发现一个O'Reilly's CD bookshelf，并提供下载脚本

复制内容到剪贴板

代码:

[No.505 04:03:08 ~]$ wget -r http://www.chinalinuxpub.com/doc/oreillybookself/perl/perlnut/index.htm
--04:03:29--  http://www.chinalinuxpub.com/doc/oreillybookself/perl/perlnut/index.htm
           => `www.chinalinuxpub.com/doc/oreillybookself/perl/perlnut/index.htm'
Resolving www.chinalinuxpub.com... 210.82.89.226
Connecting to www.chinalinuxpub.com|210.82.89.226|:80... connected.
HTTP request sent, awaiting response... 403 Forbidden
04:03:30 ERROR 403: Forbidden.


FINISHED --04:03:30--
Downloaded: 0 bytes in 0 files
[No.506 04:03:30 ~]$

复制内容到剪贴板

代码:

[No.616 04:24:22 Downloads]$ cat down.sh
#! /bin/bash
#
# author: li-jiahuan@sohu.com
# date  : 06/02/01
# usage : ./down.txt dir_to_save book_link

# set -n

link="http://210.82.89.226/doc/oreillybookself/perl/learn"
index=${link}/index.htm

# ${para-default}, ${para:-default}
dir=${1:-$PWD}
link=${2:-$link}
mkdir -p $dir
cd $dir
#if [[ $PWD != $dir ]];then
#       echo "Can not cd to $dir"
#       exit
#fi


# download the index page
[[ -f "index.htm" ]] || curl $index > index.htm

# web="http://210.82.89.226/doc/oreillybookself/perl/learn/prf1_01.htm"
# download the Preface
for i in {1..5};do
        for j in `seq -w 1 15`;do
                web=${link}/prf${i}_${j}.htm
                preface=${web##*/}
                [[ -e $preface ]] && continue
                echo -e "\nDownloading $web ..."
                curl $web > $preface
                 if grep "was not found on this server" $preface ;then
            rm $preface
            break
        fi
    done
done


# web="http://210.82.89.226/doc/oreillybookself/perl/learn/ch0_01.htm"

# download chapters
for i in `seq -w 1 19`;do
        for j in `seq -w 1 50`;do
                web="${link}/ch${i}_${j}.htm"
                chapter=${web##*/}
                [[ -e $chapter ]] && continue
        echo -e "\nDownloading $web ..."
                curl $web > $chapter
                if grep "was not found on this server" $chapter ;then
                        rm $chapter
                        break
                fi
        done
done

# web=http://210.82.89.226/doc/oreillybookself/perl/learn/appa_01.htm"
# download Appendix

for i in {a..z};do
    for j in `seq -w 1 50`;do
        web="${link}/app${i}_${j}.htm"
        appendix=${web##*/}
        [[ -e $appendix ]] && continue
        echo -e "\nDownloading $web ..."
        curl $web > $appendix
        if grep "was not found on this server" $appendix ;then
            rm $appendix
            break
        fi
    done
done

# web=http://210.82.89.226/doc/oreillybookself/perl/learn/index/idx_a.htm
# download index
link=${link}/index
mkdir -p index
cd index
[[ -f idx_0.htm ]] || curl $link/idx_0.htm > idx_0.htm
for j in {a..z};do
        web="${link}/idx_${j}.htm"
        idx=${web##*/}
        [[ -e $idx ]] && continue
        echo -e "\nDownloading $web ..."
        curl $web > $idx
        if grep "was not found on this server" $idx ;then
            rm $idx
#            break
        fi
    done

[No.617 04:24:25 Downloads]$