/[safari]/get_book.sh
This is repository of my old source code which isn't updated any more. Go to git.rot13.org for current projects!
ViewVC logotype

Annotation of /get_book.sh

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.7 - (hide annotations)
Sun Feb 15 11:40:43 2004 UTC (20 years, 1 month ago) by dpavlin
Branch: MAIN
Changes since 1.6: +8 -2 lines
File MIME type: application/x-sh
fping proxy and check if book is on bookshelf

1 dpavlin 1.1 #!/bin/sh
2    
3 dpavlin 1.5 # proxy settings (same as in firebird)
4 dpavlin 1.7 fping proxy && export http_proxy=http://proxy:8080
5 dpavlin 1.5 # user agent (same as in firebird)
6     ua="Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.5) Gecko/20031225 Firebird/0.7"
7    
8     # wait between pages
9     export wait=120
10    
11 dpavlin 1.1
12 dpavlin 1.2 if [ -z "$1" ] ; then
13     echo "Usage: $0 ISBN"
14     exit 1
15     fi
16    
17 dpavlin 1.5 if [ -e orig ] ; then
18     echo "orig directory found. Resume download? [Y/n]"
19     read ans
20     if [ "$ans" = "n" ] ; then
21     exit 1;
22     fi
23     mv orig/* .
24     rm -Rf orig
25    
26 dpavlin 1.7 grep -l 'promo.asp' * | xargs -i rm {}
27     grep -l 'This is only a preview of the full book' * | xargs -i rm {}
28 dpavlin 1.5 fi
29    
30 dpavlin 1.2 isbn=$1;
31 dpavlin 1.1
32     isbn2=`echo $isbn | sed 's/-//g'`
33    
34     function mirror() {
35 dpavlin 1.5
36     url="$1"
37    
38     file=`echo $url | sed -e s,http://[^?]*?,index.html?, -e s,#.*$,, -e s,/,%2F,g`
39     if [ -e "$file" ] ; then
40     # echo "skip $url"
41     return
42     fi
43    
44     if echo $url | grep '/index' >/dev/null ; then
45     cookies=""
46     echo -n "no login (index) "
47     elif echo $url | grep 'mode=toc' >/dev/null ; then
48     cookies=""
49     echo -n "no login (toc) "
50     else
51     cookies="--load-cookies=/home/dpavlin/.phoenix/default/g6b45nt6.slt/cookies.txt"
52     echo -n "with login "
53     fi
54     echo $url
55    
56 dpavlin 1.1 wget -p -nH -nc -k \
57 dpavlin 1.5 -t 1 -U "$ua" \
58     $cookies $url
59 dpavlin 1.1
60     # -D safari.oreilly.com \
61     # -A 0-201-41975-0 \
62 dpavlin 1.5
63     perl -e '$t=rand($ENV{wait} || 30);print "sleep for $t sec.\n"; sleep($t);'
64 dpavlin 1.1 }
65    
66     function geturl() {
67 dpavlin 1.2 hindent -s $1 | grep -i href | grep mode=[st][eo]c | \
68 dpavlin 1.1 sed -e 's/^.*<a.*href="//i' \
69     -e 's/".*//' -e 's/amp;//g' \
70     -e 's,^[^\?]*\?,http://safari.oreilly.com/,' \
71     -e 's/#$//' \
72 dpavlin 1.2 -e 's/\&srchText=//' \
73     -e 's/open=false/open=true/' | \
74 dpavlin 1.1 grep '&s=1&b=1&f=1&t=1&c=1&u=1&r=&o=1' | \
75 dpavlin 1.2 grep $2 | \
76 dpavlin 1.5 grep -v "$2/[0-9][0-9][0-9][0-9][0-9][0-9][0-9]" | \
77 dpavlin 1.1 sort -u >> in
78     }
79    
80 dpavlin 1.2 function uniqurl() {
81     mv in in.tmp
82     grep -v 'view=[A-Z]' in.tmp | sort -u > in
83     grep 'view=[A-Z].*/index' in.tmp | sort -u >> in
84     }
85    
86 dpavlin 1.4 function mirror_in() {
87     cat in | while read url ; do
88     mirror "$url"
89 dpavlin 1.5 #sleep $wait
90 dpavlin 1.4
91     if grep 'promo.asp' `ls -t index.html* | head -3` >/dev/null ; then
92 dpavlin 1.5 echo "WARNING: safari seems to logout you as user. Aborting."
93     exit 1
94     fi
95    
96     if grep -i '>Account locked<' `ls -t index.html* | head -3` >/dev/null ; then
97     echo "WARNING: your safari account is locked. Aborting."
98     exit 1
99     fi
100    
101     if grep -i 'session disabled' `ls -t index.html* | head -3` >/dev/null ; then
102     echo "WARNING: your safari session is disabled. Aborting."
103 dpavlin 1.4 exit 1
104     fi
105 dpavlin 1.7
106     if grep -i 'This is only a preview of the full book' `ls -t index.html* | head -3` >/dev/null ; then
107     echo "WARNING: you didn't add this book to your bookshelf!"
108     exit 1
109     fi
110 dpavlin 1.4 done
111 dpavlin 1.3 }
112    
113 dpavlin 1.4 echo -n > in
114 dpavlin 1.2 mirror "http://safari.oreilly.com/?XmlId=$isbn"
115 dpavlin 1.1
116     echo "extract URLs from first page..."
117     geturl "index.html?XmlId=$isbn" $isbn
118 dpavlin 1.2 uniqurl
119 dpavlin 1.1
120 dpavlin 1.4 mirror_in
121 dpavlin 1.1
122     echo -n "extracting URLs [1]"
123     ls index.html* | while read file ; do
124     echo -n "."
125     geturl $file $isbn
126     done
127     echo
128    
129 dpavlin 1.2 uniqurl
130 dpavlin 1.1
131 dpavlin 1.4 mirror_in
132 dpavlin 1.1
133 dpavlin 1.4 echo -n > in
134 dpavlin 1.1 echo -n "extracting URLs [2]"
135     ls index.html* | while read file ; do
136     echo -n "."
137     geturl $file $isbn
138     done
139    
140 dpavlin 1.2 uniqurl
141    
142 dpavlin 1.4 mirror_in
143 dpavlin 1.2
144     # convert links in html
145     bn=`basename $0`
146     dir=`echo $0 | sed "s/$bn$//"`
147     ls index.html* | xargs -i $dir/filter.pl {}
148     mkdir orig
149     mv index.html* orig/
150 dpavlin 1.1

  ViewVC Help
Powered by ViewVC 1.1.26