diff --git a/kubernetes/cronjob-index.yaml b/kubernetes/cronjob-index.yaml index b378097..038c545 100644 --- a/kubernetes/cronjob-index.yaml +++ b/kubernetes/cronjob-index.yaml @@ -5,9 +5,12 @@ metadata: namespace: bioc-code-explorer spec: schedule: "*/15 * * * *" + concurrencyPolicy: Forbid + startingDeadlineSeconds: 60 jobTemplate: spec: ttlSecondsAfterFinished: 100 + activeDeadlineSeconds: 780 template: spec: securityContext: @@ -26,7 +29,7 @@ spec: cpu: 1000m memory: 2Gi requests: - cpu: 700m + cpu: 100m memory: 1Gi imagePullPolicy: Always image: grimbough/code.bioc-mirror-updater:0.1.6 diff --git a/kubernetes/cronjob-logrotate.yaml b/kubernetes/cronjob-logrotate.yaml index 3e649b8..fd72567 100644 --- a/kubernetes/cronjob-logrotate.yaml +++ b/kubernetes/cronjob-logrotate.yaml @@ -5,9 +5,12 @@ metadata: namespace: bioc-code-explorer spec: schedule: "0 0 * * *" # Daily at midnight + concurrencyPolicy: Forbid + startingDeadlineSeconds: 300 jobTemplate: spec: ttlSecondsAfterFinished: 600 + activeDeadlineSeconds: 3600 template: spec: securityContext: diff --git a/mirror-updater/utils.R b/mirror-updater/utils.R index c5c2b69..22ed1da 100644 --- a/mirror-updater/utils.R +++ b/mirror-updater/utils.R @@ -158,7 +158,9 @@ write_robots_txt <- function(pkgs, output_file = "/var/shared/robots.txt") { "GPTBot", "AhrefsBot", "PetalBot", "ClaudeBot", "SemrushBot", "meta-externalagent", "SEOkicks", "AwarioRssBot", "AwarioSmartBot", "ImagesiftBot", - "AliyunSecBot", "Aliyun", "Bytespider") + "AliyunSecBot", "Aliyun", "Bytespider", "YandexBot", + "AcademicBotRTU", "Claude-SearchBot", "dotbot", + "ChatGPT-User") for(bot in excluded_bots) { writeLines(paste0("User-agent: ", bot), con = con) @@ -166,25 +168,12 @@ write_robots_txt <- function(pkgs, output_file = "/var/shared/robots.txt") { } writeLines("User-agent: *", con = con) - - writeLines(paste0("Allow: /browse/*/"), con = con) - writeLines(paste0("Disallow: /browse/*/*/"), con = con) - writeLines(paste0("Disallow: /browse/*/treegraph"), con = con) - writeLines(paste0("Disallow: /browse/themes"), con = con) - writeLines(paste0("Disallow: *tree/"), con = con) - writeLines(paste0("Disallow: *blob/"), con = con) - writeLines(paste0("Disallow: *commit"), con = con) - writeLines(paste0("Disallow: *stats/"), con = con) - writeLines(paste0("Disallow: *network/"), con = con) - writeLines(paste0("Disallow: *RELEASE_"), con = con) - writeLines(paste0("Disallow: *raw/"), con = con) - writeLines(paste0("Disallow: *logpatch/"), con = con) - writeLines(paste0("Disallow: *zipball/"), con = con) - writeLines(paste0("Disallow: *tarball/"), con = con) - writeLines(paste0("Disallow: *blame/"), con = con) - writeLines(paste0("Disallow: *rss/"), con = con) - - writeLines(paste0("Disallow: /search/search?q"), con = con) + writeLines("Disallow: /", con = con) + writeLines("Allow: /browse/", con = con) + writeLines("Allow: /search/", con = con) + writeLines("Allow: /index.html", con = con) + writeLines("Allow: /about.html", con = con) + writeLines(sprintf("Allow: /browse/%s/", basename(pkgs)), con = con) writeLines("\nSitemap: https://code.bioconductor.org/sitemap.txt", con = con) }