json2csv

#!/usr/bin/env python3
"""
Generate list of all free IMDB entries as CSV.
"""

import argparse
import codecs
import csv
import json
import sys

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('files', metavar='N', type=str, nargs='*',
                        default=['free-movies-manual.json'],
                        help='input file(s)')
    args = parser.parse_args()

    keys = ['status', 'year', 'idurl', 'title', 'freenessurl', 'archive',
            'wp', 'wdurl', 'vodo', 'comment']

    completeset = {}
    writer = csv.DictWriter(sys.stdout, keys)
    for file in args.files:
        with open(file, 'rt', encoding='utf-8') as input:
            j = json.load(input)
            for id in j.keys():
                if not id in completeset:
                    completeset[id] = j[id]
                else:
                    #print(file,id)
                    if 'year' not in completeset[id] and 'year' in j[id]:
                        completeset[id]['year'] = j[id]['year']
                    if 'freenessurl' in completeset[id] \
                       and 'freenessurl' in j[id] \
                       and j[id]['freenessurl'] != completeset[id]['freenessurl']:
                        completeset[id]['archive'] = j[id]['freenessurl']

    #writer.writerow(keys)
    for id in sorted(completeset.keys()):
        if -1 == id.find("/www.imdb.com/title/"):
            continue
        if 'status' not in completeset[id] or 'free' != completeset[id]['status']:
            continue
        completeset[id]['idurl'] = id
        #print(j[e])
        fields = list(completeset[id].keys())
        for k in fields:
            if k not in keys:
                del completeset[id][k]
        writer.writerow(completeset[id])

if __name__ == '__main__':
    main()