crawler_detect 1.1.1 → 1.2.1

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 CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 6535ee2f876e0b1e05444bf0bb4a7a9082fd70ba4a454d7b1e2e9737b4b84d41
4
- data.tar.gz: ff05c16b5cd08416dfded4a8ca3c83ee73d2599dc2641aa8d212a7d3d72f3bd0
3
+ metadata.gz: a4411718d5f2c9a80ea433300e7aecffacf688865bf743c1255012c8b6aa5456
4
+ data.tar.gz: ac322dbc28c3a6d4f4dc87668235c9f853a4b71fffdcd7500d4ed22e485085e4
5
5
  SHA512:
6
- metadata.gz: 384c92b53a77f3b8280259897060f7fc74e6d0ac214d6469cfdd87a84c290286ae9bacace2875c2c033d69a77eb863cb7eee5053552d0c619b85f1f15ba9a79d
7
- data.tar.gz: 3904d9beef1ff2211881408d7ab2c60caf44c2103d07f8188a5c8d9454e58d274f1779ca4d0ad0ca53a548631062dd9f4f97c32c0ee9e811191b17c117b59db5
6
+ metadata.gz: c60e597777a7ddc600d706b881235f15b63463c65f9c688630cb3cfe5c88113fa428b00b5c9e1c08c19ab299c4cc18e5f668f929b8c3e690c67f8a3298659a54
7
+ data.tar.gz: f983aa1a0b9b70854ea9b0a9120be5b666cff6a1f7a60ff507e3893e6f85f01794a7116d434d6c07b0e1303d8dcfaa8694c88377d6f0a919a38a81fd5c9b324e
@@ -21,7 +21,7 @@ jobs:
21
21
  strategy:
22
22
  fail-fast: false
23
23
  matrix:
24
- ruby: [2.5, 2.6, 2.7]
24
+ ruby: [2.5, 2.6, 2.7, 3.0, 3.1]
25
25
  test-group: [1, 2, 3, 4]
26
26
  name: Ruby ${{ matrix.ruby }}, test-group ${{ matrix.test-group }}
27
27
  steps:
data/CHANGELOG.md CHANGED
@@ -3,6 +3,10 @@
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
+
6
10
  1.1.0
7
11
  ---------
8
12
  - Moves to Ruby's Stdlib JSON implementation to reduce dependencies
data/Gemfile.lock CHANGED
@@ -1,13 +1,13 @@
1
1
  PATH
2
2
  remote: .
3
3
  specs:
4
- crawler_detect (1.1.0)
5
- qonfig (~> 0.24)
4
+ crawler_detect (1.2.0)
5
+ qonfig (= 0.26)
6
6
 
7
7
  GEM
8
8
  remote: https://rubygems.org/
9
9
  specs:
10
- activesupport (6.0.3.1)
10
+ activesupport (6.0.4.7)
11
11
  concurrent-ruby (~> 1.0, >= 1.0.2)
12
12
  i18n (>= 0.7, < 2)
13
13
  minitest (~> 5.1)
@@ -19,31 +19,31 @@ GEM
19
19
  rubocop-rails (= 2.5.2)
20
20
  rubocop-rake (= 0.5.1)
21
21
  rubocop-rspec (= 1.38.1)
22
- ast (2.4.0)
23
- awesome_print (1.8.0)
24
- byebug (11.1.2)
25
- coderay (1.1.2)
26
- concurrent-ruby (1.1.6)
27
- diff-lcs (1.3)
28
- fuubar (2.5.0)
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 (1.5.0)
28
+ fuubar (2.5.1)
29
29
  rspec-core (~> 3.0)
30
30
  ruby-progressbar (~> 1.4)
31
- i18n (1.8.2)
31
+ i18n (1.10.0)
32
32
  concurrent-ruby (~> 1.0)
33
33
  jaro_winkler (1.5.4)
34
34
  method_source (1.0.0)
35
- minitest (5.14.1)
36
- parallel (1.19.1)
35
+ minitest (5.15.0)
36
+ parallel (1.21.0)
37
37
  parallel_tests (2.32.0)
38
38
  parallel
39
- parser (2.7.1.2)
40
- ast (~> 2.4.0)
41
- pry (0.13.1)
39
+ parser (3.1.1.0)
40
+ ast (~> 2.4.1)
41
+ pry (0.14.1)
42
42
  coderay (~> 1.1)
43
43
  method_source (~> 1.0)
44
- pry-byebug (3.9.0)
44
+ pry-byebug (3.8.0)
45
45
  byebug (~> 11.0)
46
- pry (~> 0.13.0)
46
+ pry (~> 0.10)
47
47
  pry-meta (0.0.10)
48
48
  awesome_print
49
49
  pry
@@ -52,26 +52,26 @@ GEM
52
52
  pry-remote (0.1.8)
53
53
  pry (~> 0.9)
