let facebook bot fetch game images

Author: ornicar

app/controllers/Export.scala

@@ -15,7 +15,7 @@ object Export extends LilaController {
   private def env = Env.game
 
   def pgn(id: String) = Open { implicit ctx =>
-    NotForBots {
+    OnlyHumans {
       OptionFuResult(GameRepo game id) { game =>
         (game.pgnImport.ifTrue(~get("as") == "imported") match {
           case Some(i) => fuccess(i.pgn)
@@ -34,7 +34,7 @@ object Export extends LilaController {
   }
 
   def pdf(id: String) = Open { implicit ctx =>
-    NotForBots {
+    OnlyHumans {
       OptionResult(GameRepo game id) { game =>
         Ok.chunked(Enumerator.outputStream(env.pdfExport(game.id))).withHeaders(
           CONTENT_TYPE -> "application/pdf",
@@ -44,7 +44,7 @@ object Export extends LilaController {
   }
 
   def png(id: String) = Open { implicit ctx =>
-    NotForBots {
+    OnlyHumansAndFacebook {
       OptionResult(GameRepo game id) { game =>
         Ok.chunked(Enumerator.outputStream(env.pngExport(game))).withHeaders(
           CONTENT_TYPE -> "image/png",
@@ -53,10 +53,15 @@ object Export extends LilaController {
     }
   }
 
-  private def NotForBots(result: => Fu[Result])(implicit ctx: lila.api.Context) =
+  private def OnlyHumans(result: => Fu[Result])(implicit ctx: lila.api.Context) =
     if (HTTPRequest isBot ctx.req) fuccess(NotFound)
     else result
 
+  private def OnlyHumansAndFacebook(result: => Fu[Result])(implicit ctx: lila.api.Context) =
+    if (HTTPRequest isFacebookBot ctx.req) result
+    else if (HTTPRequest isBot ctx.req) fuccess(NotFound)
+    else result
+
   private def gameOpening(game: GameModel) =
     if (game.fromPosition || game.variant.exotic) none
     else chess.OpeningExplorer openingOf game.pgnMoves

modules/common/src/main/HTTPRequest.scala

@@ -24,9 +24,13 @@ object HTTPRequest {
   def sid(req: RequestHeader): Option[String] = req.session get "sid"
 
   private val isBotPattern =
-    """(?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|yandex|purebot|lingueebot|voyager|cyberpatrol|voilabot|baiduspider|citeseerxbot|spbot|twengabot|postrank|turnitinbot|scribdbot|page2rss|sitebot|linkdex|ezooms|dotbot|mail.ru|discobot|heritrix|findthatfile|europarchive.org|nerdbynature.bot|sistrixcrawler|ahrefsbot|aboundex|domaincrawler|wbsearchbot|summify|ccbot|edisterbot|seznambot|ec2linkfinder|gslfbot|aihitbot|intelium_bot|facebookexternalhit|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).*""".r.pattern
+    """(?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|yandex|purebot|lingueebot|""" +
+      """voyager|cyberpatrol|voilabot|baiduspider|citeseerxbot|spbot|twengabot|postrank|turnitinbot|scribdbot|page2rss|sitebot|linkdex|ezooms|dotbot|mail.ru|discobot|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).*""".r.pattern
 
   def isBot(req: RequestHeader): Boolean = userAgent(req) ?? { ua =>
     isBotPattern.matcher(ua).matches
   }
+
+  def isFacebookBot(req: RequestHeader) = req.userAgent ?? (_ contains "facebookexternalhit")
 }