crawler_detect 1.0.2 → 1.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.github/workflows/build.yml +38 -0
- data/CHANGELOG.md +8 -0
- data/Gemfile.lock +34 -36
- data/README.md +15 -13
- data/crawler_detect.gemspec +0 -1
- data/lib/crawler_detect/library/loader.rb +1 -1
- data/lib/crawler_detect/library/raw/Crawlers.json +1 -1
- data/lib/crawler_detect/library/raw/Exclusions.json +1 -1
- data/lib/crawler_detect/library.rb +12 -2
- data/lib/crawler_detect/version.rb +1 -1
- data/lib/crawler_detect.rb +2 -2
- metadata +3 -17
- data/.travis.yml +0 -26
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: abc20006d901205f658b54f78a94acb2480f3efbbc80213540381a1f956ce9d8
|
4
|
+
data.tar.gz: 53a3959effd4a78f93afa1d438ea06b6db567a3f3227311f24bbc7a1ea0d89fc
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: '018d27fba7246b394e3cb5444cd8c0862e4ea08bf1b9e1fa12adb46d887b8753820ecbc103030c89af0b0e8ab05fa2c1d42ee33466685eaadfbc61b3185ef32f'
|
7
|
+
data.tar.gz: 02536c1035099e35961fafc9877a3d29d72ff5ed20848f2f4eb183d4fbbc300d6d5d7d68d23282e49e2a19ad589c04bc6ffb8dd8200e14b81a602286af924261
|
@@ -0,0 +1,38 @@
|
|
1
|
+
name: build
|
2
|
+
|
3
|
+
on: [push]
|
4
|
+
|
5
|
+
jobs:
|
6
|
+
lint:
|
7
|
+
runs-on: ubuntu-latest
|
8
|
+
steps:
|
9
|
+
- uses: actions/checkout@v2
|
10
|
+
- uses: ruby/setup-ruby@v1
|
11
|
+
with:
|
12
|
+
ruby-version: 2.7
|
13
|
+
- name: install gems
|
14
|
+
run: |
|
15
|
+
gem install bundler
|
16
|
+
bundle install --jobs 4 --retry 3
|
17
|
+
- run: bundle exec rubocop
|
18
|
+
test:
|
19
|
+
needs: lint
|
20
|
+
runs-on: ubuntu-latest
|
21
|
+
strategy:
|
22
|
+
fail-fast: false
|
23
|
+
matrix:
|
24
|
+
ruby: [2.5, 2.6, 2.7]
|
25
|
+
test-group: [1, 2, 3, 4]
|
26
|
+
name: Ruby ${{ matrix.ruby }}, test-group ${{ matrix.test-group }}
|
27
|
+
steps:
|
28
|
+
- uses: actions/checkout@v2
|
29
|
+
- uses: ruby/setup-ruby@v1
|
30
|
+
with:
|
31
|
+
ruby-version: ${{ matrix.ruby }}
|
32
|
+
- name: install gems
|
33
|
+
run: |
|
34
|
+
gem install bundler
|
35
|
+
bundle install --jobs 4 --retry 3
|
36
|
+
- name: test
|
37
|
+
run: |
|
38
|
+
bundle exec parallel_rspec spec/ -n 4 --only-group ${{ matrix.test-group }} --group-by runtime --runtime-log spec/fixtures/parallel_runtime_rspec.log
|
data/CHANGELOG.md
CHANGED
@@ -3,6 +3,14 @@
|
|
3
3
|
This changelog **does not contain** raw data updates
|
4
4
|
but only major changes.
|
5
5
|
|
6
|
+
1.2.0
|
7
|
+
---------
|
8
|
+
- Speed up crawler detection by caching Regexp objects [#38]
|
9
|
+
|
10
|
+
1.1.0
|
11
|
+
---------
|
12
|
+
- Moves to Ruby's Stdlib JSON implementation to reduce dependencies
|
13
|
+
|
6
14
|
1.0.0
|
7
15
|
---------
|
8
16
|
- Use raw JSON files instead of copy them to rb [#8]
|
data/Gemfile.lock
CHANGED
@@ -1,14 +1,13 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
crawler_detect (1.
|
5
|
-
oj (>= 3.0)
|
4
|
+
crawler_detect (1.1.2)
|
6
5
|
qonfig (~> 0.24)
|
7
6
|
|
8
7
|
GEM
|
9
8
|
remote: https://rubygems.org/
|
10
9
|
specs:
|
11
|
-
activesupport (6.0.
|
10
|
+
activesupport (6.0.4.1)
|
12
11
|
concurrent-ruby (~> 1.0, >= 1.0.2)
|
13
12
|
i18n (>= 0.7, < 2)
|
14
13
|
minitest (~> 5.1)
|
@@ -20,32 +19,31 @@ GEM
|
|
20
19
|
rubocop-rails (= 2.5.2)
|
21
20
|
rubocop-rake (= 0.5.1)
|
22
21
|
rubocop-rspec (= 1.38.1)
|
23
|
-
ast (2.4.
|
24
|
-
awesome_print (1.
|
25
|
-
byebug (11.1.
|
26
|
-
coderay (1.1.
|
27
|
-
concurrent-ruby (1.1.
|
28
|
-
diff-lcs (1.
|
29
|
-
fuubar (2.5.
|
22
|
+
ast (2.4.2)
|
23
|
+
awesome_print (1.9.2)
|
24
|
+
byebug (11.1.3)
|
25
|
+
coderay (1.1.3)
|
26
|
+
concurrent-ruby (1.1.9)
|
27
|
+
diff-lcs (1.4.4)
|
28
|
+
fuubar (2.5.1)
|
30
29
|
rspec-core (~> 3.0)
|
31
30
|
ruby-progressbar (~> 1.4)
|
32
|
-
i18n (1.8.
|
31
|
+
i18n (1.8.10)
|
33
32
|
concurrent-ruby (~> 1.0)
|
34
33
|
jaro_winkler (1.5.4)
|
35
34
|
method_source (1.0.0)
|
36
|
-
minitest (5.14.
|
37
|
-
|
38
|
-
parallel (1.19.1)
|
35
|
+
minitest (5.14.4)
|
36
|
+
parallel (1.20.1)
|
39
37
|
parallel_tests (2.32.0)
|
40
38
|
parallel
|
41
|
-
parser (
|
42
|
-
ast (~> 2.4.
|
43
|
-
pry (0.
|
39
|
+
parser (3.0.2.0)
|
40
|
+
ast (~> 2.4.1)
|
41
|
+
pry (0.14.1)
|
44
42
|
coderay (~> 1.1)
|
45
43
|
method_source (~> 1.0)
|
46
|
-
pry-byebug (3.
|
44
|
+
pry-byebug (3.8.0)
|
47
45
|
byebug (~> 11.0)
|
48
|
-
pry (~> 0.
|
46
|
+
pry (~> 0.10)
|
49
47
|
pry-meta (0.0.10)
|
50
48
|
awesome_print
|
51
49
|
pry
|
@@ -54,26 +52,26 @@ GEM
|
|
54
52
|
pry-remote (0.1.8)
|
55
53
|
pry (~> 0.9)
|
56
54
|
slop (~> 3.0)
|
57
|
-
qonfig (0.
|
55
|
+
qonfig (0.26.0)
|
58
56
|
rack (2.2.3)
|
59
57
|
rack-test (1.1.0)
|
60
58
|
rack (>= 1.0, < 3)
|
61
59
|
rainbow (3.0.0)
|
62
|
-
rake (13.0.
|
63
|
-
rexml (3.2.
|
64
|
-
rspec (3.
|
65
|
-
rspec-core (~> 3.
|
66
|
-
rspec-expectations (~> 3.
|
67
|
-
rspec-mocks (~> 3.
|
68
|
-
rspec-core (3.
|
69
|
-
rspec-support (~> 3.
|
70
|
-
rspec-expectations (3.
|
60
|
+
rake (13.0.6)
|
61
|
+
rexml (3.2.5)
|
62
|
+
rspec (3.10.0)
|
63
|
+
rspec-core (~> 3.10.0)
|
64
|
+
rspec-expectations (~> 3.10.0)
|
65
|
+
rspec-mocks (~> 3.10.0)
|
66
|
+
rspec-core (3.10.1)
|
67
|
+
rspec-support (~> 3.10.0)
|
68
|
+
rspec-expectations (3.10.1)
|
71
69
|
diff-lcs (>= 1.2.0, < 2.0)
|
72
|
-
rspec-support (~> 3.
|
73
|
-
rspec-mocks (3.
|
70
|
+
rspec-support (~> 3.10.0)
|
71
|
+
rspec-mocks (3.10.2)
|
74
72
|
diff-lcs (>= 1.2.0, < 2.0)
|
75
|
-
rspec-support (~> 3.
|
76
|
-
rspec-support (3.
|
73
|
+
rspec-support (~> 3.10.0)
|
74
|
+
rspec-support (3.10.2)
|
77
75
|
rubocop (0.82.0)
|
78
76
|
jaro_winkler (~> 1.5.1)
|
79
77
|
parallel (~> 1.10)
|
@@ -92,13 +90,13 @@ GEM
|
|
92
90
|
rubocop
|
93
91
|
rubocop-rspec (1.38.1)
|
94
92
|
rubocop (>= 0.68.1)
|
95
|
-
ruby-progressbar (1.
