extract_actor_quid.py

from __future__ import print_function
import re
import ijson.backends.yajl2 as ijson

with open("movies_rule_agent/actors.txt", "r") as f_actors:
    actors = [re.sub(r'\n', '', entry).lower() for entry in f_actors.readlines()]

with open("movies_rule_agent/actor_qids.txt", "w") as f_actor_qids:
    with open('wikidata_json_dump/latest-all.json', "r") as f_wiki:
        for obj in ijson.items(f_wiki, 'item'):
            if "en" in obj['labels']:
                actor_name = obj["labels"]["en"]["value"].lower()

                if actor_name in actors:
                    print(actor_name)
                    f_actor_qids.write("{},{}\n".format(actor_name, obj['id']))