruby (~> 1.0, >= 1.0.2)
|
|
11
|
+
i18n (>= 0.7, < 2)
|
|
12
|
+
minitest (~> 5.1)
|
|
13
|
+
tzinfo (~> 1.1)
|
|
14
|
+
awesome_print (1.8.0)
|
|
15
|
+
byebug (11.1.2)
|
|
16
|
+
coderay (1.1.2)
|
|
17
|
+
concurrent-ruby (1.1.6)
|
|
18
|
+
diff-lcs (1.3)
|
|
19
|
+
fuubar (2.5.0)
|
|
20
|
+
rspec-core (~> 3.0)
|
|
21
|
+
ruby-progressbar (~> 1.4)
|
|
22
|
+
i18n (1.8.2)
|
|
23
|
+
concurrent-ruby (~> 1.0)
|
|
24
|
+
method_source (1.0.0)
|
|
25
|
+
minitest (5.14.0)
|
|
26
|
+
parallel (1.19.1)
|
|
27
|
+
parallel_tests (2.32.0)
|
|
28
|
+
parallel
|
|
29
|
+
pry (0.13.1)
|
|
30
|
+
coderay (~> 1.1)
|
|
31
|
+
method_source (~> 1.0)
|
|
32
|
+
pry-byebug (3.9.0)
|
|
33
|
+
byebug (~> 11.0)
|
|
34
|
+
pry (~> 0.13.0)
|
|
35
|
+
pry-meta (0.0.10)
|
|
36
|
+
awesome_print
|
|
37
|
+
pry
|
|
38
|
+
pry-byebug
|
|
39
|
+
pry-remote
|
|
40
|
+
pry-remote (0.1.8)
|
|
41
|
+
pry (~> 0.9)
|
|
42
|
+
slop (~> 3.0)
|
|
43
|
+
rack (2.2.2)
|
|
44
|
+
rack-test (1.1.0)
|
|
45
|
+
rack (>= 1.0, < 3)
|
|
46
|
+
rake (13.0.1)
|
|
47
|
+
rspec (3.9.0)
|
|
48
|
+
rspec-core (~> 3.9.0)
|
|
49
|
+
rspec-expectations (~> 3.9.0)
|
|
50
|
+
rspec-mocks (~> 3.9.0)
|
|
51
|
+
rspec-core (3.9.1)
|
|
52
|
+
rspec-support (~> 3.9.1)
|
|
53
|
+
rspec-expectations (3.9.1)
|
|
54
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
|
55
|
+
rspec-support (~> 3.9.0)
|
|
56
|
+
rspec-mocks (3.9.1)
|
|
57
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
|
58
|
+
rspec-support (~> 3.9.0)
|
|
59
|
+
rspec-support (3.9.2)
|
|
60
|
+
ruby-progressbar (1.10.1)
|
|
61
|
+
slop (3.6.0)
|
|
62
|
+
thread_safe (0.3.6)
|
|
63
|
+
tzinfo (1.2.7)
|
|
64
|
+
thread_safe (~> 0.1)
|
|
65
|
+
|
|
66
|
+
PLATFORMS
|
|
67
|
+
ruby
|
|
68
|
+
|
|
69
|
+
DEPENDENCIES
|
|
70
|
+
activesupport (~> 5.2.0)
|
|
71
|
+
bundler (>= 1.15)
|
|
72
|
+
crawler_detect!