54
54
  slop (~> 3.0)
55
- qonfig (0.24.1)
55
+ qonfig (0.26.0)
56
56
  rack (2.2.3)
57
57
  rack-test (1.1.0)
58
58
  rack (>= 1.0, < 3)
59
- rainbow (3.0.0)
60
- rake (13.0.1)
61
- rexml (3.2.4)
62
- rspec (3.9.0)
63
- rspec-core (~> 3.9.0)
64
- rspec-expectations (~> 3.9.0)
65
- rspec-mocks (~> 3.9.0)
66
- rspec-core (3.9.1)
67
- rspec-support (~> 3.9.1)
68
- rspec-expectations (3.9.1)
59
+ rainbow (3.1.1)
60
+ rake (13.0.6)
61
+ rexml (3.2.5)
62
+ rspec (3.11.0)
63
+ rspec-core (~> 3.11.0)
64
+ rspec-expectations (~> 3.11.0)
65
+ rspec-mocks (~> 3.11.0)
66
+ rspec-core (3.11.0)
67
+ rspec-support (~> 3.11.0)
68
+ rspec-expectations (3.11.0)
69
69
  diff-lcs (>= 1.2.0, < 2.0)
70
- rspec-support (~> 3.9.0)
71
- rspec-mocks (3.9.1)
70
+ rspec-support (~> 3.11.0)
71
+ rspec-mocks (3.11.0)
72
72
  diff-lcs (>= 1.2.0, < 2.0)
73
- rspec-support (~> 3.9.0)
74
- rspec-support (3.9.2)
73
+ rspec-support (~> 3.11.0)
74
+ rspec-support (3.11.0)
75
75
  rubocop (0.82.0)
76
76
  jaro_winkler (~> 1.5.1)
77
77
  parallel (~> 1.10)
@@ -90,13 +90,13 @@ GEM
90
90
  rubocop
91
91
  rubocop-rspec (1.38.1)
92
92
  rubocop (>= 0.68.1)
93
- ruby-progressbar (1.10.1)
93
+ ruby-progressbar (1.11.0)
94
94
  slop (3.6.0)
95
95
  thread_safe (0.3.6)
96
- tzinfo (1.2.7)
96
+ tzinfo (1.2.9)
97
97
  thread_safe (~> 0.1)
98
- unicode-display_width (1.7.0)
99
- zeitwerk (2.3.0)
98
+ unicode-display_width (1.8.0)
99
+ zeitwerk (2.5.4)
100
100
 
101
101
  PLATFORMS
102
102
  ruby
@@ -1 +1 @@
1
- [" YLT","^b0t$","^bluefish ","^Calypso v\\\/","^Corax","^COMODO DCV","^DangDang","^DavClnt","^DHSH","^FDM ","^git\\\/","^Goose\\\/","^Grabber","^HTTPClient\\\/","^Java\\\/","^Jeode\\\/","^Jetty\\\/","^Mail\\\/","^Mget","^Microsoft URL Control","^NG\\\/[0-9\\.]","^NING\\\/","^Nuclei","^PHP\\\/","^RMA\\\/","^Ruby|Ruby\\\/[0-9]","^Swurl ","^VSE\\\/[0-9]","^WordPress\\.com","^XRL\\\/[0-9]","^ZmEu","008\\\/","13TABS","192\\.comAgent","2GDPR\\\/","2ip\\.ru","404enemy","7Siters","80legs","a\\.pr-cy\\.ru","a3logics\\.in","A6-Indexer","Abonti","Aboundex","aboutthedomain","Accoona-AI-Agent","acebookexternalhit\\\/","acoon","acrylicapps\\.com\\\/pulp","Acunetix","AdAuth\\\/","adbeat","AddThis","ADmantX","AdminLabs","adressendeutschland","adreview\\\/","adscanner","Adstxtaggregator","adstxt-worker","adstxt\\.com","AffiliateLabz\\\/","agentslug","AHC","aihit","aiohttp\\\/","Airmail","akka-http\\\/","akula\\\/","alertra","alexa site audit","Alibaba\\.Security\\.Heimdall","Alligator","allloadin","AllSubmitter","alyze\\.info","amagit","^Amazon Simple Notification Service Agent$","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-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","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
