Python script to bulk insert an ndjson file to an ElasticSearch cluster

bulk_insert_ndjson.py

from elasticsearch import Elasticsearch
from elasticsearch.helpers import bulk

es_host = "MY_ES_URL:PORT"
user = "MY_USERNAME"
secret = "MY_PASSWORD"

file_path = "/PATH/TO/FILE.ndjson"
index = "INDEX_NAME"
doc_type = "_doc"

es = Elasticsearch(hosts=[es_host],
                   http_auth=(user, secret),
                   port=443,
                   scheme="https",
                   timeout=90)


def read_file_generator(ndjson_path):
    file_object = open(ndjson_path, 'r')
    while True:
        doc = file_object.readline()
        if not doc:
            break
        yield doc


bulk(es, read_file_generator(file_path), index=index, doc_type=doc_type)