Bearloga has submitted this change and it was merged. Change subject: Add data collection script for pageviews to the portal ......................................................................
Add data collection script for pageviews to the portal Bug: T125737 Change-Id: I9ac5464d631f873acab3ad2e506b3dd13112e6ba --- A portal/pageviews.R 1 file changed, 26 insertions(+), 0 deletions(-) Approvals: Bearloga: Verified; Looks good to me, approved diff --git a/portal/pageviews.R b/portal/pageviews.R new file mode 100644 index 0000000..4f188fb --- /dev/null +++ b/portal/pageviews.R @@ -0,0 +1,26 @@ +base_path <- paste0(write_root, "portal/") + +main <- function(date = NULL){ + + # Date handling + if(is.null(date)){ + date <- Sys.Date() - 1 + } + + # Date subquery + subquery <- date_clause(date) + + # Query + data <- query_hive(paste0("USE wmf; + SELECT COUNT(*) AS pageviews + FROM webrequest + ", subquery, + "AND uri_host IN('www.wikipedia.org', 'wikipedia.org') + AND content_type RLIKE('^text/html') + AND webrequest_source = 'text'")) + + output <- data.frame(date = date, pageviews = data$pageviews) + + #Return! + conditional_write(output, file.path(base_path, "portal_pageviews.tsv")) +} -- To view, visit https://gerrit.wikimedia.org/r/271688 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: I9ac5464d631f873acab3ad2e506b3dd13112e6ba Gerrit-PatchSet: 2 Gerrit-Project: wikimedia/discovery/golden Gerrit-Branch: master Gerrit-Owner: OliverKeyes <oke...@wikimedia.org> Gerrit-Reviewer: Bearloga <mpo...@wikimedia.org> _______________________________________________ MediaWiki-commits mailing list MediaWiki-commits@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits