NewsExtractor/SiteSpecificExtractor/www_ntdtv_com.pm

filter: Statementstmt 44.0% 11 / 25 Branchbran 0.0% 0 / 2 Conditioncond n/a MC/DCmcdc n/a Subroutinesub 60.0% 3 / 5 Podpod 0.0% 0 / 2 totaltotal 41.1% 14 / 34 CC 2 SCAR 10.4
CC
2
Cov
41%
content_text
6.0
journalist
2.0
BEGIN
1.0
CRAP 2.8
« NewsExtractor/SiteSpecificExtractor/www_xinhuanet_com.pm ↑ Summary NewsExtractor/SiteSpecificExtractor/m_news_cctv_com.pm »
1 package NewsExtractor::SiteSpecificExtractor::www_ntdtv_com;
2 1 ▶use utf8;
Subroutine BEGIN: called CC=1 SCAR=0.0
3 1 ▶use Moo;
Subroutine BEGIN: called CC=1 SCAR=0.0
4 1 extends 'NewsExtractor::GenericExtractor';
5 1 ▶use Importer 'NewsExtractor::TextUtil' => qw( normalize_whitespace );
Subroutine BEGIN: called CC=1 SCAR=0.0
6  
7 0 ▶sub content_text {
Subroutine content_text: not called CC=2 SCAR=17.9
Pod undocumented
8 0 my ($self) = @_;
9 0 my $el = $self->dom->at("div[itemprop=articleBody]");
10 0 $el->find("div.print_link, div.single_ad")->map("remove");
11 0 my $last_child = $el->children->last;
12 0 ▶ if ($last_child->all_text =~ /相關鏈接:/) {
Branch: 1 branch
BranchTrueFalseTotal
if ($last_child->all_text =~ /\x{76f8}\x{95dc}\x{93c8}\x{63a5}\x{ff1a}/) 0 0 0
13 0 $last_child->remove;
14 }
15 0 my $txt = $el->all_text;
16 0 $txt = normalize_whitespace($txt);
17 0 return $txt;
18 }
19  
20 0 ▶sub journalist {
Subroutine journalist: not called CC=1 SCAR=6.9
Pod undocumented
21 0 my ($self) = @_;
22 0 my ($name) = $self->content_text =~ m{
23 \n
24 (
25 新唐人亞太電視\p{Letter}+?報導
26 | ( 新唐人記者[\p{Letter}、]+報導 )
27 | ( 新唐人\p{Letter}+記者站綜合報導 )
28 | (\s* 記者\p{Letter}+報導/責任編輯:\p{Letter}+ \s*)
29 | (\s* 責任編輯:\p{Letter}+ \s*)
30 | (轉自\p{Letter}+/責任編輯:\p{Letter}+ \s*)
31 | ( 採訪/\p{Letter}+ \s+ 編輯/\p{Letter}+ \s+ 後製/\p{Letter}+ )
32 )
33 \z}xs;
34  
35 0 $name =~ s/\A(//;
36 0 $name =~ s/)\z//;
37  
38 0 return $name;
39 }
40  
41 1 1;
« NewsExtractor/SiteSpecificExtractor/www_xinhuanet_com.pm ↑ Summary NewsExtractor/SiteSpecificExtractor/m_news_cctv_com.pm »