line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package NewsExtractor::SiteSpecificExtractor::www_aljazeera_com; |
2
|
1
|
|
|
1
|
|
8
|
use utf8; |
|
1
|
|
|
|
|
3
|
|
|
1
|
|
|
|
|
7
|
|
3
|
1
|
|
|
1
|
|
37
|
use Moo; |
|
1
|
|
|
|
|
3
|
|
|
1
|
|
|
|
|
6
|
|
4
|
|
|
|
|
|
|
|
5
|
|
|
|
|
|
|
extends 'NewsExtractor::JSONLDExtractor'; |
6
|
|
|
|
|
|
|
|
7
|
|
|
|
|
|
|
with 'NewsExtractor::Role::ContentTextExtractor'; |
8
|
|
|
|
|
|
|
|
9
|
1
|
|
|
1
|
|
377
|
use Importer 'NewsExtractor::TextUtil' => qw(u); |
|
1
|
|
|
|
|
3
|
|
|
1
|
|
|
|
|
7
|
|
10
|
1
|
|
|
1
|
|
42
|
use Importer 'HTTP::Date' => qw(parse_date); |
|
1
|
|
|
|
|
2
|
|
|
1
|
|
|
|
|
5
|
|
11
|
|
|
|
|
|
|
|
12
|
|
|
|
|
|
|
around dateline => sub { |
13
|
|
|
|
|
|
|
my ($orig) = shift; |
14
|
|
|
|
|
|
|
my $ret = $orig->(@_); |
15
|
|
|
|
|
|
|
my @t = parse_date($ret); |
16
|
|
|
|
|
|
|
return u(sprintf('%04d-%02d-%02dT%02d:%02d:%02d%s', $t[0], $t[1], $t[2], $t[3], $t[4], $t[5], 'Z')); |
17
|
|
|
|
|
|
|
}; |
18
|
|
|
|
|
|
|
|
19
|
|
|
|
|
|
|
1; |
20
|
|
|
|
|
|
|
|