|
93
|
+
ruby-progressbar (1.11.0)
|
96
94
|
slop (3.6.0)
|
97
95
|
thread_safe (0.3.6)
|
98
|
-
tzinfo (1.2.
|
96
|
+
tzinfo (1.2.9)
|
99
97
|
thread_safe (~> 0.1)
|
100
98
|
unicode-display_width (1.7.0)
|
101
|
-
zeitwerk (2.
|
99
|
+
zeitwerk (2.4.2)
|
102
100
|
|
103
101
|
PLATFORMS
|
104
102
|
ruby
|
data/README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1
1
|
# CrawlerDetect
|
2
2
|
|
3
|
-
|
3
|
+
![Build](https://github.com/loadkpi/crawler_detect/workflows/build/badge.svg?branch=master) [![Gem Version](https://badge.fury.io/rb/crawler_detect.svg)](https://badge.fury.io/rb/crawler_detect)
|
4
4
|
|
5
5
|
## About
|
6
6
|
**CrawlerDetect** is a Ruby version of PHP class @[CrawlerDetect](https://github.com/JayBizzle/Crawler-Detect).
|
@@ -15,50 +15,52 @@ Comparing with other popular bot-detection gems:
|
|
15
15
|
| Number of checked HTTP-headers | 10 | 1 | 1 |
|
16
16
|
| Number of updates of bot-list *(1st half of 2018)* | 14 | 1 | 7 |
|
17
17
|
|
18
|
+
In order to remain up-to-date, this gem does not accept any crawler data updates – any PRs to edit the crawler data should be offered to the original [JayBizzle/CrawlerDetect](https://github.com/JayBizzle/Crawler-Detect) project.
|
19
|
+
|
18
20
|
## Installation
|
19
21
|
Add this line to your application's Gemfile:
|
20
22
|
|
21
23
|
`gem 'crawler_detect'`
|
22
24
|
## Basic Usage
|
23
|
-
```
|
25
|
+
```ruby
|
24
26
|
CrawlerDetect.is_crawler?("Bot user agent")
|
25
27
|
=> true
|
26
28
|
```
|
27
29
|
Or if you need crawler name:
|
28
|
-
```
|
30
|
+
```ruby
|
29
31
|
detector = CrawlerDetect.new("Googlebot/2.1 (http://www.google.com/bot.html)")
|
30
32
|
detector.is_crawler?
|
31
|
-
=> true
|
33
|
+
# => true
|
32
34
|
detector.crawler_name
|
33
|
-
=> "Googlebot"
|
35
|
+
# => "Googlebot"
|
34
36
|
```
|
35
37
|
## Rack::Request extension
|
36
38
|
**Optionally** you can add additional methods for `request`:
|
37
|
-
```
|
39
|
+
```ruby
|
38
40
|
request.is_crawler?
|
39
|
-
=> false
|
41
|
+
# => false
|
40
42
|
request.crawler_name
|
41
|
-
=> nil
|
43
|
+
# => nil
|
42
44
|
```
|
43
45
|
It's more flexible to use `request.is_crawler?` rather than `CrawlerDetect.is_crawler?` because it automatically checks 10 HTTP-headers, not only `HTTP_USER_AGENT`.
|
44
46
|
|
45
47
|
Only one thing you have to do is to configure `Rack::CrawlerDetect` midleware:
|
46
48
|
### Rails
|
47
|
-
```
|
49
|
+
```ruby
|
48
50
|
class Application < Rails::Application
|
49
|
-
...
|
51
|
+
# ...
|
50
52
|
config.middleware.use Rack::CrawlerDetect
|
51
53
|
end
|
52
54
|
```
|
53
|
-
###
|
54
|
-
```
|
55
|
+
### Rack
|
56
|
+
```ruby
|
55
57
|
use Rack::CrawlerDetect
|
56
58
|
```
|
57
59
|
## Configuration
|
58
60
|
In some cases you may want to use your own white-list, or black-list or list of http-headers to detect User-agent.
|
59
61
|
|
60
62
|
It is possible to do via `CrawlerDetect::Config`. For example, you may have initializer like this:
|
61
|
-
```
|
63
|
+
```ruby
|
62
64
|
CrawlerDetect.setup! do |config|
|
63
65
|
config.raw_headers_path = File.expand_path("crawlers/MyHeaders.json", __dir__)
|
64
66
|
config.raw_crawlers_path = File.expand_path("crawlers/MyCrawlers.json", __dir__)
|
data/crawler_detect.gemspec
CHANGED
@@ -24,7 +24,6 @@ Gem::Specification.new do |spec|
|
|
24
24
|
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
25
25
|
spec.require_paths = ["lib"]
|
26
26
|
|
27
|
-
spec.add_dependency "oj", ">= 3.0"
|
28
27
|
spec.add_dependency "qonfig", "~> 0.24"
|
29
28
|
|
30
29
|
spec.add_development_dependency "activesupport", "~> 6.0.3"
|
@@ -1 +1 @@
|
|
1
|
-
[" YLT","^b0t$","^bluefish ","^Calypso v\\\/","^Corax","^COMODO DCV","^DangDang","^DavClnt","^DHSH","^FDM ","^git\\\/","^Goose\\\/","^Grabber","^HTTPClient\\\/","^Java\\\/","^Jeode\\\/","^Jetty\\\/","^Mail\\\/","^Mget","^Microsoft URL Control","^NG\\\/[0-9\\.]","^NING\\\/","^Nuclei","^PHP\\\/[0-9]","^RMA\\\/","^Ruby|Ruby\\\/[0-9]","^Swurl ","^VSE\\\/[0-9]","^WordPress\\.com","^XRL\\\/[0-9]","^ZmEu","008\\\/","13TABS","192\\.comAgent","2GDPR\\\/","2ip\\.ru","404enemy","7Siters","80legs","a\\.pr-cy\\.ru","a3logics\\.in","A6-Indexer","Abonti","Aboundex","aboutthedomain","Accoona-AI-Agent","acebookexternalhit\\\/","acoon","acrylicapps\\.com\\\/pulp","Acunetix","AdAuth\\\/","adbeat","AddThis","ADmantX","AdminLabs","adressendeutschland","adreview\\\/","adscanner","Adstxtaggregator","adstxt-worker","adstxt\\.com","AffiliateLabz\\\/","agentslug","AHC","aihit","aiohttp\\\/","Airmail","akka-http\\\/","akula\\\/","alertra","alexa site audit","Alibaba\\.Security\\.Heimdall","Alligator","allloadin","AllSubmitter","alyze\\.info","amagit","^Amazon Simple Notification Service Agent$","Anarchie","AndroidDownloadManager","Anemone","AngleSharp","annotate_google","Ant\\.com","Anturis Agent","AnyEvent-HTTP\\\/","Apache Droid","Apache OpenOffice","Apache-HttpAsyncClient","Apache-HttpClient","ApacheBench","Apexoo","apimon\\.de","APIs-Google","AportWorm\\\/","AppBeat\\\/","AppEngine-Google","AppleSyndication","Aprc\\\/[0-9]","Arachmo","arachnode","Arachnophilia","aria2","Arukereso","asafaweb","AskQuickly","Ask Jeeves","ASPSeek","Asterias","Astute","asynchttp","Attach","attohttpc","autocite","AutomaticWPTester","Autonomy","axios\\\/","AWS Security Scanner","B-l-i-t-z-B-O-T","Backlink-Ceck","backlink-check","BacklinkHttpStatus","BackStreet","BackupLand","BackWeb","Bad-Neighborhood","Badass","baidu\\.com","Bandit","basicstate","BatchFTP","Battleztar Bazinga","baypup\\\/","BazQux","BBBike","BCKLINKS","BDFetch","BegunAdvertising","Bewica-security-scan","Bidtellect","BigBozz","Bigfoot","biglotron","BingLocalSearch","BingPreview","binlar","biNu image cacher","Bitacle","biz_Directory","Black Hole","Blackboard Safeassign","BlackWidow","BlockNote\\.Net","BlogBridge","Bloglines","Bloglovin","BlogPulseLive","BlogSearch","Blogtrottr","BlowFish","boitho\\.com-dc","Boost\\.Beast","BPImageWalker","Braintree-Webhooks","Branch Metrics API","Branch-Passthrough","Brandprotect","BrandVerity","Brandwatch","Brodie\\\/","Browsershots","BUbiNG","Buck\\\/","Buddy","BuiltWith","Bullseye","BunnySlippers","Burf Search","Butterfly\\\/","BuzzSumo","CAAM\\\/[0-9]","CakePHP","Calculon","Canary%20Mail","CaretNail","catexplorador","CC Metadata Scaper","Cegbfeieh","censys","centuryb.o.t9[at]gmail.com","Cerberian Drtrs","CERT\\.at-Statistics-Survey","cg-eye","changedetection","ChangesMeter","Charlotte","CheckHost","checkprivacy","CherryPicker","ChinaClaw","Chirp\\\/","chkme\\.com","Chlooe","Chromaxa","CirrusExplorer","CISPA Vulnerability Notification","Citoid","CJNetworkQuality","Clarsentia","clips\\.ua\\.ac\\.be","Cloud mapping","CloudEndure","CloudFlare-AlwaysOnline","Cloudflare-Healthchecks","Cloudinary","cmcm\\.com","coccoc","cognitiveseo","colly -","CommaFeed","Commons-HttpClient","commonscan","contactbigdatafr","contentkingapp","Contextual Code Sites Explorer","convera","CookieReports","copyright sheriff","CopyRightCheck","Copyscape","cortex\\\/","Cosmos4j\\.feedback","Covario-IDS","Craw\\\/","Crescent","Crowsnest","Criteo","CSHttp","CSSCheck","Cula\\\/","curb","Curious George","curl","cuwhois\\\/","cybo\\.com","DAP\\\/NetHTTP","DareBoost","DatabaseDriverMysqli","DataCha0s","Datafeedwatch","Datanyze","DataparkSearch","dataprovider","DataXu","Daum(oa)?