line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package NewsExtractor::SiteSpecificExtractor::m_news_cctv_com; |
2
|
1
|
|
|
1
|
|
19
|
use utf8; |
|
1
|
|
|
|
|
2
|
|
|
1
|
|
|
|
|
7
|
|
3
|
1
|
|
|
1
|
|
43
|
use Moo; |
|
1
|
|
|
|
|
3
|
|
|
1
|
|
|
|
|
6
|
|
4
|
|
|
|
|
|
|
extends 'NewsExtractor::GenericExtractor'; |
5
|
|
|
|
|
|
|
|
6
|
1
|
|
|
1
|
|
363
|
use Importer 'NewsExtractor::TextUtil' => qw(normalize_whitespace reformat_dateline); |
|
1
|
|
|
|
|
2
|
|
|
1
|
|
|
|
|
7
|
|
7
|
|
|
|
|
|
|
|
8
|
|
|
|
|
|
|
sub dateline { |
9
|
0
|
|
|
0
|
0
|
|
my ($self) = @_; |
10
|
0
|
0
|
|
|
|
|
my $el = $self->dom->at('span.info i') or return; |
11
|
0
|
|
|
|
|
|
return reformat_dateline( $el->all_text(), '+08:00' ); |
12
|
|
|
|
|
|
|
} |
13
|
|
|
|
|
|
|
|
14
|
|
|
|
|
|
|
sub journalist { |
15
|
0
|
|
|
0
|
0
|
|
my ($self) = @_; |
16
|
0
|
|
|
|
|
|
my ($txt) = $self->content_text() =~ m/( (?:总台记者|编辑) (.+?))\z/xg; |
17
|
0
|
|
|
|
|
|
$txt = normalize_whitespace($txt); |
18
|
0
|
|
|
|
|
|
return $txt; |
19
|
|
|
|
|
|
|
} |
20
|
|
|
|
|
|
|
|
21
|
|
|
|
|
|
|
1; |