Convert iTunes exported library to JSON

itunes2json.py

#!/usr/bin/env python

from __future__ import print_function
from pprint import pprint

import json
import plistlib as plist
import sys


library = plist.readPlist(sys.argv[1])

for track_id, track in library['Tracks'].iteritems():
    fields = (
        'artist',
        'name',
        'album',
        'year',
        'total_time',
        'genre',
        'play_count',
        'kind',
        'total_time',
        'bit_rate',
        'size',
    )

    track = dict(map(lambda (k,v): (k.lower().replace(' ', '_'), v), track.iteritems()))

    try:
        track_fields = dict().fromkeys(fields) & track.viewkeys()
        track = {k: track[k] for k in track_fields }

        # Filter out non-music files
        if ('kind' in track.keys() and track['kind'] in ('MPEG-4 video file', 'Ringtone')) or \
           ('genre' in track.keys() and track['genre'] in ('Podcast', 'Video Games', 'Tech News')):
            continue

        # Convert years in strings (required by Elasticsearch to index it as 'date' type)
        if 'year' in track.keys():
            track['year'] = str(track['year'])

        # Convert Track durations from milliseconds to seconds
        if 'total_time' in track.keys():
            track['total_time'] = int(track['total_time'] / 1000)

        print(json.dumps(track))
    except:
        continue

Hi
Can you please explain these steps more clearly.
1.how to create shell script and location and how to exectue it?
2 where to create index file creation,location/path and execution steps?

The more efficient way I've found to index the JSON documents into Elasticsearch is to use its Bulk API. This method requires a bit of shell scripting to bulk the records:
$ while read track; do
echo '{"index":{"_index":"library","_type":"track"}}'
echo $track
done < library.json > bulk

The library Elasticsearch index settings and mapping for the "track" document type looks like this:
$ cat library.index
{
"settings" : {
"index" : {
"number_of_shards" : 1,
"number_of_replicas" : 0
}
},
"mappings": {
"track": {
"properties": {
"year": { "format": "year", "type": "date" },
"album": { "index": "not_analyzed", "type": "string" },
"artist": { "index": "not_analyzed", "type": "string" },
"genre": { "index": "not_analyzed", "type": "string" },
"kind": { "index": "not_analyzed", "type": "string" },
"name": { "index": "not_analyzed", "type": "string" },
"play_count": { "type": "long" },
"total_time": { "type": "long" },
"bit_rate": { "type": "long" },
"size": { "type": "long"
}
}
}
}
}