--- get_book.sh	2004/02/15 11:40:43	1.7
+++ get_book.sh	2004/02/17 19:06:10	1.8
@@ -38,6 +38,7 @@
 	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
 
@@ -68,7 +69,7 @@
 	sed -e 's/^.*<a.*href="//i' \
 		-e 's/".*//' -e 's/amp;//g' \
 		-e 's,^[^\?]*\?,http://safari.oreilly.com/,' \
-		-e 's/#$//' \
+		-e 's/#.*$//' \
 		-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' | \
@@ -81,6 +82,8 @@
 	mv in in.tmp
 	grep -v 'view=[A-Z]' in.tmp | sort -u > in
 	grep 'view=[A-Z].*/index' in.tmp | sort -u >> in
+	links=`wc -l in | cut -d" " -f1`
+	echo "found $links unique links"
 }
 
 function mirror_in() {
@@ -108,10 +111,12 @@
 			exit 1
 		fi
 	done
+	echo
 }
 
 echo -n > in
 mirror "http://safari.oreilly.com/?XmlId=$isbn"
+echo
 
 echo "extract URLs from first page..."
 geturl "index.html?XmlId=$isbn" $isbn