--- get_book.sh	2003/12/14 19:11:30	1.1.1.1
+++ get_book.sh	2004/07/21 13:58:35	1.12
@@ -1,46 +1,143 @@
 #!/bin/sh
 
-#export http_proxy=http://proxy.pliva.hr:8080
+# proxy settings (same as in firebird)
+fping -q proxy && export http_proxy=http://proxy:8080
+if [ -z "$http_proxy" ] ; then
+	fping -q proxy.lan && export http_proxy=http://proxy.lan:8080
+fi
+# user agent (same as in firebird)
+ua="Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.6) Gecko/20040506 Firefox/0.8"
+cookie_file="cookie.txt"
+
+# wait between pages
+export wait=120
+
+if [ ! -z "$http_proxy" ] ; then
+	echo "Using proxy $http_proxy"
+fi
+
+if [ -z "$1" ] ; then
+	echo "Usage: $0 ISBN"
+	exit 1
+fi
+
+if [ -e orig ] ; then
+	echo "orig directory found. Resume download? [Y/n]"
+	read ans
+	if [ "$ans" = "n" ] ; then
+		exit 1;
+	fi
+	mv orig/* .
+	rm -Rf orig
+
+	grep -l 'promo.asp' * | xargs -i rm {}
+	grep -l 'This is only a preview of the full book' * | xargs -i rm {}
+fi
 
-#isbn="0-201-41975-0"
-isbn="0-672-32240-4"
+isbn=`echo $1 | sed 's/-//g' | tr '[a-z]' '[A-Z]'`
 
-wait=10
+function mirror() {
 
-isbn2=`echo $isbn | sed 's/-//g'`
+	url="$1"
 
-function mirror() {
-	wget -p -nH -nc -k \
-		--random-wait --wait=$wait -t 0 \
-		--load-cookies=/home/dpavlin/.phoenix/default/g6b45nt6.slt/cookies.txt \
-		-U "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.5) Gecko/20031206 Firebird/0.7" \
-		$1
+	file=`echo $url | sed -e s,http://[^?]*?,index.html?, -e s,#.*$,, -e s,/,%2F,g`
+	if [ -e "$file" ] ; then
+#		echo "skip $url"
+		echo -n "."
+		return
+	fi
+
+	cookie=""
+	if echo $url | grep '/index' >/dev/null ; then
+		echo -n "no login (index) "
+	elif echo $url | grep 'mode=toc' >/dev/null ; then
+		echo -n "no login (toc) "
+	else
+		if [ ! -e $cookie_file ] ; then
+			echo "cookies file $cookie_file doesn't exits! Please create it."
+			echo "It should be in format:"
+			echo "Cookie: Site=UICode=&Portal=oreilly&GUID=..."
+			exit 1
+		fi
+		read cookie < $cookie_file
+		if [ -z "$cookie" ] ; then
+			echo "Empty cookie file $cookie_file !"
+			exit 1
+		fi
+	fi
+
+	if [ -z "$cookie" ] ; then
+		echo "$url [no cookie]"
+	else
+		echo "$url [with cookie]"
+	fi
+
+	wget -q -p -nH -nc -k -t 1 -U "$ua" --cookies=off --header="$cookie" $url
+	perl -e '$t=rand($ENV{wait} || 120);print "sleep for $t sec.\n"; sleep($t);'
 
-#	-D safari.oreilly.com \
-#	-A 0-201-41975-0 \
 }
 
 function geturl() {
-	hindent -s $1 | grep $2 | grep -i href | grep mode=[st][eo]c | \
+	hindent -s $1 | grep -i href | grep mode=[st][eo]c | \
 	sed -e 's/^.*<a.*href="//i' \
 		-e 's/".*//' -e 's/amp;//g' \
 		-e 's,^[^\?]*\?,http://safari.oreilly.com/,' \
-		-e 's/#$//' \
-		-e 's/srchText=//' | \
-		grep -v open=false | \
-		grep -v 'view=[A-Z].*%2F[^i]' | \
-		grep -v 'view=[A-Z].*/[^i]' | \
-		grep '&s=1&b=1&f=1&t=1&c=1&u=1&r=&o=1' | \
+		-e 's/#.*$//' \
+		-e 's/\&srchText=//' \
+		-e 's/open=false/open=true/' | \
+		grep '&s=1&b=1&f=1&t=1&c=1&u=1&r=&o=1&n=1&d=1&p=1&a=0' | \
+		grep -i "xmlid=[0-9A-Za-z\-][0-9A-Za-z\-]*" | \
+		grep -vi "xmlid=[0-9A-Za-z\-]*/[0-9][0-9][0-9][0-9][0-9][0-9][0-9]" | \
 		sort -u >> in
 }
 
-echo > in
-#mirror "http://safari.oreilly.com/?XmlId=$isbn"
+function uniqurl() {
+	mv in in.tmp
+	grep -v 'view=[A-Z]' in.tmp | grep 'a=0$' | sort -u > in
+	grep 'view=[A-Z].*/index' in.tmp | grep 'a=0$' | sort -u >> in
+	links=`wc -l in | cut -d" " -f1`
+	echo "found $links unique links"
+}
+
+function mirror_in() {
+	cat in | while read url ; do
+		mirror "$url"
+		#sleep $wait
+
+		if grep 'promo.asp' `ls -t index.html* | head -3` >/dev/null ; then
+			echo "WARNING: safari seems to logout you as user. Aborting."
+			exit 1
+		fi
+
+		if grep -i '>Account locked<' `ls -t index.html* | head -3` >/dev/null ; then
+			echo "WARNING: your safari account is locked. Aborting."
+			exit 1
+		fi
+
+		if grep -i 'session disabled' `ls -t index.html* | head -3` >/dev/null ; then
+			echo "WARNING: your safari session is disabled. Aborting."
+			exit 1
+		fi
+
+		if grep -i 'This is only a preview of the full book' `ls -t index.html* | head -3` >/dev/null ; then
+			echo "WARNING: you didn't add this book to your bookshelf!"
+			exit 1
+		fi
+	done
+	echo
+}
+
+echo -n > in
+mirror "http://safari.oreilly.com/$isbn"
+echo
 
-echo "extract URLs from first page..."
-geturl "index.html?XmlId=$isbn" $isbn
+file=`ls *index.html?XmlId=*`
+isbn=`echo $file | cut -d= -f2`
+echo "extract URLs from first page $file... [$isbn]"
+geturl $file $isbn
+uniqurl
 
-mirror "-i in"
+mirror_in
 
 echo -n "extracting URLs [1]"
 ls index.html* | while read file ; do
@@ -49,17 +146,25 @@
 done
 echo
 
-sort -u in > in2
+uniqurl
 
-mirror "-i in2"
+mirror_in
 
-echo > in
+echo -n > in
 echo -n "extracting URLs [2]"
 ls index.html* | while read file ; do
 	echo -n "."
 	geturl $file $isbn
 done
 
-sort -u in > in2
+uniqurl
+
+mirror_in
+
+# convert links in html
+bn=`basename $0`
+dir=`echo $0 | sed "s/$bn$//"`
+ls index.html* | xargs -i $dir/filter.pl {}
+mkdir orig
+mv index.html* orig/
 
-mirror "-i in2"