Extract a specify country's locations from openweathermap city list. Very fast.

extract_country.py

# coding: utf-8
__author__ = 'Paul Cunningham'
__copyright = 'Copyright 2020, Paul Cunningham'

from jsonstreams import Stream
from jsonstreams import Type
import json
import ijson
from decimal import Decimal


class DecimalEncoder(json.JSONEncoder):
    def default(self, obj):
        if isinstance(obj, Decimal):
            return float(obj)
        return json.JSONEncoder.default(self, obj)


# http://bulk.openweathermap.org/sample/city.list.json.gz
source_file_path = 'C:/Users/Paul/Downloads/city.list.json'
sink_file_path = 'gb.city.list.json'

with Stream(Type.array, filename=sink_file_path, encoder=DecimalEncoder, indent=4, pretty=True) as sink_stream:
    with open(source_file_path, 'rb') as source_file:
        items = ijson.items(source_file, 'item')
        filtered_cities = (o for o in items if o['country'] == 'GB')
        for city in filtered_cities:
            sink_stream.write(city)