[ \\\/][0-9]","dBpoweramp","ddline","deeris","delve\\.ai","Demon","DeuSu","developers\\.google\\.com\\\/\\+\\\/web\\\/snippet\\\/","Devil","Digg","Digincore","DigitalPebble","Dirbuster","Discourse Forum Onebox","Disqus\\\/","Dispatch\\\/","DittoSpyder","dlvr","DMBrowser","DNSPod-reporting","docoloc","Dolphin http client","DomainAppender","DomainLabz","Domains Project\\\/","Donuts Content Explorer","dotMailer content retrieval","dotSemantic","downforeveryoneorjustme","Download Wonder","downnotifier","DowntimeDetector","Drip","drupact","Drupal \\(\\+http:\\\/\\\/drupal\\.org\\\/\\)","DTS Agent","dubaiindex","DuplexWeb-Google","DynatraceSynthetic","EARTHCOM","Easy-Thumb","EasyDL","Ebingbong","ec2linkfinder","eCairn-Grabber","eCatch","ECCP","eContext\\\/","Ecxi","EirGrabber","ElectricMonk","elefent","EMail Exractor","EMail Wolf","EmailWolf","Embarcadero","Embed PHP Library","Embedly","endo\\\/","europarchive\\.org","evc-batch","EventMachine HttpClient","Everwall Link Expander","Evidon","Evrinid","ExactSearch","ExaleadCloudview","Excel\\\/","exif","ExoRank","Exploratodo","Express WebPictures","Extreme Picture Finder","EyeNetIE","ezooms","facebookexternalhit","facebookexternalua","facebookplatform","fairshare","Faraday v","fasthttp","Faveeo","Favicon downloader","faviconkit","faviconarchive","FavOrg","Feed Wrangler","Feedable\\\/","Feedbin","FeedBooster","FeedBucket","FeedBunch\\\/","FeedBurner","feeder","Feedly","Feedshow\\\/","FeedshowOnline","Feedspot","FeedViewer\\\/","Feedwind\\\/","FeedZcollector","feeltiptop","Fetch API","Fetch\\\/[0-9]","Fever\\\/[0-9]","FHscan","Fiery%20Feeds","Filestack","Fimap","findlink","findthatfile","FlashGet","FlipboardBrowserProxy","FlipboardProxy","FlipboardRSS","Flock\\\/","fluffy","Flunky","flynxapp","forensiq","FoundSeoTool","http:\\\/\\\/www.neomo.de\\\/","free thumbnails","Freeuploader","FreshRSS","Funnelback","Fuzz Faster U Fool","G-i-g-a-b-o-t","g00g1e\\.net","ganarvisitas","gdnplus\\.com","geek-tools","Genieo","GentleSource","GetCode","Getintent","GetLinkInfo","getprismatic","GetRight","getroot","GetURLInfo\\\/","GetWeb","Geziyor","Ghost Inspector","GigablastOpenSource","GIS-LABS","github-camo","GitHub-Hookshot","github\\.com","Goldfire Server","Go [\\d\\.]* package http","Go http package","Go-Ahead-Got-It","Go-http-client","Go!Zilla","gobyus","Gofeed","gofetch","GomezAgent","gooblog","Goodzer\\\/","Google AppsViewer","Google Desktop","Google favicon","Google Keyword Suggestion","Google Keyword Tool","Google Page Speed Insights","Google-Podcast","Google PP Default","Google Search Console","Google Web Preview","Google-Ads-Overview","Google-Adwords","Google-Apps-Script","Google-Calendar-Importer","Google-HotelAdsVerifier","Google-HTTP-Java-Client","Google-Publisher-Plugin","Google-Read-Aloud","Google-SearchByImage","Google-Site-Verification","Google-speakr","Google-Structured-Data-Testing-Tool","Google-Youtube-Links","google-xrawler","GoogleDocs","GoogleHC\\\/","GoogleProducer","GoogleSites","Google-Transparency-Report","Gookey","GoSpotCheck","gosquared-thumbnailer","Gotit","GoZilla","grabify","GrabNet","Grafula","Grammarly","GrapeFX","GreatNews","Gregarius","GRequests","grokkit","grouphigh","grub-client","gSOAP\\\/","GT::WWW","GTmetrix","GuzzleHttp","gvfs\\\/","HAA(A)?RTLAND http client","Haansoft","hackney\\\/","Hadi Agent","HappyApps-WebCheck","Hatena","Havij","HaxerMen","HeadlessChrome","HEADMasterSEO","HeartRails_Capture","help@dataminr\\.com","heritrix","Hexometer","historious","hkedcity","hledejLevne\\.cz","Hloader","HMView","Holmes","HonesoSearchEngine","HootSuite Image proxy","Hootsuite-WebFeed","hosterstats","HostTracker","ht:\\\/\\\/check","htdig","HTMLparser","htmlyse","HTTP Banner Detection","HTTP_Compression_Test","http_request2","http_requester","http-get","HTTP-Header-Abfrage","http-kit","http-request\\\/","HTTP-Tiny","HTTP::Lite","http\\.rb\\\/","http_get","HttpComponents","httphr","HTTPMon","HTTPie","httpRequest","httpscheck","httpssites_power","httpunit","HttpUrlConnection","httrack","huaweisymantec","HubSpot ","Humanlinks","i2kconnect\\\/","Iblog","ichiro","Id-search","IdeelaborPlagiaat","IDG Twitter Links Resolver","IDwhois\\\/","Iframely","igdeSpyder","iGooglePortal","IlTrovatore","Image Fetch","Image Sucker","ImageEngine\\\/","ImageVisu\\\/","Imagga","imagineeasy","imgsizer","InAGist","inbound\\.li parser","InDesign%20CC","Indy Library","InetURL","infegy","infohelfer","InfoTekies","InfoWizards Reciprocal Link","inpwrd\\.com","instabid","Instapaper","Integrity","integromedb","Intelliseek","InterGET","internet_archive","Internet Ninja","InternetSeer","internetVista monitor","internetwache","intraVnews","IODC","IOI","iplabel","ips-agent","IPS\\\/[0-9]","IPWorks HTTP\\\/S Component","iqdb\\\/","Iria","Irokez","isitup\\.org","iskanie","isUp\\.li","iThemes Sync\\\/","IZaBEE","iZSearch","JAHHO","janforman","Jaunt\\\/","Java.*outbrain","javelin\\.io","Jbrofuzz","Jersey\\\/","JetCar","Jigsaw","Jobboerse","JobFeed discovery","Jobg8 URL Monitor","jobo","Jobrapido","Jobsearch1\\.5","JoinVision Generic","JolokiaPwn","Joomla","Jorgee","JS-Kit","JustView","Kaspersky Lab CFR link resolver","Kelny\\\/","Kerrigan\\\/","KeyCDN","Keyword Density","Keywords Research","khttp\\\/","KickFire","KimonoLabs\\\/","Kml-Google","knows\\.is","KOCMOHABT","kouio","kubectl","kube-probe","kulturarw3","KumKie","L\\.webis","Larbin","Lavf\\\/","LeechFTP","LeechGet","letsencrypt","Lftp","LibVLC","LibWeb","Libwhisker","libwww","Licorne","Liferea\\\/","Lightspeedsystems","Lighthouse","Likse","limber\\.io","Link Valet","link_thumbnailer","LinkAlarm\\\/","linkCheck","linkdex","LinkExaminer","linkfluence","linkpeek","LinkScan","LinksManager","LinkPreview","LinkTiger","LinkWalker","Lipperhey","Litemage_walker","livedoor ScreenShot","LoadImpactRload","localsearch-web","LongURL API","longurl-r-package","looid\\.com","looksystems\\.net","ltx71","lua-resty-http","Lush Http Client","lwp-request","lwp-trivial","LWP::Simple","lycos","LYT\\.SR","mabontland","Mag-Net","MagpieRSS","Mail\\.Ru","MailChimp","Majestic12","makecontact\\\/","Mandrill","MapperCmd","marketinggrader","MarkMonitor","MarkWatch","Mass