这样子的链接可以这样
代码： 全选
#!/bin/bash
wget $1 -q -T 10 -O- 2>/dev/null |grep -o http://download.ourdev.cn/[a-z0-9_]*/[a-z0-9_]*/[a-z0-9_]*.[a-z]* >/tmp/tmp$$
for i in `cat /tmp/tmp$$`
do
wget "$i"
done
#rm /tmp/tmp$$
代码： 全选
#!/usr/bin/perl
use LWP::UserAgent;
my $url=shift;
my $url='http://www.ouravr.com/bbs/bbs_content.jsp?bbs_sn=3402316&bbs_page_no=1&search_mode=1&search_text=pdf&bbs_id=1000';
my $ua=new LWP::UserAgent();
my $re= $ua->get($url);
die "Couldn't get $url" unless defined $re;
my $html= $re->content;
#最后提取出出指定页面内容
#为wget创建批量下载文件
open (templist,">temp.txt");
close(templist);
my $type=rar;
my $type1=pdf;
# my $downpath = ;
while($html=~ /\<a href=(.*?)\>/gsi){
open (templist,'>>temp.txt');
print templist "$1\n";
close(templist);
}
system("rm -r downlist.txt");
system("sed -n -e '/\.$type/p' temp.txt > downlist.txt");
system("sed -n -e '/\.$type1/p' temp.txt >> downlist.txt");
#根据情况删除 有些 <a href= > 中不光是路径 还有其他标签 看网页源码情况
system("sed -i 's/target=.*/ /g' downlist.txt >> downlist.txt");
unlink("temp.txt");
#路径
system("wget -i downlist.txt -P ~/download/");