azq2 / perl-html5-dom Goto Github PK

C:\home\sunnyday1>cpan ZHUMARIN/HTML5-DOM-1.23.tar.gz

Configuring Z/ZH/ZHUMARIN/HTML5-DOM-1.23.tar.gz with Makefile.PL
CPAN: CPAN::Reporter loaded ok (v1.2018)
Checking if your kit is complete...
Warning: the following files are missing in your kit:
        HTML5-DOM-1.23/META.json
        HTML5-DOM-1.23/META.yml
Please inform the author.

my $t = {
    t0 => sub {
        state $parser = HTML5::DOM->new( { threads => 0, } );

        my $tree = $parser->parse($html);
    },
    t4 => sub {
        state $parser = HTML5::DOM->new( { threads => 4, } );

        my $tree = $parser->parse($html);
    },
};

Benchmark::cmpthese( Benchmark::timethese( 1000, $t ) );

Benchmark: timing 1000 iterations of t0, t4...
        t0:  5 wallclock secs ( 3.63 usr +  0.85 sys =  4.48 CPU) @ 223.21/s (n=1000)
        t4:  8 wallclock secs ( 8.12 usr +  1.87 sys =  9.99 CPU) @ 100.10/s (n=1000)
    Rate   t4   t0
t4 100/s   -- -55%
t0 223/s 123% 

my $parser = HTML5::DOM->new( {
    threads => 4,
    async   => 1,
} );
my $tree = $parser->parse($html);
say $tree->parsed ? 1 : 0;

use strict;
use warnings;

use LWP::UserAgent;
use HTTP::Request;
use HTML5::DOM;
use Encode;

my $ua = LWP::UserAgent->new();
my $response = $ua->request(
  HTTP::Request->new(
	'GET' => 'https://www.areiospagos.gr/proedros.htm',
	[
		'Connection' => 'keep-alive',
		'Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
		'Accept-Encoding' => 'gzip, deflate',
		'Accept-Language' => 'en-GB,en;q=0.5',
		'Referer' => 'http://www.polignosi.com/cgibin/hweb',
		'User-Agent' => 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/110.0',
		'Upgrade-Insecure-Requests' => '1'
	],
  )
);
die unless $response && $response->is_success;

my $html = $response->decoded_content;

print "encoding using detect(): ".HTML5::DOM::Encoding::id2name(HTML5::DOM::Encoding::detect($html))."\n";
print "encoding using detectUnicode(): ".HTML5::DOM::Encoding::id2name(HTML5::DOM::Encoding::detectUnicode($html))."\n";
print "encoding using detectByPrescanStream(): ".HTML5::DOM::Encoding::id2name(HTML5::DOM::Encoding::detectByPrescanStream($html))."\n";

# The above html contains
#  <meta http-equiv="Content-Type" content="text/html; charset=windows-1253">
# replacing the crappy windows-1253 with UTF-8 solves my problem
#$html =~ s/charset=windows-1253/charset=UTF-8/g;

my $parser = HTML5::DOM->new();

my $tree = $parser->parse($html, {scripts => 0});

my $is_utf8_enabled = $tree->utf8;
# it prints 'true'
print "is_utf8_enabled=".($tree ? "true" : "false")."\n"; # false
my $text = $tree->find('body table#table1 tbody tr td table#table2 tbody tr td p span')->[0]->text();
# it prints gibberish (doubly-encoded)
print $text;
# it is solved by replacing the windows-1235 charset from $html, see above

Can't locate object method "outerHTML" via package "HTML5::DOM::Tree"

say HTML5::DOM->new->parse('<b>тест</b>')->at('b')->text;

use HTML5::DOM;

my $textWin1251 = "<p>Если заголовок заполнен, а подзаголовка нет – для материала все остается так же, как раньше.</p>";
my $parser = HTML5::DOM->new();

print $DOM_tree->encoding; # WINDOWS-1251
print $DOM_tree->utf8; # 0

my $DOM_tree = $parser->parse($text);
my $nodes = $DOM_tree->querySelectorAll('body > *');
my $div2 = $DOM_tree->createElement('div');

$div2->innerHTML(qq{<div>Вставляемый фрагмент кода</div>});

$nodes->[0]->after($div2);

$textWin1251 = $DOM_tree->body->innerHTML;

print $textWin1251;

my $parser = HTML5::DOM->new({
  encoding => "WINDOWS-1251", # and / or
  utf8 => 0, # and / or
  default_encoding => "WINDOWS-1251"
});