Skip to content

Commit

Permalink
Merge f0f32d4 into 624eab2
Browse files Browse the repository at this point in the history
  • Loading branch information
MaxGiting committed Jan 31, 2020
2 parents 624eab2 + f0f32d4 commit df3258a
Show file tree
Hide file tree
Showing 4 changed files with 57 additions and 2 deletions.
2 changes: 1 addition & 1 deletion raw/Crawlers.json

Large diffs are not rendered by default.

18 changes: 18 additions & 0 deletions raw/Crawlers.txt
Original file line number Diff line number Diff line change
Expand Up @@ -103,6 +103,7 @@ Asterias
Astute
asynchttp
Attach
attohttpc
autocite
AutomaticWPTester
Autonomy
Expand All @@ -127,6 +128,7 @@ BBBike
BCKLINKS
BDFetch
BegunAdvertising
Bewica-security-scan
Bidtellect
BigBozz
Bigfoot
Expand All @@ -141,13 +143,15 @@ 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
Expand Down Expand Up @@ -240,6 +244,7 @@ Daum(oa)?[ \/][0-9]
dBpoweramp
ddline
deeris
delve\.ai
Demon
DeuSu
developers\.google\.com\/\+\/web\/snippet\/
Expand All @@ -258,6 +263,7 @@ DNSPod-reporting
docoloc
Dolphin http client
DomainAppender
DomainLabz
Donuts Content Explorer
dotMailer content retrieval
dotSemantic
Expand Down Expand Up @@ -301,6 +307,7 @@ ExactSearch
ExaleadCloudview
Excel\/
exif
ExoRank
Exploratodo
Express WebPictures
Extreme Picture Finder
Expand Down Expand Up @@ -352,6 +359,7 @@ http:\/\/www.neomo.de\/
free thumbnails
Freeuploader
Funnelback
Fuzz Faster U Fool
G-i-g-a-b-o-t
g00g1e\.net
ganarvisitas
Expand Down Expand Up @@ -443,6 +451,7 @@ HEADMasterSEO
HeartRails_Capture
help@dataminr\.com
heritrix
Hexometer
historious
hkedcity
hledejLevne\.cz
Expand Down Expand Up @@ -589,6 +598,7 @@ Liferea\/
Lightspeedsystems
Lighthouse
Likse
limber\.io
Link Valet
link_thumbnailer
LinkAlarm\/
Expand All @@ -608,6 +618,7 @@ livedoor ScreenShot
LoadImpactRload
localsearch-web
LongURL API
longurl-r-package
looid\.com
looksystems\.net
ltx71
Expand Down Expand Up @@ -756,6 +767,7 @@ Optimizer
Orbiter
OrgProbe\/
orion-semantics
OSPScraper
Outlook-Express
Outlook-iOS
ow\.ly
Expand Down Expand Up @@ -835,6 +847,7 @@ PTST
PTST\/[0-9]+
Pulsepoint XT3 web scraper
Pump
python-httpx
Python-httplib2
python-requests
Python-urllib
Expand Down Expand Up @@ -875,6 +888,7 @@ Robozilla
ROI Hunter
RPT-HTTPClient
RSSOwl
RyowlEngine
safe-agent-scanner
SalesIntelligent
Saleslift
Expand All @@ -883,6 +897,7 @@ SauceNAO
SBIder
sc-downloader
scalaj-http
Scamadviser-Frontend
scan\.lol
ScanAlert
Scoop
Expand Down Expand Up @@ -916,6 +931,7 @@ Seobility
SEOCentro
SeoCheck
SEOkicks
SEOlizer
Seomoz
SEOprofiler
SEOsearch
Expand All @@ -929,6 +945,7 @@ Shelob
Shodan
Shoppimon
ShopWiki
shortURL lengthener
ShortLinkTranslate
shrinktheweb
Sideqik
Expand Down Expand Up @@ -1191,6 +1208,7 @@ WinPodder
wkhtmlto
wmtips
Woko
Wolfram HTTPClient
woorankreview
Word\/
WordPress\/
Expand Down
18 changes: 18 additions & 0 deletions src/Fixtures/Crawlers.php
Original file line number Diff line number Diff line change
Expand Up @@ -124,6 +124,7 @@ class Crawlers extends AbstractProvider
'Astute',
'asynchttp',
'Attach',
'attohttpc',
'autocite',
'AutomaticWPTester',
'Autonomy',
Expand All @@ -148,6 +149,7 @@ class Crawlers extends AbstractProvider
'BCKLINKS',
'BDFetch',
'BegunAdvertising',
'Bewica-security-scan',
'Bidtellect',
'BigBozz',
'Bigfoot',
Expand All @@ -162,13 +164,15 @@ class Crawlers extends AbstractProvider
'Blackboard Safeassign',
'BlackWidow',
'BlockNote\.Net',
'BlogBridge',
'Bloglines',
'Bloglovin',
'BlogPulseLive',
'BlogSearch',
'Blogtrottr',
'BlowFish',
'boitho\.com-dc',
'Boost\.Beast',
'BPImageWalker',
'Braintree-Webhooks',
'Branch Metrics API',
Expand Down Expand Up @@ -261,6 +265,7 @@ class Crawlers extends AbstractProvider
'dBpoweramp',
'ddline',
'deeris',
'delve\.ai',
'Demon',
'DeuSu',
'developers\.google\.com\/\+\/web\/snippet\/',
