Apache logs in R

log_parser.r

require(plyr)
require(lubridate)
log <- read.table(file='httpd.combine.20120509')
# in the file I used, there was a space between the time and the time zone, creating two fields.
names(log) <- c('host', 'identity', 'user', 'time' ,'V5','request', 'status', 'bytes','referer','agent')
# Paste the two fields together
log$time <- paste(log$time, log$V5, sep=' ')
# remove the extra field
log$V5 <- NULL

# extract the URIs from the request field
log$uri <- gsub('GET |PROPFIND |HEAD |OPTIONS | HTTP/*.*','',log$request)

# convert the timestamp to something R can work with
log$rtime <- strptime(log$time, '[%d/%B/%Y:%H:%M:%S')

# Identify the obvious bots from the agent field
log$isbot <- grepl (".*bot.*", log$agent)

views <- function(x, subset.code) {
			switch(subset.code,
			'nobots' = subset(x, isbot==TRUE),
			'pdfs' = subset(x, grepl('.*.pdf$', x$uri))
			)
			}

views(log, 'pdfs')