README.md
1# NAME
2
3HTML::TreeBuilder::LibXML - HTML::TreeBuilder and XPath compatible interface with libxml
4
5# SYNOPSIS
6
7 use HTML::TreeBuilder::LibXML;
8
9 my $tree = HTML::TreeBuilder::LibXML->new;
10 $tree->parse($html);
11 $tree->eof;
12
13 # $tree and $node compatible to HTML::Element
14 my @nodes = $tree->findvalue($xpath);
15 for my $node (@nodes) {
16 print $node->tag;
17 my %attr = $node->all_external_attr;
18 }
19
20 HTML::TreeBuilder::LibXML->replace_original(); # replace HTML::TreeBuilder::XPath->new
21
22# DESCRIPTION
23
24HTML::TreeBuilder::XPath is libxml based compatible interface to
25HTML::TreeBuilder, which could be slow for a large document.
26
27HTML::TreeBuilder::LibXML is drop-in-replacement for HTML::TreeBuilder::XPath.
28
29This module doesn't implement all of HTML::TreeBuilder and
30HTML::Element APIs, but enough methods are defined so modules like
31Web::Scraper work.
32
33# BENCHMARK
34
35This is a benchmark result by tools/benchmark.pl
36
37 Web::Scraper: 0.26
38 HTML::TreeBuilder::XPath: 0.09
39 HTML::TreeBuilder::LibXML: 0.01_01
40
41 Rate no_libxml use_libxml
42 no_libxml 5.45/s -- -94%
43 use_libxml 94.3/s 1632% --
44
45# AUTHOR
46
47Tokuhiro Matsuno <tokuhirom@gmail.com>
48
49Tatsuhiko Miyagawa <miyagawa@cpan.org>
50
51Masahiro Chiba
52
53# THANKS TO
54
55woremacx++
56http://d.hatena.ne.jp/woremacx/20080202/1201927162
57
58id:dailyflower
59
60# SEE ALSO
61
62[HTML::TreeBuilder](http://search.cpan.org/perldoc?HTML::TreeBuilder), [HTML::TreeBuilder::XPath](http://search.cpan.org/perldoc?HTML::TreeBuilder::XPath)
63
64# LICENSE
65
66This library is free software; you can redistribute it and/or modify
67it under the same terms as Perl itself.
68