viewvc.cgi/safari/get_book.sh

#!/bin/sh

#export http_proxy=http://proxy:8080

if [ -z "$1" ] ; then
        echo "Usage: $0 ISBN"
        exit 1
fi

isbn=$1;

wait=10

isbn2=`echo $isbn | sed 's/-//g'`

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

#       -D safari.oreilly.com \
#       -A 0-201-41975-0 \
}

function geturl() {
        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=//' \
                -e 's/open=false/open=true/' | \
                grep '&s=1&b=1&f=1&t=1&c=1&u=1&r=&o=1' | \
                grep $2 | \
                sort -u >> in
}

function uniqurl() {
        mv in in.tmp
        grep -v 'view=[A-Z]' in.tmp | sort -u > in
        grep 'view=[A-Z].*/index' in.tmp | sort -u >> in
}

echo > in
mirror "http://safari.oreilly.com/?XmlId=$isbn"

echo "extract URLs from first page..."
geturl "index.html?XmlId=$isbn" $isbn
uniqurl

mirror "-i in"

echo -n "extracting URLs [1]"
ls index.html* | while read file ; do
        echo -n "."
        geturl $file $isbn
done
echo

uniqurl

mirror "-i in"

echo > in
echo -n "extracting URLs [2]"
ls index.html* | while read file ; do
        echo -n "."
        geturl $file $isbn
done

uniqurl

mirror "-i 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/

1	dpavlin	1.1	#!/bin/sh
2
3	dpavlin	1.2	#export http_proxy=http://proxy:8080
4	dpavlin	1.1
5	dpavlin	1.2	if [ -z "$1" ] ; then
6			echo "Usage: $0 ISBN"
7			exit 1
8			fi
9
10			isbn=$1;
11	dpavlin	1.1
12			wait=10
13
14			isbn2=`echo $isbn \| sed 's/-//g'`
15
16			function mirror() {
17			wget -p -nH -nc -k \
18			--random-wait --wait=$wait -t 0 \
19			--load-cookies=/home/dpavlin/.phoenix/default/g6b45nt6.slt/cookies.txt \
20			-U "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.5) Gecko/20031206 Firebird/0.7" \
21			$1
22
23			# -D safari.oreilly.com \
24			# -A 0-201-41975-0 \
25			}
26
27			function geturl() {
28	dpavlin	1.2	hindent -s $1 \| grep -i href \| grep mode=[st][eo]c \| \
29	dpavlin	1.1	sed -e 's/^.<a.href="//i' \
30			-e 's/".*//' -e 's/amp;//g' \
31			-e 's,^[^\?]*\?,http://safari.oreilly.com/,' \
32			-e 's/#$//' \
33	dpavlin	1.2	-e 's/\&srchText=//' \
34			-e 's/open=false/open=true/' \| \
35	dpavlin	1.1	grep '&s=1&b=1&f=1&t=1&c=1&u=1&r=&o=1' \| \
36	dpavlin	1.2	grep $2 \| \
37	dpavlin	1.1	sort -u >> in
38			}
39
40	dpavlin	1.2	function uniqurl() {
41			mv in in.tmp
42			grep -v 'view=[A-Z]' in.tmp \| sort -u > in
43			grep 'view=[A-Z].*/index' in.tmp \| sort -u >> in
44			}
45
46	dpavlin	1.1	echo > in
47	dpavlin	1.2	mirror "http://safari.oreilly.com/?XmlId=$isbn"
48	dpavlin	1.1
49			echo "extract URLs from first page..."
50			geturl "index.html?XmlId=$isbn" $isbn
51	dpavlin	1.2	uniqurl
52	dpavlin	1.1
53			mirror "-i in"
54
55			echo -n "extracting URLs [1]"
56			ls index.html* \| while read file ; do
57			echo -n "."
58			geturl $file $isbn
59			done
60			echo
61
62	dpavlin	1.2	uniqurl
63	dpavlin	1.1
64	dpavlin	1.2	mirror "-i in"
65	dpavlin	1.1
66			echo > in
67			echo -n "extracting URLs [2]"
68			ls index.html* \| while read file ; do
69			echo -n "."
70			geturl $file $isbn
71			done
72
73	dpavlin	1.2	uniqurl
74
75			mirror "-i in"
76
77			# convert links in html
78			bn=`basename $0`
79			dir=`echo $0 \| sed "s/$bn$//"`
80			ls index.html* \| xargs -i $dir/filter.pl {}
81			mkdir orig
82			mv index.html* orig/
83	dpavlin	1.1