1 |
#!/bin/sh |
2 |
|
3 |
#export http_proxy=http://proxy.pliva.hr:8080 |
4 |
|
5 |
#isbn="0-201-41975-0" |
6 |
isbn="0-672-32240-4" |
7 |
|
8 |
wait=10 |
9 |
|
10 |
isbn2=`echo $isbn | sed 's/-//g'` |
11 |
|
12 |
function mirror() { |
13 |
wget -p -nH -nc -k \ |
14 |
--random-wait --wait=$wait -t 0 \ |
15 |
--load-cookies=/home/dpavlin/.phoenix/default/g6b45nt6.slt/cookies.txt \ |
16 |
-U "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.5) Gecko/20031206 Firebird/0.7" \ |
17 |
$1 |
18 |
|
19 |
# -D safari.oreilly.com \ |
20 |
# -A 0-201-41975-0 \ |
21 |
} |
22 |
|
23 |
function geturl() { |
24 |
hindent -s $1 | grep $2 | grep -i href | grep mode=[st][eo]c | \ |
25 |
sed -e 's/^.*<a.*href="//i' \ |
26 |
-e 's/".*//' -e 's/amp;//g' \ |
27 |
-e 's,^[^\?]*\?,http://safari.oreilly.com/,' \ |
28 |
-e 's/#$//' \ |
29 |
-e 's/srchText=//' | \ |
30 |
grep -v open=false | \ |
31 |
grep -v 'view=[A-Z].*%2F[^i]' | \ |
32 |
grep -v 'view=[A-Z].*/[^i]' | \ |
33 |
grep '&s=1&b=1&f=1&t=1&c=1&u=1&r=&o=1' | \ |
34 |
sort -u >> in |
35 |
} |
36 |
|
37 |
echo > in |
38 |
#mirror "http://safari.oreilly.com/?XmlId=$isbn" |
39 |
|
40 |
echo "extract URLs from first page..." |
41 |
geturl "index.html?XmlId=$isbn" $isbn |
42 |
|
43 |
mirror "-i in" |
44 |
|
45 |
echo -n "extracting URLs [1]" |
46 |
ls index.html* | while read file ; do |
47 |
echo -n "." |
48 |
geturl $file $isbn |
49 |
done |
50 |
echo |
51 |
|
52 |
sort -u in > in2 |
53 |
|
54 |
mirror "-i in2" |
55 |
|
56 |
echo > in |
57 |
echo -n "extracting URLs [2]" |
58 |
ls index.html* | while read file ; do |
59 |
echo -n "." |
60 |
geturl $file $isbn |
61 |
done |
62 |
|
63 |
sort -u in > in2 |
64 |
|
65 |
mirror "-i in2" |