|
|
73
|
+
fuubar (~> 2.0)
|
|
74
|
+
parallel_tests (~> 2.0)
|
|
75
|
+
pry-meta (~> 0.0.10)
|
|
76
|
+
rack-test (~> 1.1)
|
|
77
|
+
rake (>= 10.0)
|
|
78
|
+
rspec (~> 3.0)
|
|
79
|
+
|
|
80
|
+
BUNDLED WITH
|
|
81
|
+
2.1.3
|
|
@@ -56,6 +56,7 @@ AddThis
|
|
|
56
56
|
ADmantX
|
|
57
57
|
AdminLabs
|
|
58
58
|
adressendeutschland
|
|
59
|
+
adreview\/
|
|
59
60
|
adscanner
|
|
60
61
|
Adstxtaggregator
|
|
61
62
|
adstxt-worker
|
|
@@ -95,7 +96,6 @@ AportWorm\/
|
|
|
95
96
|
AppBeat\/
|
|
96
97
|
AppEngine-Google
|
|
97
98
|
AppleSyndication
|
|
98
|
-
AppStoreScraperZ
|
|
99
99
|
Aprc\/[0-9]
|
|
100
100
|
Arachmo
|
|
101
101
|
arachnode
|
|
@@ -110,6 +110,7 @@ Asterias
|
|
|
110
110
|
Astute
|
|
111
111
|
asynchttp
|
|
112
112
|
Attach
|
|
113
|
+
attohttpc
|
|
113
114
|
autocite
|
|
114
115
|
AutomaticWPTester
|
|
115
116
|
Autonomy
|
|
@@ -134,6 +135,7 @@ BBBike
|
|
|
134
135
|
BCKLINKS
|
|
135
136
|
BDFetch
|
|
136
137
|
BegunAdvertising
|
|
138
|
+
Bewica-security-scan
|
|
137
139
|
Bidtellect
|
|
138
140
|
BigBozz
|
|
139
141
|
Bigfoot
|
|
@@ -148,6 +150,7 @@ Black Hole
|
|
|
148
150
|
Blackboard Safeassign
|
|
149
151
|
BlackWidow
|
|
150
152
|
BlockNote\.Net
|
|
153
|
+
BlogBridge
|
|
151
154
|
Bloglines
|
|
152
155
|
Bloglovin
|
|
153
156
|
BlogPulseLive
|
|
@@ -155,6 +158,7 @@ BlogSearch
|
|
|
155
158
|
Blogtrottr
|
|
156
159
|
BlowFish
|
|
157
160
|
boitho\.com-dc
|
|
161
|
+
Boost\.Beast
|
|
158
162
|
BPImageWalker
|
|
159
163
|
Braintree-Webhooks
|
|
160
164
|
Branch Metrics API
|
|
@@ -205,6 +209,7 @@ clips\.ua\.ac\.be
|
|
|
205
209
|
Cloud mapping
|
|
206
210
|
CloudEndure
|
|
207
211
|
CloudFlare-AlwaysOnline
|
|
212
|
+
Cloudflare-Healthchecks
|
|
208
213
|
Cloudinary
|
|
209
214
|
cmcm\.com
|
|
210
215
|
coccoc
|
|
@@ -247,6 +252,7 @@ Daum(oa)?[ \/][0-9]
|
|
|
247
252
|
dBpoweramp
|
|
248
253
|
ddline
|
|
249
254
|
deeris
|
|
255
|
+
delve\.ai
|
|
250
256
|
Demon
|
|
251
257
|
DeuSu
|
|
252
258
|
developers\.google\.com\/\+\/web\/snippet\/
|
|
@@ -265,6 +271,7 @@ DNSPod-reporting
|
|
|
265
271
|
docoloc
|
|
266
272
|
Dolphin http client
|
|
267
273
|
DomainAppender
|
|
274
|
+
DomainLabz
|
|
268
275
|
Donuts Content Explorer
|
|
269
276
|
dotMailer content retrieval
|
|
270
277
|
dotSemantic
|
|
@@ -278,6 +285,7 @@ Drupal \(\+http:\/\/drupal\.org\/\)
|
|
|
278
285
|
DTS Agent
|
|
279
286
|
dubaiindex
|
|
280
287
|
DuplexWeb-Google
|
|
288
|