Downloader","masscan\\\/","Mata Hari","Mediametric","Mediapartners-Google","mediawords","MegaIndex\\.ru","MeltwaterNews","Melvil Rawi","MemGator","Metaspinner","MetaURI","MFC_Tear_Sample","Microsearch","Microsoft\\.Data\\.Mashup","Microsoft Office ","Microsoft Outlook","Microsoft Windows Network Diagnostics","Microsoft-WebDAV-MiniRedir","Microsoft Data Access","MIDown tool","MIIxpc","Mindjet","Miniature\\.io","Miniflux","Mister PiX","mixdata dot com","mixed-content-scan","mixnode","Mnogosearch","mogimogi","Mojeek","Mojolicious \\(Perl\\)","Monit\\\/","monitis","Monitority\\\/","montastic","MonTools","Moreover","Morfeus Fucking Scanner","Morning Paper","MovableType","mowser","Mr\\.4x3 Powered","Mrcgiguy","MS Web Services Client Protocol","MSFrontPage","mShots","MuckRack\\\/","muhstik-scan","MVAClient","MxToolbox\\\/","myseosnapshot","nagios","Najdi\\.si","Name Intelligence","NameFo\\.com","Nameprotect","nationalarchives","Navroad","NearSite","Needle","Nessus","Net Vampire","NetAnts","NETCRAFT","NetLyzer","NetMechanic","NetNewsWire","Netpursual","netresearch","NetShelter ContentScan","Netsparker","NetTrack","Netvibes","NetZIP","Neustar WPM","NeutrinoAPI","NewRelicPinger","NewsBlur .*Finder","NewsGator","newsme","newspaper\\\/","NetSystemsResearch","Nexgate Ruby Client","nghttp2","NG-Search","Nibbler","NICErsPRO","Nikto","nineconnections","NLNZ_IAHarvester","Nmap Scripting Engine","node-superagent","node-urllib","node\\.io","Nodemeter","NodePing","nominet\\.org\\.uk","nominet\\.uk","Norton-Safeweb","Notifixious","notifyninja","NotionEmbedder","nuhk","nutch","Nuzzel","nWormFeedFinder","nyawc\\\/","Nymesis","NYU","Ocelli\\\/","Octopus","oegp","Offline Explorer","Offline Navigator","OgScrper","okhttp","omgili","OMSC","Online Domain Tools","OpenCalaisSemanticProxy","Openfind","OpenLinkProfiler","Openstat\\\/","OpenVAS","OPPO A33","Optimizer","Open Source RSS","Orbiter","OrgProbe\\\/","orion-semantics","Outlook-Express","Outlook-iOS","ow\\.ly","Owler","Owlin","ownCloud News","OxfordCloudService","Page Valet","page_verifier","page scorer","page2rss","PageFreezer","PageGrabber","PagePeeker","PageScorer","Pagespeed\\\/","Panopta","panscient","Papa Foto","parsijoo","Pavuk","PayPal IPN","pcBrowser","Pcore-HTTP","Pearltrees","PECL::HTTP","peerindex","Peew","PeoplePal","Perlu -","PhantomJS Screenshoter","PhantomJS\\\/","Photon\\\/","phpservermon","php-requests","Pi-Monster","Picscout","Picsearch","PictureFinder","Pimonster","ping\\.blo\\.gs","Pingability","PingAdmin\\.Ru","Pingdom","Pingoscope","PingSpot","pinterest\\.com","Pixray","Pizilla","Plagger\\\/","Ploetz \\+ Zeller","Plukkie","plumanalytics","PocketImageCache","PocketParser","Pockey","POE-Component-Client-HTTP","Polymail\\\/","Pompos","Porkbun","Port Monitor","postano","PostmanRuntime","postplanner\\.com","PostPost","postrank","PowerPoint\\\/","Prebid","Priceonomics Analysis Engine","PrintFriendly","PritTorrent","Prlog","probethenet","Project ?25499","prospectb2b","Protopage","ProWebWalker","proximic","PRTG Network Monitor","pshtt, https scanning","PTST ","PTST\\\/[0-9]+","Pump","python-httpx","Python-httplib2","python-requests","Python-urllib","Qirina Hurdler","QQDownload","QrafterPro","Qseero","Qualidator","QueryN Metasearch","queuedriver","QuiteRSS","Quora Link Preview","Qwantify","Radian6","RankActive","RankFlex","RankSonicSiteAuditor","Re-re Studio","ReactorNetty","Readability","RealDownload","RealPlayer%20Downloader","RebelMouse","Recorder","RecurPost\\\/","redback\\\/","ReederForMac","Reeder\\\/","ReGet","RepoMonkey","request\\.js","reqwest\\\/","ResponseCodeTest","RestSharp","Riddler","Rival IQ","Robosourcer","Robozilla","ROI Hunter","RPT-HTTPClient","RSSOwl","RyowlEngine","safe-agent-scanner","SalesIntelligent","Saleslift","Sendsay\\.Ru","SauceNAO","SBIder","sc-downloader","scalaj-http","Scamadviser-Frontend","scan\\.lol","ScanAlert","Scoop","scooter","ScoutJet","ScopeContentAG-HTTP-Client","ScoutURLMonitor","ScrapeBox Page Scanner","Scrapy","Screaming","ScreenShotService","Scrubby","Scrutiny\\\/","search\\.thunderstone","Search37","searchenginepromotionhelp","Searchestate","SearchExpress","SearchSight","Seeker","semanticdiscovery","semanticjuice","Semiocast HTTP client","Semrush","sentry\\\/","SEO Browser","Seo Servis","seo-nastroj\\.cz","seo4ajax","Seobility","SEOCentro","SeoCheck","SEOkicks","SEOlizer","Seomoz","SEOprofiler","SEOsearch","seoscanners","seositecheckup","SEOstats","servernfo","sexsearcher","Seznam","Shelob","Shodan","Shoppimon","ShopWiki","shortURL lengthener","ShortLinkTranslate","shrinktheweb","Sideqik","Siege","SimplePie","SimplyFast","Siphon","SISTRIX","Site-Shot\\\/","Site Sucker","Site24x7","SiteBar","Sitebeam","Sitebulb\\\/","SiteCondor","SiteExplorer","SiteGuardian","Siteimprove","SiteIndexed","Sitemap(s)? Generator","SitemapGenerator","SiteMonitor","Siteshooter B0t","SiteSnagger","SiteSucker","SiteTruth","Sitevigil","sitexy\\.com","SkypeUriPreview","Slack\\\/","slider\\.com","sli-systems\\.com","slurp","SlySearch","SmartDownload","SMRF URL Expander","SMUrlExpander","Snake","Snappy","SnapSearch","Snarfer\\\/","SniffRSS","sniptracker","Snoopy","SnowHaze Search","sogou web","SortSite","Sottopop","sovereign\\.ai","SpaceBison","SpamExperts","Spammen","Spanner","spaziodati","SPDYCheck","Specificfeeds","speedy","SPEng","Spinn3r","spray-can","Sprinklr ","spyonweb","sqlmap","Sqlworm","Sqworm","SSL Labs","ssl-tools","StackRambler","Statastico\\\/","Statically-Screenshot","StatusCake","Steeler","Stratagems Kumo","Stroke\\.cz","StudioFACA","StumbleUpon","suchen","Sucuri","summify","SuperHTTP","Surphace Scout","Suzuran","swcd ","Symfony BrowserKit","Symfony2 BrowserKit","SynHttpClient-Built","Sysomos","sysscan","Szukacz","T0PHackTeam","tAkeOut","Tarantula\\\/","Taringa UGC","TarmotGezgin","techiaith\\.cymru","Teleport","Telesoft","Telesphoreo","Telesphorep","Tenon\\.io","teoma","terrainformatica","Test Certificate Info","testuri","Tetrahedron","TextRazor Downloader","The Drop Reaper","The Expert HTML Source Viewer","The Knowledge AI","The Intraformant","theinternetrules","TheNomad","Thinklab","Thumbshots","ThumbSniper","Thumbor","timewe\\.net","TinEye","Tiny Tiny RSS","TLSProbe\\\/","Toata","topster","touche\\.com","Traackr\\.com","tracemyfile","Trackuity","TrapitAgent","Trendiction","Trendsmap","trendspottr","truwoGPS","TryJsoup","TulipChain","Turingos","Turnitin","tweetedtimes","Tweetminster","Tweezler\\\/","twibble","Twice","Twikle","Twingly","Twisted PageGetter","Typhoeus","ubermetrics-technologies","uclassify","UdmSearch","unchaos","unirest-java","ultimate_sitemap_parser","UniversalFeedParser","Unshorten\\.It","Untiny","UnwindFetchor","updated","updown\\.io daemon","Upflow","Uptimia","Urlcheckr","URL