script to check how many of the top 100 sites are blocked by CyberRoam

check-top1000.sh

#!/bin/bash

# To get the data
# curl -s -O http://s3.amazonaws.com/alexa-static/top-1m.csv.zip ; unzip -q -o top-1m.csv.zip top-1m.csv ; head -1000 top-1m.csv | cut -d, -f2 | cut -d/ -f1 > topsites.txt

# Process Data
cat topsites.txt | while read line
do
	echo $line
	count=$( wget -T 30 -qO- $line | grep -c "><font class=accessdeniedcategoryfont>")
	if [ "$count" != "0" ]
	then
		echo "^BLOCKED"
		echo $line >> blocked.txt
	fi
done