line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package NewsExtractor::SiteSpecificExtractor::www_penghutimes_com; |
2
|
1
|
|
|
1
|
|
8
|
use utf8; |
|
1
|
|
|
|
|
2
|
|
|
1
|
|
|
|
|
7
|
|
3
|
1
|
|
|
1
|
|
33
|
use Moo; |
|
1
|
|
|
|
|
2
|
|
|
1
|
|
|
|
|
6
|
|
4
|
|
|
|
|
|
|
extends 'NewsExtractor::GenericExtractor'; |
5
|
|
|
|
|
|
|
|
6
|
1
|
|
|
1
|
|
324
|
use Importer 'NewsExtractor::TextUtil' => 'reformat_dateline'; |
|
1
|
|
|
|
|
3
|
|
|
1
|
|
|
|
|
6
|
|
7
|
|
|
|
|
|
|
|
8
|
|
|
|
|
|
|
sub journalist { |
9
|
0
|
|
|
0
|
0
|
|
my ($self) = @_; |
10
|
0
|
|
|
|
|
|
my $el = $self->dom->at('h1.main-title')->next(); |
11
|
0
|
|
|
|
|
|
my ($t) = $el->all_text() =~ m/記者:\s*(\S+)\s*/; |
12
|
0
|
|
|
|
|
|
return $t; |
13
|
|
|
|
|
|
|
} |
14
|
|
|
|
|
|
|
|
15
|
|
|
|
|
|
|
sub dateline { |
16
|
0
|
|
|
0
|
0
|
|
my ($self) = @_; |
17
|
0
|
|
|
|
|
|
my $node = $self->dom->at('h1.main-title')->next()->child_nodes->first; |
18
|
0
|
|
|
|
|
|
my $t = reformat_dateline("$node", '+08:00'); |
19
|
0
|
|
|
|
|
|
return $t; |
20
|
|
|
|
|
|
|
} |
21
|
|
|
|
|
|
|
|
22
|
|
|
|
|
|
|
1; |