Verifier","URLitor","urlresolver","Urlstat","URLTester","UrlTrends Ranking Updater","URLy Warning","URLy\\.Warning","Vacuum","Vagabondo","VB Project","vBSEO","VCI","via ggpht\\.com GoogleImageProxy","Virusdie","visionutils","vkShare","VoidEYE","Voil","voltron","voyager\\\/","VSAgent\\\/","VSB-TUO\\\/","Vulnbusters Meter","VYU2","w3af\\.org","W3C_Unicorn","W3C-checklink","W3C-mobileOK","WAC-OFU","Wallpapers\\\/[0-9]+","WallpapersHD","WakeletLinkExpander","wangling","Wappalyzer","WatchMouse","WbSrch\\\/","WDT\\.io","web-capture\\.net","Web-sniffer","Web Auto","Web Collage","Web Enhancer","Web Fetch","Web Fuck","Web Pix","Web Sauger","Web spyder","Web Sucker","Webalta","Webauskunft","WebAuto","WebCapture","WebClient\\\/","webcollage","WebCookies","WebCopier","WebCorp","WebDataStats","WebDoc","WebEnhancer","WebFetch","WebFuck","WebGazer","WebGo IS","WebImageCollector","WebImages","WebIndex","webkit2png","WebLeacher","webmastercoffee","webmon ","WebPix","WebReaper","WebSauger","webscreenie","Webshag","Webshot","Website Quester","websitepulse agent","WebsiteQuester","Websnapr","WebSniffer","Webster","WebStripper","WebSucker","Webthumb\\\/","WebThumbnail","WebWhacker","WebZIP","WeLikeLinks","WEPA","WeSEE","wf84","Wfuzz\\\/","wget","WhatCMS","WhatsApp","WhatsMyIP","WhatWeb","WhereGoes\\?","Whibse","WhoAPI\\\/","WhoRunsCoinHive","Whynder Magnet","WinHTTP\\\/","WinHttp-Autoproxy-Service","Windows-RSS-Platform","WinPodder","wkhtmlto","wmtips","Woko","Wolfram HTTPClient","woorankreview","Word\\\/","WordPress\\\/","worldping-api","WordupinfoSearch","wotbox","WP Engine Install Performance API","wpif","wprecon\\.com survey","WPScan","wscheck","Wtrace","WWW-Collector-E","WWW-Mechanize","WWW::Document","WWW::Mechanize","www\\.monitor\\.us","WWWOFFLE","x09Mozilla","x22Mozilla","XaxisSemanticsClassifier","XenForo\\\/","Xenu Link Sleuth","XING-contenttabreceiver","xpymep([0-9]?)\\.exe","Y!J-(ASR|BSC)","Y\\!J-BRW","Yaanb","yacy","Yahoo Link Preview","YahooCacheSystem","YahooMailProxy","YahooYSMcm","YandeG","Yandex(?!Search)","yanga","yeti","Yo-yo","Yoleo Consumer","yomins\\.com","yoogliFetchAgent","YottaaMonitor","Your-Website-Sucks","yourls\\.org","YoYs\\.net","YP\\.PL","Zabbix","Zade","Zao","Zauba","Zemanta Aggregator","Zend_Http_Client","Zend\\\\Http\\\\Client","Zermelo","Zeus ","zgrab","ZnajdzFoto","ZnHTTP","Zombie\\.js","Zoom\\.Mac","ZoteroTranslationServer","ZyBorg","[a-z0-9\\-_]*(bot|crawl|archiver|transcoder|spider|uptime|validator|fetcher|cron|checker|reader|extractor|monitoring|analyzer|scraper)"]
|
1
|
+
[" YLT","^b0t$","^bluefish ","^Calypso v\\\/","^Corax","^COMODO DCV","^DangDang","^DavClnt","^DHSH","^FDM ","^git\\\/","^Goose\\\/","^Grabber","^HTTPClient\\\/","^Java\\\/","^Jeode\\\/","^Jetty\\\/","^Mail\\\/","^Mget","^Microsoft URL Control","^NG\\\/[0-9\\.]","^NING\\\/","^Nuclei","^PHP\\\/","^RMA\\\/","^Ruby|Ruby\\\/[0-9]","^Swurl ","^VSE\\\/[0-9]","^WordPress\\.com","^XRL\\\/[0-9]","^ZmEu","008\\\/","13TABS","192\\.comAgent","2GDPR\\\/","2ip\\.ru","404enemy","7Siters","80legs","a\\.pr-cy\\.ru","a3logics\\.in","A6-Indexer","Abonti","Aboundex","aboutthedomain","Accoona-AI-Agent","acebookexternalhit\\\/","acoon","acrylicapps\\.com\\\/pulp","Acunetix","AdAuth\\\/","adbeat","AddThis","ADmantX","AdminLabs","adressendeutschland","adreview\\\/","adscanner","Adstxtaggregator","adstxt-worker","adstxt\\.com","AffiliateLabz\\\/","agentslug","AHC","aihit","aiohttp\\\/","Airmail","akka-http\\\/","akula\\\/","alertra","alexa site audit","Alibaba\\.Security\\.Heimdall","Alligator","allloadin","AllSubmitter","alyze\\.info","amagit","^Amazon Simple Notification Service Agent$","Anarchie","AndroidDownloadManager","Anemone","AngleSharp","annotate_google","Anthill","Ant\\.com","Anturis Agent","AnyEvent-HTTP\\\/","Apache Droid","Apache OpenOffice","Apache-HttpAsyncClient","Apache-HttpClient","ApacheBench","Apexoo","apimon\\.de","APIs-Google","AportWorm\\\/","AppBeat\\\/","AppEngine-Google","AppleSyndication","Aprc\\\/[0-9]","Arachmo","arachnode","Arachnophilia","aria2","Arukereso","asafaweb","Asana\\\/","AskQuickly","Ask Jeeves","ASPSeek","Asterias","Astute","asynchttp","Attach","attohttpc","autocite","AutomaticWPTester","Autonomy","axios\\\/","AWS Security Scanner","B-l-i-t-z-B-O-T","Backlink-Ceck","backlink-check","BacklinkHttpStatus","BackStreet","BackupLand","BackWeb","Bad-Neighborhood","Badass","baidu\\.com","Bandit","basicstate","BatchFTP","Battleztar Bazinga","baypup\\\/","BazQux","BBBike","BCKLINKS","BDFetch","BegunAdvertising","Bewica-security-scan","Bidtellect","BigBozz","Bigfoot","biglotron","BingLocalSearch","BingPreview","binlar","biNu image cacher","Bitacle","biz_Directory","BKCTwitterUnshortener\\\/","Black Hole","Blackboard Safeassign","BlackWidow","BlockNote\\.Net","BlogBridge","Bloglines","Bloglovin","BlogPulseLive","BlogSearch","Blogtrottr","BlowFish","boitho\\.com-dc","Boost\\.Beast","BPImageWalker","Braintree-Webhooks","Branch Metrics API","Branch-Passthrough","Brandprotect","BrandVerity","Brandwatch","Brodie\\\/","Browsershots","BUbiNG","Buck\\\/","Buddy","BuiltWith","Bullseye","BunnySlippers","Burf Search","Butterfly\\\/","BuzzSumo","CAAM\\\/[0-9]","CakePHP","Calculon","Canary%20Mail","CaretNail","catexplorador","CC Metadata Scaper","Cegbfeieh","censys","centuryb.o.t9[at]gmail.com","Cerberian Drtrs","CERT\\.at-Statistics-Survey","cf-facebook","cg-eye","changedetection","ChangesMeter","Charlotte","CheckHost","checkprivacy","CherryPicker","ChinaClaw","Chirp\\\/","chkme\\.com","Chlooe","Chromaxa","CirrusExplorer","CISPA Vulnerability Notification","Citoid","CJNetworkQuality","Clarsentia","clips\\.ua\\.ac\\.be","Cloud mapping","CloudEndure","CloudFlare-AlwaysOnline","Cloudflare-Healthchecks","Cloudinary","cmcm\\.com","coccoc","cognitiveseo","colly -","CommaFeed","Commons-HttpClient","commonscan","contactbigdatafr","contentkingapp","Contextual Code Sites Explorer","convera","CookieReports","copyright sheriff","CopyRightCheck","Copyscape","cortex\\\/","Cosmos4j\\.feedback","Covario-IDS","Craw\\\/","Crescent","Crowsnest","Criteo","CSHttp","CSSCheck","Cula\\\/","curb","Curious George","curl","cuwhois\\\/","cybo\\.com","DAP\\\/NetHTTP","DareBoost","DatabaseDriverMysqli","DataCha0s","Datafeedwatch","Datanyze","DataparkSearch","dataprovider","DataXu","Daum(oa)?