perl 抓取html,perl 抓取网页内容

抓取×××网历年排列5数据

use LWP::Simple;

use FileOperate;

my $src = 'http://www.17500.cn/p5/all.php';

my $FileOperate = FileOperate->new();

my $FilePath = "C:\\Documents and Settings\\Administrator\\桌面\\PrelTest\\保存的模块\\文本处理";

#获取文件夹下所有内容

#http://www.17500.cn/p5/all.php?p=5

foreach my $index(1..200)

{

$url=$src."?p=".$index;

my @FileContent;

#print "usl is $url\n";

#my $input = ;

my $content = get $url;

die "Couldn't get $url" unless defined $content;

#  $content 里是网页内容，下面是对此内容作些分析：

#print $content ;

my $WriteFilePath = $index.".txt";

push @FileContent,$content;

FileOperate->WriteFileContent($WriteFilePath,@FileContent);

undef @FileContent;

}

my $input = ;

if($content =~ m/jazz/i) {

print "They're talking about jazz today on Fresh Air!/n";

} else {

print "Fresh Air is apparently jazzless today./n";

}