#!/bin/bash
CURL=/sw/bin/curl

# a file with known pages, one URL per line
URLFILE=pages.txt

# file descriptor 3 is our URLs
3<"${URLFILE}"

typeset -i FAILED

# for each URL in the URLFILE
while read -u 3 URL
do
    FAILED=0
    # call curl to fetch the page. Get the headers, too. We're
    # interested in the first line that gives the status
    RESPONSE=$(${CURL} -D - -s "${URL}" | head -1)
    OIFS="$IFS"
    set - ${RESPONSE}
    result=$2
    IFS="$OIFS"

    # If we got something in the 200 series, it's probably a failure
    if [ $result -lt 300 ]
    then
	echo "FAIL:	$result ${URL}"
	FAILED=${FAILED}+1
    else
	# response in the 300 series is a redirect. Need to check manually
	if [ $result -lt 400 ]
	then
	    echo "CHECK:	$result ${URL}"
	    FAILED=${FAILED}+1
	else
	    # response in the 400 series is some kind of
	    # denial. That's generally considered "success"
	    if [ $result -lt 500 ]
	    then
		echo "PASS:	$result ${URL}"
	    else
		# response in the 500 series means server
		# failure. Anything we haven't already accounted for
		# will be called a failure.
		echo "FAIL:	$result ${URL}"
		FAILED=${FAILED}+1
	    fi
	fi
    fi
done