alexbilbie · September 27, 2012 19:36 · Sep 25, 2012
diff --git a/rss-subscribers.sh b/rss-subscribers.sh
@@ -0,0 +1,51 @@
+#!/bin/bash
+
+# Schedule this to run once a day with cron. Doesn't matter what time since it parses yesterday's hits (by default).
+# I only tested this on the Marco.org server, which runs CentOS (RHEL). No idea how it'll work on other distributions, but it's pretty basic.
+
+# Required variables:
+RSS_URI="/rss"
+MAIL_TO="your@email.com"
+LOG_FILE="/var/log/httpd/access_log"
+
+# --- Optional customization ---
+
+MAIL_SUBJECT="RSS feed subscribers"
+
+# Date expression for yesterday
+DATE="-1 day" 
+
+# Locale for printf number formatting (e.g. "10000" => "10,000")
+LANG=en_US
+
+# 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'`
+
+# --- The actual log parsing ---
+
+# 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 | uniq | cut -d' ' -f 1 | 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 " $RSS_URI" | fgrep -v 'subscribers; feed-id=' | egrep '[0-9]+ subscribers' | egrep -o '"[^"]+"$' | sort | uniq | egrep -o '[0-9]+ subscribers' | awk '{s+=$1} END {print s}'`
+
+REPORT=$(
+    printf "Feed stats for $HUMAN_FDATE:\n\n"
+    printf "%'8d Google Reader subscribers\n" $GRSUBS
+    printf "%'8d subscribers from other aggregators\n" $OTHERSUBS
+    printf "%'8d direct subscribers\n" $IPSUBS
+    echo   "--------"
+    printf "%'8d total subscribers\n" `expr $GRSUBS + $OTHERSUBS + $IPSUBS`
+)
+
+echo "$REPORT"
+echo ""
+echo "Also emailed to $MAIL_TO."
+
+echo "$REPORT " | mail -s "[$HUMAN_FDATE] $MAIL_SUBJECT" "$MAIL_TO"