re = /^(Mozilla\/5\.0 (\(Linux; Android 6.0.1; Nexus 5X Build\/MMB29P\) )?(AppleWebKit\/[0-9]+\.[0-9]+ \(KHTML, like Gecko[\);] )?(Chrome\/[0-9]{2,3}\.[0-9]+\.[0-9]+\.[0-9]+ Mobile Safari\/[0-9]+\.[0-9]+ )?\(?compatible; )?Googlebot((-Image|-Video)?\/[0-9]\.[0-9]|-News)(;? \(?\+http:\/\/www\.google\.com\/bot\.html\)( Chrome\/[0-9]{2,3}\.[0-9]+\.[0-9]+\.[0-9]+ Safari\/[0-9]+\.[0-9]+)?)?$
/m
str = 'Valid GoogleBots:
Googlebot-Image/1.0
Googlebot-News
Googlebot-Video/1.0
Googlebot/2.1 (+http://www.google.com/bot.html)
Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; Googlebot/2.1; +http://www.google.com/bot.html) Chrome/80.20.123.1243 Safari/537.36
Mozilla/5.0 (Linux; Android 6.0.1; Nexus 5X Build/MMB29P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2213.123 Mobile Safari/537.36 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)
Invalid GoogleBots:
Googlebot
googlebot/2.1
Googlebot/2.1 (+http://www.google.com/bot.html) +IKAUE
'
# Print the match result
str.scan(re) do |match|
puts match.to_s
end
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Ruby, please visit: http://ruby-doc.org/core-2.2.0/Regexp.html