# Note: Robots IDs are in lower case, '_', ' ' and '+' are changed into '[_+\s]' and are quoted.\r
#-------------------------------------------------------\r
\r
+# RJC\r
+\r
+# Removed Baidu catchall because its picking up baidu.sogo.uc.UCBrowser which is a phone browser\r
+\r
+# Newly added from 2021-05-05\r
+# Adsbot\r
+# BW/\r
+# Bytespider\r
+# CheckMarkNetwork/\r
+# DuckDuckBot\r
+# Edg/\r
+# Foregenix Web Scan\r
+# IonCrawl\r
+# Linguee Bot\r
+# PetalBot\r
+# TkBot\r
+# vuhuvBot\r
\r
@RobotsSearchIDOrder_list1 = (\r
# Common robots (In robot file)\r
'Googlebot\-Video/',\r
'AdsBot\-Google[\x20]\(',\r
'AdsBot\-Google\-Mobile\-Apps',\r
+'Adsbot',\r
'Mediapartners-Google',\r
'Feedfetcher\-Google',\r
'Google\-Adwords\-Instant',\r
'Yahoo![\x20]Slurp',\r
'Baiduspider/',\r
'Baiduspider\-image',\r
-'baidu',\r
'YandexBot/',\r
'YandexImages/',\r
'YandexImageResizer',\r
'boitho\.com\-dc/',\r
'BoogleBot',\r
'BusinessBot:',\r
+'BW/',\r
+'Bytespider',\r
'CatchBot/',\r
'CB/Nutch',\r
'CCBot/',\r
+'CheckMarkNetwork/',\r
'Cliqzbot/',\r
'CMS[\x20]Crawler',\r
'Companybook\-Crawler',\r
'DomainStatsBot/',\r
'DotBot/',\r
'DuckDuckBot-Https',\r
+'DuckDuckBot',\r
'DuckDuckGo\-Favicons\-Bot/',\r
+'Edg/',\r
'ELinks/',\r
'ELinks[\x20]\(',\r
'EmailMarketingRobot/',\r
'flamingo',\r
'FlippyBearBot/',\r
'^foo$',\r
+'Foregenix[\x20]Web[\x20]Scan',\r
'FreeWebMonitoring[\x20]SiteChecker/',\r
'fujilabol',\r
'FurlBot/',\r
'Incutio[\x20]XML',\r
'IndeedBot',\r
'InfluenceBot',\r
+'IonCrawl',\r
'IRLbot/',\r
'IssueCrawler',\r
'istellabot/',\r
'Lightspeed',\r
'linkapediabot',\r
'metager\-linkchecker',\r
+'Linguee[\x20]Bot',\r
'linkchecker',\r
'LinkCheck',\r
'linkdexbot/',\r
'Pcore',\r
'pdffillerbot/',\r
'peopleman',\r
+'PetalBot',\r
'PhantomJS',\r
'PHP/5\.2\.8',\r
'Pinterestbot',\r
'Test[\x20]Spider',\r
'TestCrawler',\r
'The[\x20]Knowledge[\x20]AI',\r
+'TkBot',\r
'tracemyfile',\r
'trendiction',\r
'TurnitinBot/',\r
'VoilaBot',\r
'VORTEX/',\r
'voyager/',\r
+'vuhuvBot',\r
'W3C_Validator/',\r
'W3C\-checklink/',\r
'WBSearchBot/',\r
'Googlebot\-Video/','Googlebot-Video',\r
'AdsBot\-Google[\x20]\(','AdsBot-Google',\r
'AdsBot\-Google\-Mobile\-Apps','AdsBot-Google-Mobile-Apps',\r
+'Adsbot','Adsbot',\r
'Mediapartners\-Google','Mediapartners-Google',\r
'Feedfetcher\-Google','Feedfetcher-Google',\r
'Google\-Adwords\-Instant','Google-Adwords-Instant',\r
'Yahoo![\x20]Slurp','Yahoo! Slurp',\r
'Baiduspider/','Baiduspider',\r
'Baiduspider\-image','Baiduspider-image',\r
-'baidu','Baidu ( catchall )',\r
'YandexBot/','YandexBot',\r
'YandexImages/','YandexImages',\r
'YandexImageResizer','YandexImageResizer',\r
'boitho\.com\-dc/','boitho.com-dc',\r
'BoogleBot','BoogleBot',\r
'BusinessBot:','BusinessBot:',\r
+'BW/','BW',\r
+'Bytespider','Bytespider',\r
'CatchBot/','CatchBot',\r
'CB/Nutch','CB/Nutch',\r
'CCBot/','CCBot',\r
+'CheckMarkNetwork/','CheckMarkNetwork',\r
'Cliqzbot/','Cliqzbot',\r
'CMS[\x20]Crawler','CMS Crawler',\r
'Companybook\-Crawler','Companybook-Crawler',\r
'DomainStatsBot/','DomainStatsBot',\r
'DotBot/','DotBot',\r
'DuckDuckBot-Https','DuckDuckBot-Https',\r
+'DuckDuckBot','DuckDuckBot',\r
'DuckDuckGo\-Favicons\-Bot/','DuckDuckGo-Favicons-Bot',\r
+'Edg/','Edg',\r
'ELinks/','ELinks',\r
'ELinks[\x20]\(','ELinks (',\r
'EmailMarketingRobot/','EmailMarketingRobot',\r
'flamingo','Flamingo_SearchEngine',\r
'FlippyBearBot/','FlippyBearBot',\r
'^foo$','foo',\r
+'Foregenix[\x20]Web[\x20]Scan','Foregenix Web Scan',\r
'FreeWebMonitoring[\x20]SiteChecker/','FreeWebMonitoring SiteChecker',\r
'fujilabol','fujilabol',\r
'FurlBot/','FurlBot',\r
'Incutio[\x20]XML','Incutio XML',\r
'IndeedBot','IndeedBot',\r
'InfluenceBot','InfluenceBot',\r
+'IonCrawl','IonCrawl',\r
'IRLbot/','IRLbot',\r
'IssueCrawler','IssueCrawler',\r
'istellabot/','istellabot',\r
'Lightspeed','Lightspeed',\r
'linkapediabot','linkapediabot',\r
'metager\-linkchecker','metager-linkchecker',\r
+'Linguee[\x20]Bot','Linguee Bot',\r
'linkchecker','linkchecker',\r
'LinkCheck','LinkCheck',\r
'linkdexbot/','linkdexbot',\r
'Pcore','Pcore',\r
'pdffillerbot/','pdffillerbot',\r
'peopleman','peopleman',\r
+'PetalBot','PetalBot',\r
'PhantomJS','PhantomJS',\r
'PHP/5\.2\.8','PHP/5.2.8',\r
'Pinterestbot','Pinterestbot',\r
'Test[\x20]Spider','Test Spider',\r
'TestCrawler','TestCrawler',\r
'The[\x20]Knowledge[\x20]AI', 'The Knowledge AI',\r
+'TkBot','TkBot',\r
'tracemyfile','tracemyfile',\r
'trendiction','trendiction',\r
'TurnitinBot/','TurnitinBot',\r
'VoilaBot','VoilaBot',\r
'VORTEX/','VORTEX',\r
'voyager/','voyager',\r
+'vuhuvBot','vuhuvBot',\r
'W3C_Validator/','W3C_Validator',\r
'W3C\-checklink/','W3C-checklink',\r
'WBSearchBot/','WBSearchBot',\r