html提取特定div中的,通过从其他HTML页面提取的DIV生成HTML页面的脚本

#!/usr/bin/perl

use strict;

use warnings;

use HTML::TokeParser;

use HTML::Template;

use Data::Dumper;

my ($html_file) = @ARGV;

open my $html_handle, '<:utf8>

or die "Cannot open '$html_file': $!";

my $parser = HTML::TokeParser->new($html_handle);

my @divs;

while (my $tag = $parser->get_tag('div')) {

my $attr = $tag->[1];

next unless ref $attr eq 'HASH';

next unless defined(my $id = $attr->{id});

next unless $id eq 'div1' or $id eq 'div2';

my $div = $tag->[-1];

my $in_wanted = 1;

while ($in_wanted) {

my $token = $parser->get_token;

if ($token->[0] eq 'T') {

$div .= $token->[1];

}

else {

$div .= $token->[-1];

}

my ($type, $name) = @$token[0, 1];

if ($name eq 'div') {

$in_wanted += $type eq 'S' ? 1

: $type eq 'E' ? -1

: 0;

next;

}

if ($type eq 'E' and $name eq 'html') {

warn "Warning: Reached the end of '$html_file'\n";

last;

}

}

push @divs, {DIV => $div};

}

print output(@divs);

sub output {

my $tmpl_html = <

EO_TMPL

my $tmpl = HTML::Template->new(

scalarref => \$tmpl_html,

);

$tmpl->param(DIVS => \@_);

return $tmpl->output;

}