File Coverage

blib/lib/NewsExtractor/SiteSpecificExtractor/news_ebc_net_tw.pm
Criterion Covered Total %
statement 9 22 40.9
branch 0 6 0.0
condition n/a
subroutine 3 7 42.8
pod 0 2 0.0
total 12 37 32.4


line stmt bran cond sub pod time code
1             package NewsExtractor::SiteSpecificExtractor::news_ebc_net_tw;
2 1     1   7 use utf8;
  1         3  
  1         7  
3 1     1   34 use Moo;
  1         3  
  1         6  
4             extends 'NewsExtractor::GenericExtractor';
5              
6 1     1   330 use Importer 'NewsExtractor::TextUtil' => 'reformat_dateline';
  1         3  
  1         7  
7              
8             sub _build_content_text {
9 0     0     my ($self) = @_;
10              
11             # Remove the in-article ad.
12             $self->dom->find("#contentb p > a[href^='https://bit.ly/']")->grep(
13             sub {
14 0 0   0     ($_->parent->children->size == 1)
15             && ($_->text =~ m/^★/)
16 0           })->map('remove');
17              
18             # Remove recommendations at the end of the article body.
19 0           $self->dom->at("#contentb div.raw-style > span:nth-child(1)")->following_nodes()->map('remove');
20              
21 0           return $self->SUPER::_build_content_text();
22             }
23              
24             sub journalist {
25 0     0 0   my ($self) = @_;
26 0 0         my $guess = $self->dom->at('.fncnews-content > .info > span.small-gray-text') or return;
27 0           my $text = $guess->all_text;
28 0           my ($name) = $text =~ m/(?:東森新聞(?:\s*責任編輯)?)\s+(.+)$/;
29 0           return $name;
30             }
31              
32             sub dateline {
33 0     0 0   my ($self) = @_;
34 0 0         my $el = $self->dom->at(".fncnews-content > .info > span.small-gray-text") or return;
35 0           return reformat_dateline($el->all_text(), '+08:00');
36             }
37              
38             1;