Skip to content

Commit

Permalink
Add lots of bot user agents (#205)
Browse files Browse the repository at this point in the history
  • Loading branch information
MaxGiting committed Jun 19, 2017
1 parent fa55dc4 commit 55e98a6
Show file tree
Hide file tree
Showing 2 changed files with 42 additions and 1 deletion.
21 changes: 20 additions & 1 deletion src/Fixtures/Crawlers.php
Expand Up @@ -135,6 +135,7 @@ class Crawlers extends AbstractProvider
'CERT\.at-Statistics-Survey',
'cg-eye',
'changedetection',
'ChangesMeter\/',
'Charlotte',
'CheckHost',
'checkprivacy',
Expand Down Expand Up @@ -215,6 +216,7 @@ class Crawlers extends AbstractProvider
'facebookplatform',
'fairshare',
'Faraday v',
'fasthttp',
'Faveeo',
'Favicon downloader',
'FavOrg',
Expand Down Expand Up @@ -244,6 +246,7 @@ class Crawlers extends AbstractProvider
'free thumbnails',
'FreeWebMonitoring SiteChecker',
'Funnelback',
'G-i-g-a-b-o-t',
'g00g1e\.net',
'GAChecker',
'ganarvisitas\/[0-9]',
Expand All @@ -256,6 +259,7 @@ class Crawlers extends AbstractProvider
'GetURLInfo\/[0-9]',
'Ghost Inspector',
'GigablastOpenSource',
'GIS-LABS',
'github\.com\/',
'Go [\d\.]* package http',
'Go-http-client',
Expand Down Expand Up @@ -284,6 +288,7 @@ class Crawlers extends AbstractProvider
'GoogleDocs',
'GoogleHC\/',
'GoogleProducer',
'Gookey',
'GoScraper',
'GoSpotCheck',
'GoSquared-Status-Checker',
Expand All @@ -294,6 +299,7 @@ class Crawlers extends AbstractProvider
'grouphigh',
'grub-client',
'GTmetrix',
'GuzzleHttp',
'gvfs\/',
'HAA(A)?RTLAND http client',
'Hatena',
Expand All @@ -309,8 +315,10 @@ class Crawlers extends AbstractProvider
'ht:\/\/check',
'htdig',
'HTMLParser\/',
'http-get',
'HTTP-Header-Abfrage',
'http-kit',
'http-request\/',
'HTTP-Tiny',
'HTTP_Compression_Test',
'http_request2',
Expand Down Expand Up @@ -353,6 +361,7 @@ class Crawlers extends AbstractProvider
'internet_archive',
'InternetSeer',
'internetVista monitor',
'intraVnews',
'IODC',
'IOI',
'iplabel',
Expand All @@ -365,6 +374,7 @@ class Crawlers extends AbstractProvider
'iskanie',
'iZSearch',
'janforman',
'Jaunt\/',
'Jigsaw',
'Jobboerse',
'jobo',
Expand Down Expand Up @@ -406,13 +416,14 @@ class Crawlers extends AbstractProvider
'LongURL API',
'looksystems\.net',
'ltx71',
'lua-resty-http',
'lwp-trivial',
'lycos',
'LYT\.SR',
'mabontland',
'MagpieRSS',
'Mail.Ru',
'MailChimp\.com',
'MailChimp',
'Mandrill',
'MapperCmd',
'marketinggrader',
Expand Down Expand Up @@ -442,6 +453,7 @@ class Crawlers extends AbstractProvider
'Moreover',
'Morning Paper',
'mowser',
'MovableType',
'Mrcgiguy',
'mShots',
'MVAClient',
Expand Down Expand Up @@ -507,6 +519,7 @@ class Crawlers extends AbstractProvider
'peerindex',
'Peew',
'PhantomJS\/',
'PhantomJS Screenshoter',
'Photon\/',
'phpcrawl',
'phpservermon',
Expand Down Expand Up @@ -572,6 +585,7 @@ class Crawlers extends AbstractProvider
'SalesIntelligent',
'SauceNAO',
'SBIder',
'scalaj-http',
'Scoop',
'scooter',
'ScoutJet',
Expand Down Expand Up @@ -635,6 +649,7 @@ class Crawlers extends AbstractProvider
'Spinn3r',
'spray-can',
'Sprinklr ',
'sqlmap',
'spyonweb',
'Sqworm',
'SSL Labs',
Expand All @@ -652,6 +667,7 @@ class Crawlers extends AbstractProvider
'Symfony2 BrowserKit',
'SynHttpClient-Built',
'Sysomos',
'Symfony BrowserKit',
'T0PHackTeam',
'Tarantula\/',
'Taringa UGC',
Expand All @@ -671,7 +687,9 @@ class Crawlers extends AbstractProvider
'topster',
'touche.com',
'Traackr.com',
'TrapitAgent',
'truwoGPS',
'TulipChain',
'tweetedtimes\.com',
'Tweetminster',
'Tweezler\/',
Expand All @@ -680,6 +698,7 @@ class Crawlers extends AbstractProvider
'ubermetrics-technologies',
'uclassify',
'UdmSearch',
'UniversalFeedParser',
'Untiny',
'UnwindFetchor',
'updated',
Expand Down
22 changes: 22 additions & 0 deletions tests/crawlers.txt
Expand Up @@ -3112,3 +3112,25 @@ Sens.ai http://sovereign.ai/contact
eContext/1.0 (eContext Classification Engine)
Owler
Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Slack/1.2.6 Chrome/45.0.2454.85 AtomShell/0.34.3 Safari/537.36 Slack_SSB/1.2.6
Mozilla/5.0 (compatible; ChangesMeter/1.9.1; http://intuiware.com/apps/changes-meter)
Mozilla/5.0 (compatible; Gookey.co/1.0; +http://gookey.co/)
TrapitAgent/0.1 (feed processor; +http://trapit.com/about)
sqlmap/1.0-dev-nongit-201612050a8c (http://sqlmap.org)
UniversalFeedParser/3.3 +http://feedparser.org/
TulipChain/5.xx (http://ostermiller.org/tulipchain/) Java/1.x.1_0x (http://apple.com/) Mac_OS_X/10.2.8
scalaj-http/1.0
HggH PhantomJS Screenshoter
fasthttp
fasthttp, Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.101 Safari/537.36
lua-resty-http/0.10 (Lua) ngx_lua/10000
GIS-LABS:CertMon
GuzzleHttp/6.2.1 PHP/7.0.15-0ubuntu0.16.04.4
http-request/v0.7.0 (http://git.io/tl_S2w) node.js/v0.10.29
intraVnews/1.x
MailChimp
G-i-g-a-b-o-t
Symfony BrowserKit
VCPP71 http-get 1.0a
Jaunt/1.2
Mozilla/5.0 (compatible; Owler/0.4; +; )
MovableType/x.x

0 comments on commit 55e98a6

Please sign in to comment.