[ \\\/][0-9]","dBpoweramp","ddline","deeris","delve\\.ai","Demon","DeuSu","developers\\.google\\.com\\\/\\+\\\/web\\\/snippet\\\/","Devil","Digg","Digincore","DigitalPebble","Dirbuster","Discourse Forum Onebox","Disqus\\\/","Dispatch\\\/","DittoSpyder","dlvr","DMBrowser","DNSPod-reporting","docoloc","Dolphin http client","DomainAppender","DomainLabz","Domains Project\\\/","Donuts Content Explorer","dotMailer content retrieval","dotSemantic","downforeveryoneorjustme","Download Wonder","downnotifier","DowntimeDetector","Drip","drupact","Drupal \\(\\+http:\\\/\\\/drupal\\.org\\\/\\)","DTS Agent","dubaiindex","DuplexWeb-Google","DynatraceSynthetic","EARTHCOM","Easy-Thumb","EasyDL","Ebingbong","ec2linkfinder","eCairn-Grabber","eCatch","ECCP","eContext\\\/","Ecxi","EirGrabber","ElectricMonk","elefent","EMail Exractor","EMail Wolf","EmailWolf","Embarcadero","Embed PHP Library","Embedly","endo\\\/","europarchive\\.org","evc-batch","EventMachine HttpClient","Everwall Link Expander","Evidon","Evrinid","ExactSearch","ExaleadCloudview","Excel\\\/","exif","ExoRank","Exploratodo","Express WebPictures","Extreme Picture Finder","EyeNetIE","ezooms","facebookexternalhit","facebookexternalua","facebookplatform","fairshare","Faraday v","fasthttp","Faveeo","Favicon downloader","faviconkit","faviconarchive","FavOrg","Feed Wrangler","Feedable\\\/","Feedbin","FeedBooster","FeedBucket","FeedBunch\\\/","FeedBurner","feeder","Feedly","Feedshow\\\/","FeedshowOnline","Feedspot","FeedViewer\\\/","Feedwind\\\/","FeedZcollector","feeltiptop","Fetch API","Fetch\\\/[0-9]","Fever\\\/[0-9]","FHscan","Fiery%20Feeds","Filestack","Fimap","findlink","findthatfile","FlashGet","FlipboardBrowserProxy","FlipboardProxy","FlipboardRSS","Flock\\\/","Florienzh\\\/","fluffy","Flunky","flynxapp","forensiq","FoundSeoTool","http:\\\/\\\/www.neomo.de\\\/","free thumbnails","Freeuploader","FreshRSS","Funnelback","Fuzz Faster U Fool","G-i-g-a-b-o-t","g00g1e\\.net","ganarvisitas","gdnplus\\.com","geek-tools","Genieo","GentleSource","GetCode","Getintent","GetLinkInfo","getprismatic","GetRight","getroot","GetURLInfo\\\/","GetWeb","Geziyor","Ghost Inspector","GigablastOpenSource","GIS-LABS","github-camo","GitHub-Hookshot","github\\.com","Goldfire Server","Go [\\d\\.]* package http","Go http package","Go-Ahead-Got-It","Go-http-client","Go!Zilla","gobyus","Gofeed","gofetch","GomezAgent","gooblog","Goodzer\\\/","Google AppsViewer","Google Desktop","Google favicon","Google Keyword Suggestion","Google Keyword Tool","Google Page Speed Insights","Google-Podcast","Google PP Default","Google Search Console","Google Web Preview","Google-Ads-Creatives-Assistant","Google-Ads-Overview","Google-Adwords","Google-Apps-Script","Google-Calendar-Importer","Google-HotelAdsVerifier","Google-HTTP-Java-Client","Google-Publisher-Plugin","Google-Read-Aloud","Google-SearchByImage","Google-Site-Verification","Google-speakr","Google-Structured-Data-Testing-Tool","Google-Youtube-Links","google-xrawler","GoogleDocs","GoogleHC\\\/","GoogleProducer","GoogleSites","Google-Transparency-Report","Gookey","GoSpotCheck","gosquared-thumbnailer","Gotit","GoZilla","grabify","GrabNet","Grafula","Grammarly","GrapeFX","GreatNews","Gregarius","GRequests","grokkit","grouphigh","grub-client","gSOAP\\\/","GT::WWW","GTmetrix","GuzzleHttp","gvfs\\\/","HAA(A)?RTLAND http client","Haansoft","hackney\\\/","Hadi Agent","HappyApps-WebCheck","Hatena","Havij","HaxerMen","HeadlessChrome","HEADMasterSEO","HeartRails_Capture","help@dataminr\\.com","heritrix","Hexometer","historious","hkedcity","hledejLevne\\.cz","Hloader","HMView","Holmes","HonesoSearchEngine","HootSuite Image proxy","Hootsuite-WebFeed","hosterstats","HostTracker","ht:\\\/\\\/check","htdig","HTMLparser","htmlyse","HTTP Banner Detection","HTTP_Compression_Test","http_request2","http_requester","http-get","HTTP-Header-Abfrage","http-kit","http-request\\\/","HTTP-Tiny","HTTP::Lite","http\\.rb\\\/","http_get","HttpComponents","httphr","HTTPMon","HTTPie","httpRequest","httpscheck","httpssites_power","httpunit","HttpUrlConnection","httrack","huaweisymantec","HubSpot ","HubSpot-Link-Resolver","Humanlinks","i2kconnect\\\/","Iblog","ichiro","Id-search","IdeelaborPlagiaat","IDG Twitter Links Resolver","IDwhois\\\/","Iframely","igdeSpyder","iGooglePortal","IlTrovatore","Image Fetch","Image Sucker","ImageEngine\\\/","ImageVisu\\\/","Imagga","imagineeasy","imgsizer","InAGist","inbound\\.li parser","InDesign%20CC","Indy Library","InetURL","infegy","infohelfer","InfoTekies","InfoWizards Reciprocal Link","inpwrd\\.com","instabid","Instapaper","Integrity","integromedb","Intelliseek","InterGET","internet_archive","Internet Ninja","InternetSeer","internetVista monitor","internetwache","intraVnews","IODC","IOI","iplabel","ips-agent","IPS\\\/[0-9]","IPWorks HTTP\\\/S Component","iqdb\\\/","Iria","Irokez","isitup\\.org","iskanie","isUp\\.li","iThemes Sync\\\/","IZaBEE","iZSearch","JAHHO","janforman","Jaunt\\\/","Java.*outbrain","javelin\\.io","Jbrofuzz","Jersey\\\/","JetCar","Jigsaw","Jobboerse","JobFeed discovery","Jobg8 URL Monitor","jobo","Jobrapido","Jobsearch1\\.5","JoinVision Generic","JolokiaPwn","Joomla","Jorgee","JS-Kit","JustView","Kaspersky Lab CFR link resolver","Kelny\\\/","Kerrigan\\\/","KeyCDN","Keyword Density","Keywords Research","khttp\\\/","KickFire","KimonoLabs\\\/","Kml-Google","knows\\.is","KOCMOHABT","kouio","kubectl","kube-probe","kulturarw3","KumKie","L\\.webis","Larbin","Lavf\\\/","LeechFTP","LeechGet","letsencrypt","Lftp","LibVLC","LibWeb","Libwhisker","libwww","Licorne","Liferea\\\/","Lightspeedsystems","Lighthouse","Likse","limber\\.io","Link Valet","link_thumbnailer","LinkAnalyser","LinkAlarm\\\/","linkCheck","linkdex","LinkExaminer","linkfluence","linkpeek","LinkScan","LinksManager","LinkPreview","LinkTiger","LinkWalker","Lipperhey","Litemage_walker","livedoor ScreenShot","LoadImpactRload","localsearch-web","LongURL API","longurl-r-package","looid\\.com","looksystems\\.net","ltx71","lua-resty-http","Lush Http Client","lwp-request","lwp-trivial","LWP::Simple","lycos","LYT\\.SR","mabontland","MacOutlook\\\/","Mag-Net","MagpieRSS","Mail\\.Ru","MailChimp","Majestic12","makecontact\\\/","Mandrill","MapperCmd","marketinggrader","MarkMonitor","MarkWatch","Mass Downloader","masscan\\\/","Mata Hari","mattermost","Mediametric","Mediapartners-Google","mediawords","MegaIndex\\.ru","MeltwaterNews","Melvil Rawi","MemGator","Metaspinner","MetaURI","MFC_Tear_Sample","Microsearch","Microsoft\\.Data\\.Mashup","Microsoft Office","Microsoft Outlook","Microsoft Windows Network Diagnostics","Microsoft-WebDAV-MiniRedir","Microsoft Data Access","MIDown tool","MIIxpc","Mindjet","Miniature\\.io","Miniflux","Mister PiX","mixdata dot com","mixed-content-scan","mixnode","Mnogosearch","mogimogi","Mojeek","Mojolicious \\(Perl\\)","Monit\\\/","monitis","Monitority\\\/","montastic","MonTools","Moreover","Morfeus Fucking Scanner","Morning Paper","MovableType","mowser","Mr\\.4x3 Powered","Mrcgiguy","MS Web Services Client Protocol","MSFrontPage","mShots","MuckRack\\\/","muhstik-scan","MVAClient","MxToolbox\\\/","myseosnapshot","nagios","Najdi\\.si","Name Intelligence","NameFo\\.com","Nameprotect","nationalarchives","Navroad","NearSite","Needle","Nessus","Net Vampire","NetAnts","NETCRAFT","NetLyzer","NetMechanic","NetNewsWire","Netpursual","netresearch","NetShelter ContentScan","Netsparker","NetTrack","Netvibes","NetZIP","Neustar WPM","NeutrinoAPI","NewRelicPinger","NewsBlur .