#! /bin/sh
#
# webwatcher.sh - Command line utility for tracking changes on webpages
# Copyright (C) 2002-2003 Tommi Saviranta <tsaviran@cs.helsinki.fi>
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
#
#
# Version: webwatcher.sh v0.2.2  22-Jan-2003  tsaviran@cs.helsinki.fi


BROWSER="links"
BOPTIONS="-dump"
MAILTO="user@host"
DIFFDEBUG=1

# Go to homedir
cd `echo $0 | sed -e 's/\(.*\)\/.*/\1/'`

URL=""
MODE=""
SUBJECT=""
GREP=""
OPTIONS=""
NUSER=USER
test "x$USER" == "x" && NUSER="dummy"
TEMPFILE1="/tmp/.webwatcher.1.$NUSER"	# We could use /bin/tempfile
TEMPFILE2="/tmp/.webwatcher.2.$NUSER"	# We could use /bin/tempfile
TEMPFILE3="/tmp/.webwatcher.3.$NUSER"	# We could use /bin/tempfile
TEMPFILE4="/tmp/.webwatcher.4.$NUSER"	# We could use /bin/tempfile

if [ ! -d cache ]; then
	if [ -e cache ]; then
		echo "File 'cache' exists, but it's not a directory."
		exit 1
	fi
	mkdir cache
fi
test ! -f cache/index && touch cache/index
test ! -f cache/count && echo "0" >cache/count

for LINE in `cat sites | tr ' ' '§'`; do
	# Read lines, receive data etc.
	LINE=`echo $LINE | tr '§' ' '`
	CMD=`echo $LINE | cut -d ' ' -f 1`
	DATA=`echo $LINE | cut -d ' ' -f 2-`

	test "x$CMD" == "xurl:" &&	URL="$DATA"
	test "x$CMD" == "xmode:" &&	MODE="$DATA"
	test "x$CMD" == "xsubject:" &&	SUBJECT="$DATA"
	test "x$CMD" == "xgrep:" &&	GREP="$DATA"
	test "x$CMD" == "xoptions:" &&	OPTIONS="$DATA"
	
	test "x$CMD" == "xbrowser:" &&	BROWSER="$DATA"
	test "x$CMD" == "xmailto:" &&	MAILTO="$DATA"

	# We got all we wanted.
	if [ "x$CMD" == "xok" ]; then
		# Make sure this file is in use, too
		touch $TEMPFILE4
		
		# See if page has been watched before
		CACHED=`grep -- "$URL " cache/index | cut -d ' ' -f 2`
		REPORT=1
		if [ "x$CACHED" == "x" ]; then
			# We're watching this page for the first time
			CACHED=`cat cache/count`
			touch cache/cached.$CACHED
			echo "$URL $CACHED" >>cache/index
			expr $CACHED + 1 >cache/count
			# Don't report these changes
			REPORT=0
		fi
		CACHED="cache/cached.$CACHED"

		# Fetch the page
		$BROWSER -source "$URL" >$TEMPFILE1 2>/dev/null
		# Something went wrong while fetching...
		if [ $? -ne 0 ]; then
			# Simpliest way to ignore this is to use cached file
			# as "current" version of the page.
			cp $CACHED $TEMPFILE1
		fi	

		# If we're grepping something, grep it.
		if [ "x$GREP" != "x" ]; then
			grep $OPTIONS "$GREP" $TEMPFILE1 >$TEMPFILE2
			grep $OPTIONS "$GREP" $CACHED >$TEMPFILE3
		else
			cp $TEMPFILE1 $TEMPFILE2
			cp $CACHED $TEMPFILE3
		fi

		# Compare...
		diff -q $TEMPFILE3 $TEMPFILE2 1>/dev/null 2>&1
		if [ $? -eq 1 ]; then
			# The do differ.
			test "x$MODE" == "xascii" && \
					$BROWSER $BOPTIONS \
					file://$HOMEDIR/$TEMPFILE1 \
					>$TEMPFILE4
			test "x$MODE" == "xhtml" && \
					cp -f $TEMPFILE1 $TEMPFILE4
			test "x$MODE" == "xdiff" && \
					diff $TEMPFILE2 $TEMPFILE3 >$TEMPFILE4
			test "x$MODE" == "xbrief" &&
					echo "Page changed." >$TEMPFILE4

			if [ "x$DIFFDEBUG" != "x" ]; then
				echo "-- differences --" >>$TEMPFILE4
				diff $TEMPFILE2 $TEMPFILE3 >>$TEMPFILE4
			fi

			test $REPORT -eq 1 && \
					mail -s "$SUBJECT" $MAILTO <$TEMPFILE4
		fi

		# Copy new file to replace old one and delete temporary files
		cp $TEMPFILE1 $CACHED
		rm $TEMPFILE1 $TEMPFILE2 $TEMPFILE3 $TEMPFILE4

		URL=""
		MODE=""
		SUBJECT=""
		GREP=""
		OPTIONS=""
	fi
done