+
DynatraceSynthetic
|
|
281
289
|
EARTHCOM
|
|
282
290
|
Easy-Thumb
|
|
283
291
|
EasyDL
|
|
@@ -308,6 +316,7 @@ ExactSearch
|
|
|
308
316
|
ExaleadCloudview
|
|
309
317
|
Excel\/
|
|
310
318
|
exif
|
|
319
|
+
ExoRank
|
|
311
320
|
Exploratodo
|
|
312
321
|
Express WebPictures
|
|
313
322
|
Extreme Picture Finder
|
|
@@ -342,6 +351,7 @@ Fetch API
|
|
|
342
351
|
Fetch\/[0-9]
|
|
343
352
|
Fever\/[0-9]
|
|
344
353
|
FHscan
|
|
354
|
+
Filestack
|
|
345
355
|
Fimap
|
|
346
356
|
findlink
|
|
347
357
|
findthatfile
|
|
@@ -359,6 +369,7 @@ http:\/\/www.neomo.de\/
|
|
|
359
369
|
free thumbnails
|
|
360
370
|
Freeuploader
|
|
361
371
|
Funnelback
|
|
372
|
+
Fuzz Faster U Fool
|
|
362
373
|
G-i-g-a-b-o-t
|
|
363
374
|
g00g1e\.net
|
|
364
375
|
ganarvisitas
|
|
@@ -379,6 +390,7 @@ GigablastOpenSource
|
|
|
379
390
|
GIS-LABS
|
|
380
391
|
github-camo
|
|
381
392
|
github\.com
|
|
393
|
+
Goldfire Server
|
|
382
394
|
Go [\d\.]* package http
|
|
383
395
|
Go http package
|
|
384
396
|
Go-Ahead-Got-It
|
|
@@ -398,6 +410,7 @@ Google Page Speed Insights
|
|
|
398
410
|
Google PP Default
|
|
399
411
|
Google Search Console
|
|
400
412
|
Google Web Preview
|
|
413
|
+
Google-Ads-Overview
|
|
401
414
|
Google-Adwords
|
|
402
415
|
Google-Apps-Script
|
|
403
416
|
Google-Calendar-Importer
|
|
@@ -407,6 +420,7 @@ Google-Publisher-Plugin
|
|
|
407
420
|
Google-Read-Aloud
|
|
408
421
|
Google-SearchByImage
|
|
409
422
|
Google-Site-Verification
|
|
423
|
+
Google-speakr
|
|
410
424
|
Google-Structured-Data-Testing-Tool
|
|
411
425
|
Google-Youtube-Links
|
|
412
426
|
google-xrawler
|
|
@@ -416,7 +430,6 @@ GoogleProducer
|
|
|
416
430
|
GoogleSites
|
|
417
431
|
Google-Transparency-Report
|
|
418
432
|
Gookey
|
|
419
|
-
GoScraper
|
|
420
433
|
GoSpotCheck
|
|
421
434
|
gosquared-thumbnailer
|
|
422
435
|
Gotit
|
|
@@ -450,6 +463,7 @@ HEADMasterSEO
|
|
|
450
463
|
HeartRails_Capture
|
|
451
464
|
help@dataminr\.com
|
|
452
465
|
heritrix
|
|
466
|
+
Hexometer
|
|
453
467
|
historious
|
|
454
468
|
hkedcity
|
|
455
469
|
hledejLevne\.cz
|
|
@@ -596,6 +610,7 @@ Liferea\/
|
|
|
596
610
|
Lightspeedsystems
|
|
597
611
|
Lighthouse
|
|
598
612
|
Likse
|
|
613
|
+
limber\.io
|
|
599
614
|
Link Valet
|
|
600
615
|
link_thumbnailer
|
|
601
616
|
LinkAlarm\/
|
|
@@ -615,6 +630,7 @@ livedoor ScreenShot
|
|
|
615
630
|
LoadImpactRload
|
|
616
631
|
localsearch-web
|
|
617
632
|
LongURL API
