Bash script to parse Apache log for a count of RSS subscribers and email it to you

rss-subscribers.sh

#!/bin/bash

# A modification of Marco Arment's script at
#
#   https://gist.github.com/3783146
#
# It's intended to be run once a day as a cron job. The main
# differences between it and Marco's script are:
#
#  1. It checks two feeds instead of just one.
#  2. It combines the non-Google Reader counts into a single number.
#  3. It doesn't write anything to stdout or send email.
#  4. It adds a line to a history file with the date and counts.
# 

# Required variables. Edit these for your server.
FEED_LIST="/feed"
LOG_FILE="/path/to/apache/access/log/file"
HISTORY_FILE="subscribers.txt"

# Date expression for yesterday
DATE="-1 day"

# Date format in Apache log
LOG_FDATE=`date -d "$DATE" '+%d/%b/%Y'`

# Date format for display in emails
HUMAN_FDATE=`date -d "$DATE" '+%F'`

# Date format for history file.
HISTORY_FDATE=`date -d "$DATE" '+%Y-%m-%d'`

# Start the line with yesterday's date. 
DAYLINE=$(printf "%s:  " $HISTORY_FDATE)

# Loop through the feeds, collecting subscriber counts and adding
# them to the line.
for RSS_URI in $FEED_LIST; do
  
  # Unique IPs requesting RSS, except those reporting "subscribers":
  IPSUBS=`fgrep "$LOG_FDATE" "$LOG_FILE" | fgrep " $RSS_URI " | egrep -v '[0-9]+ subscribers' | cut -d' ' -f 1 | sort | uniq | wc -l`
  
  # Google Reader subscribers and other user-agents reporting "subscribers" 
  # and using the "feed-id" parameter for uniqueness:
  GRSUBS=`fgrep "$LOG_FDATE" "$LOG_FILE" | fgrep " $RSS_URI " | egrep -o '[0-9]+ subscribers; feed-id=[0-9]+' | sort -t= -k2 -s | tac | uniq -f2 | awk '{s+=$1} END {print s}'`
  
  # Other user-agents reporting "subscribers", for which we'll use the 
  # entire user-agent string for uniqueness:
  OTHERSUBS=`fgrep "$LOG_FDATE" "$LOG_FILE" | fgrep " $RSS_URI " | fgrep -v 'subscribers; feed-id=' | egrep '[0-9]+ subscribers' | egrep -o '"[^"]+"$' | tac | awk -F\( '!x[$1]++' | egrep -o '[0-9]+ subscribers' | awk '{s+=$1} END {print s}'`
  
  # Add the non-Google Reader subscribers.
  NONGRSUBS=$(($IPSUBS + $OTHERSUBS))
  
  DAYLINE=$DAYLINE$(printf "%5d  " $GRSUBS; printf "%5d  " $NONGRSUBS)
done

# Append yesterday's info to the history file.
echo "$DAYLINE" >> $HISTORY_FILE