+ [" YLT","^Aether","^Amazon Simple Notification Service Agent$","^Amazon-Route53-Health-Check-Service","^b0t$","^bluefish ","^Calypso v\\\/","^COMODO DCV","^Corax","^DangDang","^DavClnt","^DHSH","^docker\\\/[0-9]","^Expanse","^FDM ","^git\\\/","^Goose\\\/","^Grabber","^Gradle\\\/","^HTTPClient\\\/","^HTTPing","^Java\\\/","^Jeode\\\/","^Jetty\\\/","^Mail\\\/","^Mget","^Microsoft URL Control","^Mikrotik\\\/","^Netlab360","^NG\\\/[0-9\\.]","^NING\\\/","^npm\\\/","^Nuclei","^PHP-AYMAPI\\\/","^PHP\\\/","^pip\\\/","^pnpm\\\/","^RMA\\\/","^Ruby|Ruby\\\/[0-9]","^Swurl ","^TLS tester ","^twine\\\/","^ureq","^VSE\\\/[0-9]","^WordPress\\.com","^XRL\\\/[0-9]","^ZmEu","008\\\/","13TABS","192\\.comAgent","2GDPR\\\/","2ip\\.ru","404enemy","7Siters","80legs","a3logics\\.in","A6-Indexer","Abonti","Aboundex","aboutthedomain","Accoona-AI-Agent","acebookexternalhit\\\/","acoon","acrylicapps\\.com\\\/pulp","Acunetix","AdAuth\\\/","adbeat","AddThis","ADmantX","AdminLabs","adressendeutschland","adreview\\\/","adscanner","adstxt-worker","Adstxtaggregator","adstxt\\.com","Adyen HttpClient","AffiliateLabz\\\/","affilimate-puppeteer","agentslug","AHC","aihit","aiohttp\\\/","Airmail","akka-http\\\/","akula\\\/","alertra","alexa site audit","Alibaba\\.Security\\.Heimdall","Alligator","allloadin","AllSubmitter","alyze\\.info","amagit","Anarchie","AndroidDownloadManager","Anemone","AngleSharp","annotate_google","Anthill","Anturis Agent","Ant\\.com","AnyEvent-HTTP\\\/","Apache Ant\\\/","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\\\/","Ask Jeeves","AskQuickly","ASPSeek","Asterias","Astute","asynchttp","Attach","attohttpc","autocite","AutomaticWPTester","Autonomy","awin\\.com","AWS Security Scanner","axios\\\/","a\\.pr-cy\\.ru","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","Bitrix link preview","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","chatterino-api-cache","CheckHost","checkprivacy","CherryPicker","ChinaClaw","Chirp\\\/","chkme\\.com","Chlooe","Chromaxa","CirrusExplorer","CISPA Vulnerability Notification","CISPA Web Analyser","Citoid","CJNetworkQuality","Clarsentia","clips\\.ua\\.ac\\.be","Cloud mapping","CloudEndure","CloudFlare-AlwaysOnline","Cloudflare-Healthchecks","Cloudinary","cmcm\\.com","coccoc","cognitiveseo","ColdFusion","colly -","CommaFeed","Commons-HttpClient","commonscan","contactbigdatafr","contentkingapp","Contextual Code Sites Explorer","convera","CookieReports","copyright sheriff","CopyRightCheck","Copyscape","cortex\\\/","Cosmos4j\\.feedback","Covario-IDS","Craw\\\/","Crescent","Criteo","Crowsnest","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","Dispatch\\\/","Disqus\\\/","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","faviconarchive","faviconkit","FavOrg","Feed Wrangler","Feedable\\\/","Feedbin","FeedBooster","FeedBucket","FeedBunch\\\/","FeedBurner","feeder","Feedly","FeedshowOnline","Feedshow\\\/","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","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","Go http package","Go [\\d\\.]