Prepares IIS W3C log files for use with siege

prepareforsiege.sh

#!/bin/bash

#
# Takes IIS W3C formatted log files, and creates a load file for use with siege.
# 
#


# make sure you always put $f in double quotes to avoid any nasty surprises i.e. "$f"
for f in $@
do
  echo "Processing $f..."

# dos 2 unix, remove comments, remove empty lines
sed -i -e 's/.$//' -e 's/#.*//' -e '/^$/ d' "$f"

# only requests that didnt throw an error
awk -F ' ' '$12 < 400 {print}' $f > uri

# only want uri and request method
cut -d' ' -f4-5 uri > method_uri
rm uri

# strip out load balancer check
grep -v "/load/balancer/check.html" method_uri > urls

# i just want GETs
grep "GET" urls > urls.txt

rm method_uri
rm urls

#TODO: add load balancer check every 200 requests
#awk '1;!(NR%200){print "GET /load/balancer/check.html";}' file

# prep for siege
sed -i -e 's/GET /http:\/\/siege-target.domain.com/' urls.txt

echo "Setting dates in URI to `date +%Y%m%d`\n"

# update the form submitted dates to today 
sed -i -e 's/d=[0-9]\{8\}/d='`date +%Y%m%d`'/g' urls.txt

split -l 100000 urls.txt SiegeUrls.

done