Expand All @@ -279,6 +284,7 @@ class Crawlers extends AbstractProvider
'docoloc',
'Dolphin http client',
'DomainAppender',
'DomainLabz',
'Donuts Content Explorer',
'dotMailer content retrieval',
'dotSemantic',
Expand Down Expand Up @@ -322,6 +328,7 @@ class Crawlers extends AbstractProvider
'ExaleadCloudview',
'Excel\/',
'exif',
'ExoRank',
'Exploratodo',
'Express WebPictures',
'Extreme Picture Finder',
Expand Down Expand Up @@ -373,6 +380,7 @@ class Crawlers extends AbstractProvider
'free thumbnails',
'Freeuploader',
'Funnelback',
'Fuzz Faster U Fool',
'G-i-g-a-b-o-t',
'g00g1e\.net',
'ganarvisitas',
Expand Down Expand Up @@ -464,6 +472,7 @@ class Crawlers extends AbstractProvider
'HeartRails_Capture',
'help@dataminr\.com',
'heritrix',
'Hexometer',
'historious',
'hkedcity',
'hledejLevne\.cz',
Expand Down Expand Up @@ -610,6 +619,7 @@ class Crawlers extends AbstractProvider
'Lightspeedsystems',
'Lighthouse',
'Likse',
'limber\.io',
'Link Valet',
'link_thumbnailer',
'LinkAlarm\/',
Expand All @@ -629,6 +639,7 @@ class Crawlers extends AbstractProvider
'LoadImpactRload',
'localsearch-web',
'LongURL API',
'longurl-r-package',
'looid\.com',
'looksystems\.net',
'ltx71',
Expand Down Expand Up @@ -777,6 +788,7 @@ class Crawlers extends AbstractProvider
'Orbiter',
'OrgProbe\/',
'orion-semantics',
'OSPScraper',
'Outlook-Express',
'Outlook-iOS',
'ow\.ly',
Expand Down Expand Up @@ -856,6 +868,7 @@ class Crawlers extends AbstractProvider
'PTST\/[0-9]+',
'Pulsepoint XT3 web scraper',
'Pump',
'python-httpx',
'Python-httplib2',
'python-requests',
'Python-urllib',
Expand Down Expand Up @@ -896,6 +909,7 @@ class Crawlers extends AbstractProvider
'ROI Hunter',
'RPT-HTTPClient',
'RSSOwl',
'RyowlEngine',
'safe-agent-scanner',
'SalesIntelligent',
'Saleslift',
Expand All @@ -904,6 +918,7 @@ class Crawlers extends AbstractProvider
'SBIder',
'sc-downloader',
'scalaj-http',
'Scamadviser-Frontend',
'scan\.lol',
'ScanAlert',
'Scoop',
Expand Down Expand Up @@ -937,6 +952,7 @@ class Crawlers extends AbstractProvider
'SEOCentro',
'SeoCheck',
'SEOkicks',
'SEOlizer',
'Seomoz',
'SEOprofiler',
'SEOsearch',
Expand All @@ -950,6 +966,7 @@ class Crawlers extends AbstractProvider
'Shodan',
'Shoppimon',
'ShopWiki',
'shortURL lengthener',
'ShortLinkTranslate',
'shrinktheweb',
'Sideqik',
Expand Down Expand Up @@ -1212,6 +1229,7 @@ class Crawlers extends AbstractProvider
'wkhtmlto',
'wmtips',
'Woko',
'Wolfram HTTPClient',
'woorankreview',
'Word\/',
'WordPress\/',
Expand Down
21 changes: 20 additions & 1 deletion tests/crawlers.txt
Original file line number Diff line number Diff line change
Expand Up @@ -3474,4 +3474,23 @@ HaxerMen
kubectl/v1.12.0 (linux/amd64) kubernetes/0ed3388
NetSystemsResearch studies the availability of various services across the internet. Our website is netsystemsresearch.com
Mozilla/5.0(Linux;Android 5.1.1;OPPO A33 Build/LMY47V;wv) AppleWebKit/537.36(KHTML,link Gecko) Version/4.0 Chrome/43.0.2357.121 Mobile Safari/537.36 LieBaoFast/4.51.3
sc-downloader/2.0 (http://www.searchconcepts.io)
sc-downloader/2.0 (http://www.searchconcepts.io)
[object Promise] delve.ai website analyse
attohttpc/0.9.0
Bewica-security-scan
BlogBridge 2.13 (http://www.blogbridge.com/)
Boost.Beast/248
DomainLabz
ExoRank
Fuzz Faster U Fool v1.0-rc1
Hexometer
longurl-r-package
looid.com Search Engine/0.1
Mozilla/5.0 (compatible; RyowlEngine/1.0; +https://ryowl.org)
Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:25.0; https://app.limber.io) Gecko/20100101 Firefox/25.0
OSPScraper (+https://www.opensyllabusproject.org)
python-httpx/0.11.1
shortURL lengthener/0.1 +http://kevindriscoll.info/
Scamadviser-Frontend
Wolfram HTTPClient 12.
SEOlizer/1.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.13) Gecko/20080311 Firefox/2.0.0.13

0 comments on commit df3258a

Please sign in to comment.