|
|
633
|
+
longurl-r-package
|
|
618
634
|
looid\.com
|
|
619
635
|
looksystems\.net
|
|
620
636
|
ltx71
|
|
@@ -649,6 +665,7 @@ MemGator
|
|
|
649
665
|
Metaspinner
|
|
650
666
|
MetaURI
|
|
651
667
|
MFC_Tear_Sample
|
|
668
|
+
MicroMessenger\/
|
|
652
669
|
Microsearch
|
|
653
670
|
Microsoft Office
|
|
654
671
|
Microsoft Outlook
|
|
@@ -679,6 +696,7 @@ Morfeus Fucking Scanner
|
|
|
679
696
|
Morning Paper
|
|
680
697
|
MovableType
|
|
681
698
|
mowser
|
|
699
|
+
Mr\.4x3 Powered
|
|
682
700
|
Mrcgiguy
|
|
683
701
|
MS Web Services Client Protocol
|
|
684
702
|
MSFrontPage
|
|
@@ -748,7 +766,6 @@ oegp
|
|
|
748
766
|
Offline Explorer
|
|
749
767
|
Offline Navigator
|
|
750
768
|
OgScrper
|
|
751
|
-
og-scraper
|
|
752
769
|
okhttp
|
|
753
770
|
omgili
|
|
754
771
|
OMSC
|
|
@@ -758,6 +775,7 @@ Openfind
|
|
|
758
775
|
OpenLinkProfiler
|
|
759
776
|
Openstat\/
|
|
760
777
|
OpenVAS
|
|
778
|
+
OPPO A33
|
|
761
779
|
Optimizer
|
|
762
780
|
Orbiter
|
|
763
781
|
OrgProbe\/
|
|
@@ -772,6 +790,7 @@ Page Valet
|
|
|
772
790
|
page_verifier
|
|
773
791
|
page scorer
|
|
774
792
|
page2rss
|
|
793
|
+
PageFreezer
|
|
775
794
|
PageGrabber
|
|
776
795
|
PagePeeker
|
|
777
796
|
PageScorer
|
|
@@ -825,6 +844,7 @@ PostmanRuntime
|
|
|
825
844
|
PostPost
|
|
826
845
|
postrank
|
|
827
846
|
PowerPoint\/
|
|
847
|
+
Prebid
|
|
828
848
|
Priceonomics Analysis Engine
|
|
829
849
|
PrintFriendly
|
|
830
850
|
PritTorrent
|
|
@@ -839,8 +859,8 @@ PRTG Network Monitor
|
|
|
839
859
|
pshtt, https scanning
|
|
840
860
|
PTST
|
|
841
861
|
PTST\/[0-9]+
|
|
842
|
-
Pulsepoint XT3 web scraper
|
|
843
862
|
Pump
|
|
863
|
+
python-httpx
|
|
844
864
|
Python-httplib2
|
|
845
865
|
python-requests
|
|
846
866
|
Python-urllib
|
|
@@ -881,13 +901,16 @@ Robozilla
|
|
|
881
901
|
ROI Hunter
|
|
882
902
|
RPT-HTTPClient
|
|
883
903
|
RSSOwl
|
|
904
|
+
RyowlEngine
|
|
884
905
|
safe-agent-scanner
|
|
885
906
|
SalesIntelligent
|
|
886
907
|
Saleslift
|
|
887
908
|
Sendsay\.Ru
|
|
888
909
|
SauceNAO
|
|
889
910
|
SBIder
|
|
911
|
+
sc-downloader
|
|
890
912
|
scalaj-http
|
|
913
|
+
Scamadviser-Frontend
|
|
891
914
|
scan\.lol
|
|
892
915
|
ScanAlert
|
|
893
916
|
Scoop
|
|
@@ -895,7 +918,6 @@ scooter
|
|
|
895
918
|
ScoutJet
|
|
896
919
|
ScoutURLMonitor
|
|
897
920
|
ScrapeBox Page Scanner
|
|
898
|
-
SimpleScraper
|
|
899
921
|
Scrapy
|
|
900
922
|
Screaming
|
|
901
923
|
