- 论坛徽章:
- 0
|
我想提取相关标签里边的内容,用这个模块实现,但什么都显示不了,郁闷~~~请大家帮帮忙看一下,什么问题!!~
use LWP;
use Data::Dumper qw(Dumper);
$Data::Dumper::Indent = 1;
use HTML::TreeBuilder;
my $browser = LWP::UserAgent->new;
my $url='http://xieguozhongblog.blog.hexun.com/';
my $file='d:\\temp\\index.htm';
my $response=$browser->get($url,':content_file'=>$file);
die "can't get $url --",$response->content_type unless $response->content_type eq 'text/html';
open FH,"<",$file||die "can't open $file :$!\n";
print "title\t\t\t\tdate\t\t\tsite\t\t\t\t\t\n";
my $tree = new HTML::TreeBuilder;
$tree->parse_file(\*FH);
#print Dumper($tree),"\n";
foreach my $row($tree->find_by_tag_name("tr"))
{
foreach my $cell($row->content_list)
{
print $cell->as_text,"123\t";
}
print "\n";
}
|
|
|