use JSON;
open(IN,"<:utf8","$ARGV[0]");
while(<IN>)
{
    if (m!^\s+<text.*?>({[^\{\|].+})</text>!) {
        my $jt = $+;
        $jt=~s/\&quot;/\"/g;
        my $json = new JSON;
        my $jp = $json->allow_nonref->utf8->relaxed->decode($jt);

        my $c = $jp->{'claims'};
        # "claims":{"P31":[{"mainsnak":{"snaktype":"value","property":"P31","hash":"...","datavalue":{"value":{"entity-type":"item","numeric-id":5},...}... }...}],
        if (ref($c) eq 'HASH') {
            foreach my $ch (keys %$c) {
                if (ref($c->{$ch}) eq 'ARRAY') {
                    foreach my $cg (@{$c->{$ch}}) {
                        if (defined $cg->{'mainsnak'}->{'datavalue'}->{'value'}->{'notexist'}) {}  ## THIS LINE
                    }
                }
            }
        }
    }
}