* package http","Go!Zilla","Go-Ahead-Got-It","Go-http-client","go-mtasts\\\/","gobuster","gobyus","Gofeed","gofetch","Goldfire Server","GomezAgent","gooblog","Goodzer\\\/","Google AppsViewer","Google Desktop","Google favicon","Google Keyword Suggestion","Google Keyword Tool","Google Page Speed Insights","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-Podcast","Google-Publisher-Plugin","Google-Read-Aloud","Google-SearchByImage","Google-Site-Verification","Google-SMTP-STS","Google-speakr","Google-Structured-Data-Testing-Tool","Google-Transparency-Report","google-xrawler","Google-Youtube-Links","GoogleDocs","GoogleHC\\\/","GoogleProber","GoogleProducer","GoogleSites","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","Hardenize","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-get","HTTP-Header-Abfrage","http-kit","http-request\\\/","HTTP-Tiny","HTTP::Lite","http:\\\/\\\/www.neomo.de\\\/","HttpComponents","httphr","HTTPie","HTTPMon","httpRequest","httpscheck","httpssites_power","httpunit","HttpUrlConnection","http\\.rb\\\/","HTTP_Compression_Test","http_get","http_request2","http_requester","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 Ninja","InternetSeer","internetVista monitor","internetwache","internet_archive","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","JungleKeyThumbnail","JustView","Kaspersky Lab CFR link resolver","Kelny\\\/","Kerrigan\\\/","KeyCDN","Keyword Density","Keywords Research","khttp\\\/","KickFire","KimonoLabs\\\/","Kml-Google","knows\\.is","KOCMOHABT","kouio","kube-probe","kubectl","kulturarw3","KumKie","Larbin","Lavf\\\/","leakix\\.net","LeechFTP","LeechGet","letsencrypt","Lftp","LibVLC","LibWeb","Libwhisker","libwww","Licorne","Liferea\\\/","Lighthouse","Lightspeedsystems","Likse","limber\\.io","Link Valet","LinkAlarm\\\/","LinkAnalyser","linkCheck","linkdex","LinkExaminer","linkfluence","linkpeek","LinkPreview","LinkScan","LinksManager","LinkTiger","LinkWalker","link_thumbnailer","Lipperhey","Litemage_walker","livedoor ScreenShot","LoadImpactRload","localsearch-web","LongURL API","longurl-r-package","looid\\.com","looksystems\\.net","ltx71","lua-resty-http","Lucee \\(CFML Engine\\)","Lush Http Client","lwp-request","lwp-trivial","LWP::Simple","lycos","LYT\\.SR","L\\.webis","mabontland","MacOutlook\\\/","Mag-Net","MagpieRSS","Mail::STS","MailChimp","Mail\\.Ru","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 Access","Microsoft Office","Microsoft Outlook","Microsoft Windows Network Diagnostics","Microsoft-WebDAV-MiniRedir","Microsoft\\.Data\\.Mashup","MIDown tool","MIIxpc","Mindjet","Miniature\\.io","Miniflux","mio_httpc","Miro-HttpClient","Mister PiX","mixdata dot com","mixed-content-scan","mixnode","Mnogosearch","mogimogi","Mojeek","Mojolicious \\(Perl\\)","monitis","Monitority\\\/","Monit\\\/","montastic","MonTools","Moreover","Morfeus Fucking Scanner","Morning Paper","MovableType","mowser","Mrcgiguy","Mr\\.4x3 Powered","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","NetSystemsResearch","nettle","NetTrack","Netvibes","NetZIP","Neustar WPM","NeutrinoAPI","NewRelicPinger","NewsBlur .