File: HTML.pm

package info (click to toggle)
libalien-build-perl 2.84-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 3,116 kB
  • sloc: perl: 10,350; ansic: 134; sh: 66; makefile: 2
file content (166 lines) | stat: -rw-r--r-- 3,123 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
package Alien::Build::Plugin::Decode::HTML;

use strict;
use warnings;
use 5.008004;
use Alien::Build::Plugin;
use File::Basename ();

# ABSTRACT: Plugin to extract links from HTML
our $VERSION = '2.84'; # VERSION


sub init
{
  my($self, $meta) = @_;

  $meta->add_requires('share' => 'HTML::LinkExtor' => 0);
  $meta->add_requires('share' => 'URI' => 0);
  $meta->add_requires('share' => 'URI::Escape' => 0);

  $meta->register_hook( decode => sub {
    my(undef, $res) = @_;

    die "do not know how to decode @{[ $res->{type} ]}"
      unless $res->{type} eq 'html';

    my $base = URI->new($res->{base});

    my @list;

    my $p = HTML::LinkExtor->new(sub {
      my($tag, %links) = @_;
      if($tag eq 'base' && $links{href})
      {
        $base = URI->new($links{href});
      }
      elsif($tag eq 'a' && $links{href})
      {
        my $href = $links{href};
        return if $href =~ m!^\.\.?/?$!;
        my $url = URI->new_abs($href, $base);
        my $path = $url->path;
        $path =~ s{/$}{}; # work around for Perl 5.8.7- gh#8
        push @list, {
          filename => URI::Escape::uri_unescape(File::Basename::basename($path)),
          url      => URI::Escape::uri_unescape($url->as_string),
        };
      }
    });

    $p->parse($res->{content});

    return {
      type => 'list',
      list => \@list,
    };
  });

  $self;
}

1;

__END__

=pod

=encoding UTF-8

=head1 NAME

Alien::Build::Plugin::Decode::HTML - Plugin to extract links from HTML

=head1 VERSION

version 2.84

=head1 SYNOPSIS

 use alienfile;
 plugin 'Decode::HTML';

=head1 DESCRIPTION

Note: in most case you will want to use L<Alien::Build::Plugin::Download::Negotiate>
instead.  It picks the appropriate decode plugin based on your platform and environment.
In some cases you may need to use this plugin directly instead.

This plugin decodes an HTML file listing into a list of candidates for your Prefer plugin.

=head1 SEE ALSO

L<Alien::Build::Plugin::Download::Negotiate>, L<Alien::Build>, L<alienfile>, L<Alien::Build::MM>, L<Alien>

=head1 AUTHOR

Author: Graham Ollis E<lt>plicease@cpan.orgE<gt>

Contributors:

Diab Jerius (DJERIUS)

Roy Storey (KIWIROY)

Ilya Pavlov

David Mertens (run4flat)

Mark Nunberg (mordy, mnunberg)

Christian Walde (Mithaldu)

Brian Wightman (MidLifeXis)

Zaki Mughal (zmughal)

mohawk (mohawk2, ETJ)

Vikas N Kumar (vikasnkumar)

Flavio Poletti (polettix)

Salvador Fandiño (salva)

Gianni Ceccarelli (dakkar)

Pavel Shaydo (zwon, trinitum)

Kang-min Liu (劉康民, gugod)

Nicholas Shipp (nshp)

Juan Julián Merelo Guervós (JJ)

Joel Berger (JBERGER)

Petr Písař (ppisar)

Lance Wicks (LANCEW)

Ahmad Fatoum (a3f, ATHREEF)

José Joaquín Atria (JJATRIA)

Duke Leto (LETO)

Shoichi Kaji (SKAJI)

Shawn Laffan (SLAFFAN)

Paul Evans (leonerd, PEVANS)

Håkon Hægland (hakonhagland, HAKONH)

nick nauwelaerts (INPHOBIA)

Florian Weimer

=head1 COPYRIGHT AND LICENSE

This software is copyright (c) 2011-2022 by Graham Ollis.

This is free software; you can redistribute it and/or modify it under
the same terms as the Perl 5 programming language system itself.

=cut