ScreenShotService
|
|
@@ -921,6 +943,7 @@ Seobility
|
|
|
921
943
|
SEOCentro
|
|
922
944
|
SeoCheck
|
|
923
945
|
SEOkicks
|
|
946
|
+
SEOlizer
|
|
924
947
|
Seomoz
|
|
925
948
|
SEOprofiler
|
|
926
949
|
SEOsearch
|
|
@@ -934,6 +957,7 @@ Shelob
|
|
|
934
957
|
Shodan
|
|
935
958
|
Shoppimon
|
|
936
959
|
ShopWiki
|
|
960
|
+
shortURL lengthener
|
|
937
961
|
ShortLinkTranslate
|
|
938
962
|
shrinktheweb
|
|
939
963
|
Sideqik
|
|
@@ -1013,7 +1037,6 @@ summify
|
|
|
1013
1037
|
SuperHTTP
|
|
1014
1038
|
Surphace Scout
|
|
1015
1039
|
Suzuran
|
|
1016
|
-
SwiteScraper
|
|
1017
1040
|
Symfony BrowserKit
|
|
1018
1041
|
Symfony2 BrowserKit
|
|
1019
1042
|
SynHttpClient-Built
|
|
@@ -1102,7 +1125,6 @@ VB Project
|
|
|
1102
1125
|
vBSEO
|
|
1103
1126
|
VCI
|
|
1104
1127
|
via ggpht\.com GoogleImageProxy
|
|
1105
|
-
VidibleScraper
|
|
1106
1128
|
Virusdie
|
|
1107
1129
|
visionutils
|
|
1108
1130
|
vkShare
|
|
@@ -1191,11 +1213,13 @@ WhereGoes\?
|
|
|
1191
1213
|
Whibse
|
|
1192
1214
|
WhoRunsCoinHive
|
|
1193
1215
|
Whynder Magnet
|
|
1216
|
+
WinHttp-Autoproxy-Service
|
|
1194
1217
|
Windows-RSS-Platform
|
|
1195
1218
|
WinPodder
|
|
1196
1219
|
wkhtmlto
|
|
1197
1220
|
wmtips
|
|
1198
1221
|
Woko
|
|
1222
|
+
Wolfram HTTPClient
|
|
1199
1223
|
woorankreview
|
|
1200
1224
|
Word\/
|
|
1201
1225
|
WordPress\/
|
|
@@ -1254,7 +1278,7 @@ ZnHTTP
|
|
|
1254
1278
|
Zombie\.js
|
|
1255
1279
|
Zoom\.Mac
|
|
1256
1280
|
ZyBorg
|
|
1257
|
-
[a-z0-9\-_]*(bot|crawl|archiver|transcoder|spider|uptime|validator|fetcher|cron|checker|reader|extractor|monitoring|analyzer)
|
|
1281
|
+
[a-z0-9\-_]*(bot|crawl|archiver|transcoder|spider|uptime|validator|fetcher|cron|checker|reader|extractor|monitoring|analyzer|scraper)
|
|
1258
1282
|
].strip.split(/\n+/).freeze
|
|
1259
1283
|
end
|
|
1260
1284
|
end
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: crawler_detect
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.1.
|
|
4
|
+
version: 0.1.12
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Pavel Kozlov
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date:
|
|
11
|
+
date: 2020-04-19 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: activesupport
|
|
@@ -134,6 +134,7 @@ files:
|
|
|
134
134
|
- ".rubocop.yml"
|
|
135
135
|
- ".travis.yml"
|
|
136
136
|
- Gemfile
|
|
137
|
+
- Gemfile.lock
|
|
137
138
|
- LICENSE.txt
|
|
138
139
|
- README.md
|
|
139
140
|
- Rakefile
|