*Finder","NewsGator","newsme","newspaper\\\/","Nexgate Ruby Client","NG-Search","nghttp2","Nibbler","NICErsPRO","NihilScio","Nikto","nineconnections","NLNZ_IAHarvester","Nmap Scripting Engine","node-fetch","node-superagent","node-urllib","Nodemeter","NodePing","node\\.io","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","Open Source RSS","OpenCalaisSemanticProxy","Openfind","OpenLinkProfiler","Openstat\\\/","OpenVAS","OPPO A33","Optimizer","Orbiter","OrgProbe\\\/","orion-semantics","Outlook-Express","Outlook-iOS","Owler","Owlin","ownCloud News","ow\\.ly","OxfordCloudService","page scorer","Page Valet","page2rss","PageFreezer","PageGrabber","PagePeeker","PageScorer","Pagespeed\\\/","PageThing","page_verifier","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\\\/","php-requests","phpservermon","Pi-Monster","Picscout","Picsearch","PictureFinder","Pimonster","Pingability","PingAdmin\\.Ru","Pingdom","Pingoscope","PingSpot","ping\\.blo\\.gs","pinterest\\.com","Pixray","Pizilla","Plagger\\\/","Pleroma ","Ploetz \\+ Zeller","Plukkie","plumanalytics","PocketImageCache","PocketParser","Pockey","PodcastAddict\\\/","POE-Component-Client-HTTP","Polymail\\\/","Pompos","Porkbun","Port Monitor","postano","postfix-mta-sts-resolver","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-httplib2","python-httpx","python-requests","Python-urllib","Qirina Hurdler","QQDownload","QrafterPro","Qseero","Qualidator","QueryN Metasearch","queuedriver","quic-go-HTTP\\\/","QuiteRSS","Quora Link Preview","Qwantify","Radian6","RadioPublicImageResizer","Railgun\\\/","RankActive","RankFlex","RankSonicSiteAuditor","RapidLoad\\\/","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","RSSMix\\\/","RSSOwl","RyowlEngine","safe-agent-scanner","SalesIntelligent","Saleslift","SAP NetWeaver Application Server","SauceNAO","SBIder","sc-downloader","scalaj-http","Scamadviser-Frontend","ScanAlert","scan\\.lol","Scoop","scooter","ScopeContentAG-HTTP-Client","ScoutJet","ScoutURLMonitor","ScrapeBox Page Scanner","Scrapy","Screaming","ScreenShotService","Scrubby","Scrutiny\\\/","Search37","searchenginepromotionhelp","Searchestate","SearchExpress","SearchSight","SearchWP","search\\.thunderstone","Seeker","semanticdiscovery","semanticjuice","Semiocast HTTP client","Semrush","Sendsay\\.Ru","sentry\\\/","SEO Browser","Seo Servis","seo-nastroj\\.cz","seo4ajax","Seobility","SEOCentro","SeoCheck","SEOkicks","SEOlizer","Seomoz","SEOprofiler","seoscanners","SEOsearch","seositecheckup","SEOstats","servernfo","sexsearcher","Seznam","Shelob","Shodan","Shoppimon","ShopWiki","ShortLinkTranslate","shortURL lengthener","shrinktheweb","Sideqik","Siege","SimplePie","SimplyFast","Siphon","SISTRIX","Site Sucker","Site-Shot\\\/","Site24x7","SiteBar","Sitebeam","Sitebulb\\\/","SiteCondor","SiteExplorer","SiteGuardian","Siteimprove","SiteIndexed","Sitemap(s)? Generator","SitemapGenerator","SiteMonitor","Siteshooter B0t","SiteSnagger","SiteSucker","SiteTruth","Sitevigil","sitexy\\.com","SkypeUriPreview","Slack\\\/","sli-systems\\.com","slider\\.