Indexes all CSV rows under the specified index in Elasticsearch. Uses a pre-defined array of column headers to parse the CSV into a dict.

csv-indexer.py

#!/usr/bin/env python3
# encoding: utf8
# pip install elasticsearch for the elasticsearch shim :)
import csv
from elasticsearch import Elasticsearch, Urllib3HttpConnection

CSVFILE = "tptsaves.csv"
HTTP_AUTH_DETAILS = "username:password"
INDEX_NAME = "tptsaves"
DOC_NAME = "save"
COLUMNS = ["ID","Author","Name","Description","Status","Published","Uploaded","Updated","Votes","Views"]

es = Elasticsearch(http_auth=HTTP_AUTH_DETAILS)

print ("creating index unless existing...")
es.indices.create(index=INDEX_NAME, ignore=400)


# Import Saves
with open(CSVFILE, 'r', encoding="utf8") as csvf:
  reader = csv.reader(csvf, delimiter=',')
  for row in reader:
    
    # header row
    if row[0] == COLUMNS[0]: 
      continue
    
    stuff = dict(zip(KEYS, row))
    stuffid = int(stuff['ID'])
    es.index(index=INDEX_NAME, doc_type=DOC_NAME, id=stuffid, body=stuff)