#!/bin/bash
# searchinfo - Extracts and analyzes search engine traffic indicated in the 
#    referrer field of a Common Log Format access log.

setglobal host = '"intuitive.com'"    # change to your domain, as desired
setglobal maxmatches = '20'
setglobal count = '0'
setglobal temp = ""/tmp/$[basename $0].$Pid""

trap "$[which rm] -f $temp" 0

if test $Argc -eq 0  {
  echo "Usage: $[basename $0] logfile"  > !2 
  exit 1
}
if test ! -r $1  {
  echo "Error: can't open file $1 for analysis." > !2
  exit 1
}

for URL in [$[awk '{ if (length($11) > 4) { print $11 } }' $1 | \
  grep -vE "(/www.$host|/$host)" | grep '?]]
{
  setglobal searchengine = $[echo $URL | cut -d/ -f3 | rev | cut -d. -f1-2 | rev]
  setglobal args = $[echo $URL | cut -d'?' -f2 | tr '&' '\n' | \
     grep -E '(^q=|^sid=|^p=|query=|item=|ask=|name=|topic=)' | \
  sed -e 's/+/ /g' -e 's/%20/ /g' -e 's/"//g' | cut -d= -f2]
  if test ! -z $args  {
    echo "$(searchengine):      $args" >> $temp
  } else {
    # No well-known match, show entire GET string instead...
    echo "$(searchengine)       $[echo $URL | cut -d'?' -f2]" >> $temp
  }
  setglobal count = "$shExpr(' $count + 1 ')"
}

echo "Search engine referrer info extracted from $(1):"

sort $temp | uniq -c | sort -rn | head -$maxmatches | sed 's/^/  /g'

echo ""
echo Scanned $count entries in log file out of $[wc -l < $1] total.

exit 0