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-","StatusCake","Steeler","Stratagems Kumo","Stripe\\\/","Stroke\\.cz","StudioFACA","StumbleUpon","suchen","Sucuri","summify","SuperHTTP","Surphace Scout","Suzuran","swcd ","Symfony BrowserKit","Symfony2 BrowserKit","Synapse\\\/","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 Intraformant","The Knowledge AI","theinternetrules","TheNomad","Thinklab","Thumbor","Thumbshots","ThumbSniper","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","ultimate_sitemap_parser","unchaos","unirest-java","UniversalFeedParser","unshortenit","Unshorten\\.It","Untiny","UnwindFetchor","updated","updown\\.io daemon","Upflow","Uptimia","URL Verifier","Urlcheckr","URLitor","urlresolver","Urlstat","URLTester","UrlTrends Ranking Updater","URLy Warning","URLy\\.Warning","URL\\\/Emacs","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-checklink","W3C-mobileOK","W3C_Unicorn","WAC-OFU","WakeletLinkExpander","WallpapersHD","Wallpapers\\\/[0-9]+","wangling","Wappalyzer","WatchMouse","WbSrch\\\/","WDT\\.io","Web Auto","Web Collage","Web Enhancer","Web Fetch","Web Fuck","Web Pix","Web Sauger","Web spyder","Web Sucker","web-capture\\.net","Web-sniffer","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","webtech\\\/","WebThumbnail","Webthumb\\\/","WebWhacker","WebZIP","WeLikeLinks","WEPA","WeSEE","wf84","Wfuzz\\\/","wget","WhatCMS","WhatsApp","WhatsMyIP","WhatWeb","WhereGoes\\?","Whibse","WhoAPI\\\/","WhoRunsCoinHive","Whynder Magnet","Windows-RSS-Platform","WinHttp-Autoproxy-Service","WinHTTP\\\/","WinPodder","wkhtmlto","wmtips","Woko","Wolfram HTTPClient","woorankreview","WordPress\\\/","WordupinfoSearch","Word\\\/","worldping-api","wotbox","WP Engine Install Performance API","WP Rocket","wpif","wprecon\\.com survey","WPScan","wscheck","Wtrace","WWW-Collector-E","WWW-Mechanize","WWW::Document","WWW::Mechanize","WWWOFFLE","www\\.monitor\\.us","x09Mozilla","x22Mozilla","XaxisSemanticsClassifier","XenForo\\\/","Xenu Link Sleuth","XING-contenttabreceiver","xpymep([0-9]?)\\.exe","Y!J-[A-Z][A-Z][A-Z]","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)"]
@@ -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
- data = get_array(param)
13
- %r{#{data.join('|')}}i
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
@@ -2,5 +2,5 @@
2
2
 
3
3
  # @since 0.1.0
4
4
  module CrawlerDetect
5
- VERSION = "1.1.1"
5
+ VERSION = "1.2.1"
6
6
  end
@@ -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::DATA_CLASSES.each(&:reload_data)
35
+ Library.reset_cache
36
36
  end
37
37
 
38
38
  # @since 1.0.0
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: 1.1.1
4
+ version: 1.2.1
5
5
  platform: ruby
6
6
  authors:
7
7
  - Pavel Kozlov
8
8
  autorequire:
9
9
  bindir: exe
10
10
  cert_chain: []
11
- date: 2020-12-29 00:00:00.000000000 Z
11
+ date: 2022-03-18 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: qonfig
@@ -201,7 +201,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
201
201
  - !ruby/object:Gem::Version
202
202
  version: '0'
203
203
  requirements: []
204
- rubygems_version: 3.1.2
204
+ rubygems_version: 3.3.5
205
205
  signing_key:
206
206
  specification_version: 4
207
207
  summary: 'CrawlerDetect: detect bots/crawlers'