#!/bin/bash

if [ $# -ne 1 ]; then
   echo Usage: $0 Log file
   exit 1
fi

if [ ! -f $1 ]; then
   echo File $1 seems not to exist
   exit 1
fi

grep ' \- \- ' $1 > $1.tmp
mv -f $1.tmp $1

declare -A months
months[Jan]=01
months[Feb]=02
months[Mar]=03
months[Apr]=04
months[May]=05
months[Jun]=06
months[Jul]=07
months[Aug]=08
months[Sep]=09
months[Oct]=10
months[Nov]=11
months[Dec]=12

for i in Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec; do
   echo "s/$i/${months[$i]}/" >> /tmp/$$.sed
done

sed -i -f /tmp/$$.sed -e 's/- - \[\([0-9]\{2\}\)\/\([0-9]\{2\}\)\/20\([0-9]\{2\}\):/20\3-\2-\1 /g' -e 's/ [+-][0-9]\{4\}]//' -e 's/ - / 0 /' $1

rm -f /tmp/$$.sed

# Remove hits from IPv6 addresses:
egrep -v "^.{4}:" $1 > $1.tmp
mv -f $1.tmp $1

# Remove hits from robots:
egrep -v '(Yandex|Baidu|Google|Slurp|bingbot|Sogou|DotBot|msnbot|MJ12bot|Exabot|Twitterbot|omgilibot|Kraken|Applebot|BuzzSumo|bitlybot|AhrefsBot|rogerbot|Spiderbot|linkdexbot|Cliqzbot|Buzzbot|trendictionbot|Bot|Crawler|Yeti|Mediatoolkitbot|datagnionbot|ISSbot|linkapediabot|Slack|NewsNow|ltx71)' $1 > $1.tmp
mv -f $1.tmp $1