Hello
You might try the following perl script, which will process every *.json file in current directory and yield out.csv.
* CSV currently uses space for field separator as you requested. Note that Numbers.app cannot import such CSV file correctly.
#!/bin/bash
/usr/bin/perl -CSDA -w <<'EOF' - *.json > out.csv
use strict;
use JSON::Syck;
$JSON::Syck::ImplicitUnicode = 1;
# json node paths to extract
my @paths = ('/upload_date', '/title', '/webpage_url');
for (@ARGV) {
my $json;
open(IN, "<", $_) or die "$!";
{
local $/;
$json = <IN>;
}
close IN;
my $data = JSON::Syck::Load($json) or next;
my @values = map { &json_node_at_path($data, $_) } @paths;
{
# output CSV spec
# - field separator = SPACE
# - record separator = LF
# - every field is quoted
local $, = qq( );
local $\ = qq(\n);
print map { s/"/""/og; q(").$_.q("); } @values;
}
}
sub json_node_at_path ($$) {
# $ : (reference) json object
# $ : (string) node path
#
# E.g. Given node path = '/abc/0/def', it returns either
# $obj->{'abc'}->[0]->{'def'} if $obj->{'abc'} is ARRAY; or
# $obj->{'abc'}->{'0'}->{'def'} if $obj->{'abc'} is HASH.
my ($obj, $path) = @_;
my $r = $obj;
for ( map { /(^.+$)/ } split /\//, $path ) {
if ( /^[0-9]+$/ && ref($r) eq 'ARRAY' ) {
$r = $r->[$_];
}
else {
$r = $r->{$_};
}
}
return $r;
}
EOF
For Automator workflow, you may use Run Shell Script action as follows, which will receive json files and yield out_YYYY-MM-DD_HHMMSS.csv on desktop.
Run Shell Script action
- Shell = /bin/bash
- Pass input = as arguments
- Code = as follows
#!/bin/bash
/usr/bin/perl -CSDA -w <<'EOF' - "$@" > ~/Desktop/out_"$(date '+%F_%H%M%S')".csv
use strict;
use JSON::Syck;
$JSON::Syck::ImplicitUnicode = 1;
# json node paths to extract
my @paths = ('/upload_date', '/title', '/webpage_url');
for (@ARGV) {
my $json;
open(IN, "<", $_) or die "$!";
{
local $/;
$json = <IN>;
}
close IN;
my $data = JSON::Syck::Load($json) or next;
my @values = map { &json_node_at_path($data, $_) } @paths;
{
# output CSV spec
# - field separator = SPACE
# - record separator = LF
# - every field is quoted
local $, = qq( );
local $\ = qq(\n);
print map { s/"/""/og; q(").$_.q("); } @values;
}
}
sub json_node_at_path ($$) {
# $ : (reference) json object
# $ : (string) node path
#
# E.g. Given node path = '/abc/0/def', it returns either
# $obj->{'abc'}->[0]->{'def'} if $obj->{'abc'} is ARRAY; or
# $obj->{'abc'}->{'0'}->{'def'} if $obj->{'abc'} is HASH.
my ($obj, $path) = @_;
my $r = $obj;
for ( map { /(^.+$)/ } split /\//, $path ) {
if ( /^[0-9]+$/ && ref($r) eq 'ARRAY' ) {
$r = $r->[$_];
}
else {
$r = $r->{$_};
}
}
return $r;
}
EOF
Tested under OS X 10.6.8.
Hope this may help,
H