| 1 | package NewsExtractor::SiteSpecificExtractor::www_aljazeera_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 | |||
| 5 | 1 | extends 'NewsExtractor::JSONLDExtractor'; | |
| 6 | |||
| 7 | 1 | with 'NewsExtractor::Role::ContentTextExtractor'; | |
| 8 | |||
| 9 | 1 | ▶ | use Importer 'NewsExtractor::TextUtil' => qw(u); |
|
Subroutine
BEGIN: called CC=1 SCAR=0.0
| |||
| 10 | 1 | ▶ | use Importer 'HTTP::Date' => qw(parse_date); |
|
Subroutine
BEGIN: called CC=1 SCAR=0.0
| |||
| 11 | |||
| 12 | 0 | ▶ | around dateline => sub { |
|
Subroutine
__ANON__: not called CC=1 SCAR=6.9
| |||
| 13 | 0 | my ($orig) = shift; | |
| 14 | 0 | my $ret = $orig->(@_); | |
| 15 | 0 | my @t = parse_date($ret); | |
| 16 | 0 | return u(sprintf('%04d-%02d-%02dT%02d:%02d:%02d%s', $t[0], $t[1], $t[2], $t[3], $t[4], $t[5], 'Z')); | |
| 17 | 1 | }; | |
| 18 | |||
| 19 | 1 | 1; | |
| 20 | |||