Perl：分析页面，提取下载链接和文件对应的名称。

#t.pl
# to split out index url and rar page.
use warnings;
use LWP::Simple;

sub getDownloadPage {

my @lines=split("\n", $_[0]);
my $line1="";
    foreach my $line(@lines) {

        if ($line=~/<li class="itm">[^<]*<span> *[0-9]{4}-[0-9]{2}-[0-9]{2} *<\/span>[^<]*<a href="([^"> ]*)" *>([^<]*)</) {
            print $1," ",$2,"\n";
        }
    }
}

my @indexes;
unshift @indexes, "http://www.yingyu.com/stxz/chuzhong/zhongkao/";
# get index page.
my $content=get($indexes[0]);
my @hrefs=split "href=\"", $content;
shift @hrefs;
foreach $href(@hrefs) {
    if($href=~/(http:\/\/.*index[_0-9]*\.shtml)" *>[0-9]+/) {
        push @indexes, $1;
    }
}
#page download page and its relative Chinese name.
foreach $index(@indexes) {
    $content=get($index);
    # my @pages=split "<li ", $content;
    # shift @pages;
    getDownloadPage($content);
    
}