deepcrayon
/
lila
1
0
Fork 0
Code Releases Activity

add crawler UA

deepcrayonfish^2
Thibault Duplessis 2021-11-25 19:10:27 +01:00
parent c441518850
commit c8701601ab
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
modules/common/src/main/HTTPRequest.scala
View File

@ -58,7 +58,7 @@ object HTTPRequest {
def sid(req: RequestHeader): Option[String] = req.session get LilaCookie.sessionId
val isCrawler = UaMatcher {
"""(?i)googlebot|googlebot-mobile|googlebot-image|mediapartners-google|bingbot|slurp|java|wget|curl|commons-httpclient|python-urllib|libwww|httpunit|nutch|phpcrawl|msnbot|adidxbot|blekkobot|teoma|ia_archiver|gingercrawler|webmon|httrack|webcrawler|fast-webcrawler|fastenterprisecrawler|convera|biglotron|grub\.org|usinenouvellecrawler|antibot|netresearchserver|speedy|fluffy|jyxobot|bibnum\.bnf|findlink|exabot|gigabot|msrbot|seekbot|ngbot|panscient|yacybot|aisearchbot|ioi|ips-agent|tagoobot|mj12bot|dotbot|woriobot|yanga|buzzbot|mlbot|purebot|lingueebot|yandex\.com/bots|""" +
"""(?i)googlebot|googlebot-mobile|googlebot-image|mediapartners-google|bingbot|slurp|java|wget|curl|python-requests|commons-httpclient|python-urllib|libwww|httpunit|nutch|phpcrawl|msnbot|adidxbot|blekkobot|teoma|ia_archiver|gingercrawler|webmon|httrack|webcrawler|fast-webcrawler|fastenterprisecrawler|convera|biglotron|grub\.org|usinenouvellecrawler|antibot|netresearchserver|speedy|fluffy|jyxobot|bibnum\.bnf|findlink|exabot|gigabot|msrbot|seekbot|ngbot|panscient|yacybot|aisearchbot|ioi|ips-agent|tagoobot|mj12bot|dotbot|woriobot|yanga|buzzbot|mlbot|purebot|lingueebot|yandex\.com/bots|""" +
"""voyager|cyberpatrol|voilabot|baiduspider|citeseerxbot|spbot|twengabot|postrank|turnitinbot|scribdbot|page2rss|sitebot|linkdex|ezooms|dotbot|mail\.ru|discobot|zombie\.js|heritrix|findthatfile|europarchive\.org|nerdbynature\.bot|sistrixcrawler|ahrefsbot|aboundex|domaincrawler|wbsearchbot|summify|ccbot|edisterbot|seznambot|ec2linkfinder|gslfbot|aihitbot|intelium_bot|yeti|retrevopageanalyzer|lb-spider|sogou|lssbot|careerbot|wotbox|wocbot|ichiro|duckduckbot|lssrocketcrawler|drupact|webcompanycrawler|acoonbot|openindexspider|gnamgnamspider|web-archive-net\.com\.bot|backlinkcrawler|""" +
"""coccoc|integromedb|contentcrawlerspider|toplistbot|seokicks-robot|it2media-domain-crawler|ip-web-crawler\.com|siteexplorer\.info|elisabot|proximic|changedetection|blexbot|arabot|wesee:search|niki-bot|crystalsemanticsbot|rogerbot|360spider|psbot|interfaxscanbot|lipperheyseoservice|ccmetadatascaper|g00g1e\.net|grapeshotcrawler|urlappendbot|brainobot|fr-crawler|binlar|simplecrawler|simplecrawler|livelapbot|twitterbot|cxensebot|smtbot|facebookexternalhit|daumoa|sputnikimagebot|visionutils|yisouspider|parsijoobot|mediatoolkit\.com|semrushbot"""
}