In T153699, it was found that this automated tool (https://github.com/stamparm/DSXS ) generated a lot of artificial pageviews. Looking at more recent times and all projects, it was up to 0.91% of our total "human" (agent_type = 'user') pageviews in December, between 0.37-0.63% on January 6, and still between 0.2-0.4% on February 6.
SELECT day, ROUND(100* SUM(IF(user_agent = 'Damn Small XSS Scanner (DSXS) < 100 LoC (Lines of Code)', 1, 0))/SUM(1), 2) AS DSXS_percentage FROM wmf.webrequest WHERE year = 2016 AND month = 12 AND agent_type = 'user' AND is_pageview = TRUE GROUP BY day ORDER BY day ASC LIMIT 10000; day dsxs_percentage 8 0.78 9 0.84 10 0.91 11 0.59 12 0.52 13 0.63 14 0.61 15 0.36 16 0.44 17 0.42 18 0.3 19 0.45 20 0.3 21 0.33 22 0.39 23 0.38 24 0.38 25 0.3 26 0.27 27 0.26 28 0.26 29 0.27 30 0.29 31 0.36 24 rows selected (11881.762 seconds) SELECT hour, ROUND(100* SUM(IF(user_agent = 'Damn Small XSS Scanner (DSXS) < 100 LoC (Lines of Code)', 1, 0))/SUM(1), 1) AS DSXS_percentage FROM wmf.webrequest WHERE year = 2017 AND month = 2 AND day = 6 AND agent_type = 'user' AND is_pageview = TRUE GROUP BY hour ORDER BY hour ASC LIMIT 10000; hour dsxs_percentage 0 0.4 1 0.3 2 0.3 3 0.3 4 0.3 5 0.4 6 0.4 7 0.4 8 0.3 9 0.3 10 0.3 11 0.2 12 0.3 13 0.3 14 0.2 15 0.2 16 0.3 17 0.2 18 0.2 19 0.2 20 0.2 21 0.3 22 0.3 23 0.3 24 rows selected (808.264 seconds) SELECT hour, ROUND(100* SUM(IF(user_agent = 'Damn Small XSS Scanner (DSXS) < 100 LoC (Lines of Code)', 1, 0))/SUM(1), 2) AS DSXS_percentage FROM wmf.webrequest WHERE year = 2017 AND month = 1 AND day = 6 AND agent_type = 'user' AND is_pageview = TRUE GROUP BY hour ORDER BY hour ASC LIMIT 10000; hour dsxs_percentage 0 0.59 1 0.63 2 0.61 3 0.59 4 0.64 5 0.66 6 0.64 7 0.64 8 0.36 9 0.5 10 0.51 11 0.4 12 0.43 13 0.41 14 0.44 15 0.46 16 0.37 17 0.4 18 0.42 19 0.42 20 0.44 21 0.42 22 0.47 23 0.51