cities.py

#! /usr/bin/env python3
# python3 script to retrieve Iran and Afghnistan provinces' capital cities coordinates.
# Written by Ebrahim Byagowi

import json
import re
import requests

query_result = requests.get('https://query.wikidata.org/sparql', {
    "query": """
PREFIX wikibase: <http://wikiba.se/ontology#>
PREFIX wd: <http://www.wikidata.org/entity/> 
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX p: <http://www.wikidata.org/prop/>
PREFIX q: <http://www.wikidata.org/prop/qualifier/>
PREFIX v: <http://www.wikidata.org/prop/statement/>

SELECT DISTINCT ?en ?fa ?countryEn ?coord
WHERE {
    { ?province wdt:P31* wd:Q1344695 } UNION  # find Iran provinces (Q1344695)
    { ?province wdt:P31* wd:Q158683 } .       # and Afghanistan provinces (Q158683)

    ?province wdt:P17 ?country .              # put country (P17) of province on ?country

    ?province wdt:P36 ?capital .              # put province capital (P36) value on ?capitalCity
    ?capital wdt:P625 ?coord .                # put coordinate (P625) of province capital on ?coord

    SERVICE wikibase:label {
        bd:serviceParam wikibase:language "fa" .
        ?capital rdfs:label ?fa
    }
    SERVICE wikibase:label {
        bd:serviceParam wikibase:language "en" .
        ?capital rdfs:label ?en .
        ?country rdfs:label ?countryEn
    }
}
""",
    "format": "json"
}).json()["results"]['bindings']

result = {
    "zz": {
        "en": "",
        "fa": "",
        "cities": {
            "CUSTOM": {
                "en": "None",
                "fa": "هیچ کدام",
                "latitude": 0,
                "longitude": 0
            }
        }
    },
    "ir": {
        "en": "Iran",
        "fa": "ایران",
        "cities": {}
    },
    "af": {
        "en": "Afghanistan",
        "fa": "افغانستان",
        "cities": {}
    }
}

for x in query_result:
    coord = re.findall(r'\(([\d\.]{,5})\d* ([\d\.]{,5})', x["coord"]["value"])
    country = "ir" if x["countryEn"]["value"] == "Iran" else "af"
    key = x["en"]['value'].upper().replace(" ", "_")
    result[country]["cities"][key] = {
        "en": x["en"]['value'],
        "fa": x["fa"]['value'],
        "latitude": float(coord[0][0]),
        "longitude": float(coord[0][1])
    }


with open('cities.json', 'w+') as f:
    json.dump(result, f, indent=2)