*Finder","NewsGator","newsme","newspaper\\\/","NetSystemsResearch","Nexgate Ruby Client","nghttp2","NG-Search","Nibbler","NICErsPRO","Nikto","nineconnections","NLNZ_IAHarvester","Nmap Scripting Engine","node-superagent","node-urllib","node\\.io","Nodemeter","NodePing","nominet\\.org\\.uk","nominet\\.uk","Norton-Safeweb","Notifixious","notifyninja","NotionEmbedder","nuhk","nutch","Nuzzel","nWormFeedFinder","nyawc\\\/","Nymesis","NYU","Observatory\\\/","Ocelli\\\/","Octopus","oegp","Offline Explorer","Offline Navigator","OgScrper","okhttp","omgili","OMSC","Online Domain Tools","OpenCalaisSemanticProxy","Openfind","OpenLinkProfiler","Openstat\\\/","OpenVAS","OPPO A33","Optimizer","Open Source RSS","Orbiter","OrgProbe\\\/","orion-semantics","Outlook-Express","Outlook-iOS","ow\\.ly","Owler","Owlin","ownCloud News","OxfordCloudService","Page Valet","page_verifier","page scorer","page2rss","PageFreezer","PageGrabber","PagePeeker","PageScorer","Pagespeed\\\/","Panopta","panscient","Papa Foto","parsijoo","Pavuk","PayPal IPN","pcBrowser","Pcore-HTTP","PDF24 URL To PDF","Pearltrees","PECL::HTTP","peerindex","Peew","PeoplePal","Perlu -","PhantomJS Screenshoter","PhantomJS\\\/","Photon\\\/","phpservermon","php-requests","Pi-Monster","Picscout","Picsearch","PictureFinder","Pimonster","ping\\.blo\\.gs","Pingability","PingAdmin\\.Ru","Pingdom","Pingoscope","PingSpot","pinterest\\.com","Pixray","Pizilla","Plagger\\\/","Pleroma ","Ploetz \\+ Zeller","Plukkie","plumanalytics","PocketImageCache","PocketParser","Pockey","PodcastAddict\\\/","POE-Component-Client-HTTP","Polymail\\\/","Pompos","Porkbun","Port Monitor","postano","PostmanRuntime","postplanner\\.com","PostPost","postrank","PowerPoint\\\/","Prebid","Prerender","Priceonomics Analysis Engine","PrintFriendly","PritTorrent","Prlog","probethenet","Project ?25499","Project-Resonance","prospectb2b","Protopage","ProWebWalker","proximic","PRTG Network Monitor","pshtt, https scanning","PTST ","PTST\\\/[0-9]+","Pump","python-httpx","Python-httplib2","python-requests","Python-urllib","Qirina Hurdler","QQDownload","QrafterPro","Qseero","Qualidator","QueryN Metasearch","queuedriver","QuiteRSS","Quora Link Preview","Qwantify","Radian6","Railgun\\\/","RankActive","RankFlex","RankSonicSiteAuditor","Re-re Studio","ReactorNetty","Readability","RealDownload","RealPlayer%20Downloader","RebelMouse","Recorder","RecurPost\\\/","redback\\\/","ReederForMac","Reeder\\\/","ReGet","RepoMonkey","request\\.js","reqwest\\\/","ResponseCodeTest","RestSharp","Riddler","Rival IQ","Robosourcer","Robozilla","ROI Hunter","RPT-HTTPClient","RSSOwl","RSSMix\\\/","RyowlEngine","safe-agent-scanner","SalesIntelligent","Saleslift","Sendsay\\.Ru","SauceNAO","SBIder","sc-downloader","scalaj-http","Scamadviser-Frontend","scan\\.lol","ScanAlert","Scoop","scooter","ScoutJet","ScopeContentAG-HTTP-Client","ScoutURLMonitor","ScrapeBox Page Scanner","Scrapy","Screaming","ScreenShotService","Scrubby","Scrutiny\\\/","search\\.thunderstone","Search37","searchenginepromotionhelp","Searchestate","SearchExpress","SearchSight","SearchWP","Seeker","semanticdiscovery","semanticjuice","Semiocast HTTP client","Semrush","sentry\\\/","SEO Browser","Seo Servis","seo-nastroj\\.cz","seo4ajax","Seobility","SEOCentro","SeoCheck","SEOkicks","SEOlizer","Seomoz","SEOprofiler","SEOsearch","seoscanners","seositecheckup","SEOstats","servernfo","sexsearcher","Seznam","Shelob","Shodan","Shoppimon","ShopWiki","shortURL lengthener","ShortLinkTranslate","shrinktheweb","Sideqik","Siege","SimplePie","SimplyFast","Siphon","SISTRIX","Site-Shot\\\/","Site Sucker","Site24x7","SiteBar","Sitebeam","Sitebulb\\\/","SiteCondor","SiteExplorer","SiteGuardian","Siteimprove","SiteIndexed","Sitemap(s)? Generator","SitemapGenerator","SiteMonitor","Siteshooter B0t","SiteSnagger","SiteSucker","SiteTruth","Sitevigil","sitexy\\.com","SkypeUriPreview","Slack\\\/","slider\\.com","sli-systems\\.com","slurp","SlySearch","SmartDownload","SMRF URL Expander","SMUrlExpander","Snake","Snappy","SnapSearch","Snarfer\\\/","SniffRSS","sniptracker","Snoopy","SnowHaze Search","sogou web","SortSite","Sottopop","sovereign\\.ai","SpaceBison","SpamExperts","Spammen","Spanner","spaziodati","SPDYCheck","Specificfeeds","speedy","SPEng","Spinn3r","spray-can","Sprinklr ","spyonweb","sqlmap","Sqlworm","Sqworm","SSL Labs","ssl-tools","StackRambler","Statastico\\\/","Statically-Screenshot","StatusCake","Steeler","Stratagems Kumo","Stripe\\\/","Stroke\\.cz","StudioFACA","StumbleUpon","suchen","Sucuri","summify","SuperHTTP","Surphace Scout","Suzuran","swcd ","Symfony BrowserKit","Symfony2 BrowserKit","Syndirella\\\/","SynHttpClient-Built","Sysomos","sysscan","Szukacz","T0PHackTeam","tAkeOut","Tarantula\\\/","Taringa UGC","TarmotGezgin","tchelebi\\.io","techiaith\\.cymru","Teleport","Telesoft","Telesphoreo","Telesphorep","Tenon\\.io","teoma","terrainformatica","Test Certificate Info","testuri","Tetrahedron","TextRazor Downloader","The Drop Reaper","The Expert HTML Source Viewer","The Knowledge AI","The Intraformant","theinternetrules","TheNomad","Thinklab","Thumbshots","ThumbSniper","Thumbor","timewe\\.net","TinEye","Tiny Tiny RSS","TLSProbe\\\/","Toata","topster","touche\\.com","Traackr\\.com","tracemyfile","Trackuity","TrapitAgent","Trendiction","Trendsmap","trendspottr","truwoGPS","TryJsoup","TulipChain","Turingos","Turnitin","tweetedtimes","Tweetminster","Tweezler\\\/","twibble","Twice","Twikle","Twingly","Twisted PageGetter","Typhoeus","ubermetrics-technologies","uclassify","UdmSearch","unchaos","unirest-java","ultimate_sitemap_parser","UniversalFeedParser","Unshorten\\.It","Untiny","UnwindFetchor","updated","updown\\.io daemon","Upflow","Uptimia","Urlcheckr","URL Verifier","URLitor","urlresolver","Urlstat","URLTester","UrlTrends Ranking Updater","URLy Warning","URLy\\.Warning","Vacuum","Vagabondo","VB Project","vBSEO","VCI","via ggpht\\.com GoogleImageProxy","Virusdie","visionutils","vkShare","VoidEYE","Voil","voltron","voyager\\\/","VSAgent\\\/","VSB-TUO\\\/","Vulnbusters Meter","VYU2","w3af\\.org","W3C_Unicorn","W3C-checklink","W3C-mobileOK","WAC-OFU","Wallpapers\\\/[0-9]+","WallpapersHD","WakeletLinkExpander","wangling","Wappalyzer","WatchMouse","WbSrch\\\/","WDT\\.io","web-capture\\.net","Web-sniffer","Web Auto","Web Collage","Web Enhancer","Web Fetch","Web Fuck","Web Pix","Web Sauger","Web spyder","Web Sucker","Webalta","Webauskunft","WebAuto","WebCapture","WebClient\\\/","webcollage","WebCookies","WebCopier","WebCorp","WebDataStats","WebDoc","WebEnhancer","WebFetch","WebFuck","WebGazer","WebGo IS","WebImageCollector","WebImages","WebIndex","webkit2png","WebLeacher","webmastercoffee","webmon ","WebPix","WebReaper","WebSauger","webscreenie","Webshag","Webshot","Website Quester","websitepulse agent","WebsiteQuester","Websnapr","WebSniffer","Webster","WebStripper","WebSucker","Webthumb\\\/","WebThumbnail","WebWhacker","WebZIP","WeLikeLinks","WEPA","WeSEE","wf84","Wfuzz\\\/","wget","WhatCMS","WhatsApp","WhatsMyIP","WhatWeb","WhereGoes\\?","Whibse","WhoAPI\\\/","WhoRunsCoinHive","Whynder Magnet","WinHTTP\\\/","WinHttp-Autoproxy-Service","Windows-RSS-Platform","WinPodder","wkhtmlto","wmtips","Woko","Wolfram HTTPClient","woorankreview","Word\\\/","WordPress\\\/","worldping-api","WordupinfoSearch","wotbox","WP Engine Install Performance API","WP Rocket","wpif","wprecon\\.com survey","WPScan","wscheck","Wtrace","WWW-Collector-E","WWW-Mechanize","WWW::Document","WWW::Mechanize","www\\.monitor\\.us","WWWOFFLE","x09Mozilla","x22Mozilla","XaxisSemanticsClassifier","XenForo\\\/","Xenu Link Sleuth","XING-contenttabreceiver","xpymep([0-9]?)\\.exe","Y!J-(ASR|BSC)","Y\\!J-BRW","Yaanb","yacy","Yahoo Link Preview","YahooCacheSystem","YahooMailProxy","YahooYSMcm","YandeG","Yandex(?!Search)","yanga","yeti","Yo-yo","Yoleo Consumer","yomins\\.com","yoogliFetchAgent","YottaaMonitor","Your-Website-Sucks","yourls\\.org","YoYs\\.net","YP\\.PL","Zabbix","Zade","Zao","Zauba","Zemanta Aggregator","Zend_Http_Client","Zend\\\\Http\\\\Client","Zermelo","Zeus ","zgrab","ZnajdzFoto","ZnHTTP","Zombie\\.js","Zoom\\.Mac","ZoteroTranslationServer","ZyBorg","[a-z0-9\\-_]*(bot|crawl|archiver|transcoder|spider|uptime|validator|fetcher|cron|checker|reader|extractor|monitoring|analyzer|scraper)"]
|
@@ -1 +1 @@
|
|
1
|
-
["Safari.[\\d\\.]*","Firefox.[\\d\\.]*"," Chrome.[\\d\\.]*","Chromium.[\\d\\.]*","MSIE.[\\d\\.]","Opera\\\/[\\d\\.]*","Mozilla.[\\d\\.]*","AppleWebKit.[\\d\\.]*","Trident.[\\d\\.]*","Windows NT.[\\d\\.]*","Android [\\d\\.]*","Macintosh.","Ubuntu","Linux","[ ]Intel","Mac OS X [\\d_]*","(like )?Gecko(.[\\d\\.]*)?","KHTML,","CriOS.[\\d\\.]*","CPU iPhone OS ([0-9_])* like Mac OS X","CPU OS ([0-9_])* like Mac OS X","iPod","compatible","x86_..","i686","x64","X11","rv:[\\d\\.]*","Version.[\\d\\.]*","WOW64","Win64","Dalvik.[\\d\\.]*"," \\.NET CLR [\\d\\.]*","Presto.[\\d\\.]*","Media Center PC","BlackBerry","Build","Opera Mini\\\/\\d{1,2}\\.\\d{1,2}\\.[\\d\\.]*\\\/\\d{1,2}\\.","Opera"," \\.NET[\\d\\.]*","cubot","; M bot","; CRONO","; B bot","; IDbot","; ID bot","; POWER BOT","
|
1
|
+
["Safari.[\\d\\.]*","Firefox.[\\d\\.]*"," Chrome.[\\d\\.]*","Chromium.[\\d\\.]*","MSIE.[\\d\\.]","Opera\\\/[\\d\\.]*","Mozilla.[\\d\\.]*","AppleWebKit.[\\d\\.]*","Trident.[\\d\\.]*","Windows NT.[\\d\\.]*","Android [\\d\\.]*","Macintosh.","Ubuntu","Linux","[ ]Intel","Mac OS X [\\d_]*","(like )?Gecko(.[\\d\\.]*)?","KHTML,","CriOS.[\\d\\.]*","CPU iPhone OS ([0-9_])* like Mac OS X","CPU OS ([0-9_])* like Mac OS X","iPod","compatible","x86_..","i686","x64","X11","rv:[\\d\\.]*","Version.[\\d\\.]*","WOW64","Win64","Dalvik.[\\d\\.]*"," \\.NET CLR [\\d\\.]*","Presto.[\\d\\.]*","Media Center PC","BlackBerry","Build","Opera Mini\\\/\\d{1,2}\\.\\d{1,2}\\.[\\d\\.]*\\\/\\d{1,2}\\.","Opera"," \\.NET[\\d\\.]*","cubot","; M bot","; CRONO","; B bot","; IDbot","; ID bot","; POWER BOT","OCTOPUS-CORE"]
|
@@ -5,12 +5,16 @@ module CrawlerDetect
|
|
5
5
|
module Library
|
6
6
|
DATA_CLASSES = [Library::Headers, Library::Exclusions, Library::Crawlers].freeze
|
7
7
|
|
8
|
+
@regexp_cache = {}
|
9
|
+
|
8
10
|
class << self
|
9
11
|
# @param param [String] Name of raw data
|
10
12
|
# @return [Regexp]
|
11
13
|
def get_regexp(param)
|
12
|
-
|
13
|
-
|
14
|
+
@regexp_cache[param] ||= begin
|
15
|
+
data = get_array(param)
|
16
|
+
%r{#{data.join('|')}}i
|
17
|
+
end
|
14
18
|
end
|
15
19
|
|
16
20
|
# @param param [String] Name of raw data
|
@@ -18,6 +22,12 @@ module CrawlerDetect
|
|
18
22
|
def get_array(param)
|
19
23
|
const_get("CrawlerDetect::Library::#{param.capitalize}").send(:data)
|
20
24
|
end
|
25
|
+
|
26
|
+
# @return [void]
|
27
|
+
def reset_cache
|
28
|
+
DATA_CLASSES.each(&:reload_data)
|
29
|
+
@regexp_cache = {}
|
30
|
+
end
|
21
31
|
end
|
22
32
|
end
|
23
33
|
end
|
data/lib/crawler_detect.rb
CHANGED
@@ -1,6 +1,6 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
-
require "
|
3
|
+
require "json"
|
4
4
|
require "qonfig"
|
5
5
|
|
6
6
|
require_relative "crawler_detect/config"
|
@@ -32,7 +32,7 @@ module CrawlerDetect
|
|
32
32
|
# @param config [Proc]
|
33
33
|
def setup!(&config)
|
34
34
|
@config = CrawlerDetect::Config.new(&config)
|
35
|
-
Library
|
35
|
+
Library.reset_cache
|
36
36
|
end
|
37
37
|
|
38
38
|
# @since 1.0.0
|
metadata
CHANGED
@@ -1,29 +1,15 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: crawler_detect
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0
|
4
|
+
version: 1.2.0
|
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: 2021-09-05 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
|
-
- !ruby/object:Gem::Dependency
|
14
|
-
name: oj
|
15
|
-
requirement: !ruby/object:Gem::Requirement
|
16
|
-
requirements:
|
17
|
-
- - ">="
|
18
|
-
- !ruby/object:Gem::Version
|
19
|
-
version: '3.0'
|
20
|
-
type: :runtime
|
21
|
-
prerelease: false
|
22
|
-
version_requirements: !ruby/object:Gem::Requirement
|
23
|
-
requirements:
|
24
|
-
- - ">="
|
25
|
-
- !ruby/object:Gem::Version
|
26
|
-
version: '3.0'
|
27
13
|
- !ruby/object:Gem::Dependency
|
28
14
|
name: qonfig
|
29
15
|
requirement: !ruby/object:Gem::Requirement
|
@@ -171,10 +157,10 @@ executables: []
|
|
171
157
|
extensions: []
|
172
158
|
extra_rdoc_files: []
|
173
159
|
files:
|
160
|
+
- ".github/workflows/build.yml"
|
174
161
|
- ".gitignore"
|
175
162
|
- ".rspec"
|
176
163
|
- ".rubocop.yml"
|
177
|
-
- ".travis.yml"
|
178
164
|
- CHANGELOG.md
|
179
165
|
- Gemfile
|
180
166
|
- Gemfile.lock
|
data/.travis.yml
DELETED
@@ -1,26 +0,0 @@
|
|
1
|
-
os: linux
|
2
|
-
dist: xenial
|
3
|
-
language: ruby
|
4
|
-
cache: bundler
|
5
|
-
before_install:
|
6
|
-
- gem install bundler
|
7
|
-
env:
|
8
|
-
- "TEST_GROUP=1"
|
9
|
-
- "TEST_GROUP=2"
|
10
|
-
- "TEST_GROUP=3"
|
11
|
-
- "TEST_GROUP=4"
|
12
|
-
rvm:
|
13
|
-
- 2.5
|
14
|
-
- 2.6
|
15
|
-
- 2.7
|
16
|
-
stages:
|
17
|
-
- lint
|
18
|
-
- test
|
19
|
-
script: bundle exec parallel_rspec spec/ -n 4 --only-group $TEST_GROUP --group-by runtime --runtime-log spec/fixtures/parallel_runtime_rspec.log
|
20
|
-
jobs:
|
21
|
-
fast_finish: true
|
22
|
-
include:
|
23
|
-
- stage: lint
|
24
|
-
rvm: 2.7
|
25
|
-
env: "TEST_GROUP=none"
|
26
|
-
script: bundle exec rubocop
|