Small script for importing csv files to elasticsearch

elasticsearch_import.py

#!/usr/bin/env python

import argparse
import sys, os, time
import pandas
import requests
from elasticsearch import Elasticsearch
es = Elasticsearch()


def process_file(datafile, host, port, filetype, index, group, clear_index, sep):
    ''' Host and Port not supported yet '''
    if 'csv' not in filetype:
        print('Just csv supported for now')
        sys.exit(1)

    if clear_index:
        resp = es.indices.delete(index=index, ignore=[404])
        print resp

    df = pandas.io.parsers.read_csv(datafile, sep=sep)
    df.fillna(0,inplace=True) 
    for (i, row) in df.iterrows():
        res = es.index(index=index, doc_type=group, body=row.to_dict())
        if i%1000==0:
            print i

if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--host', default='localhost')
    parser.add_argument('--port', default='9200')
    parser.add_argument('--index', required=True)
    parser.add_argument('--group', required=True)
    parser.add_argument('--sep', default=',', help="Separator for csv files")

    parser.add_argument('--clear-index', dest='clear_index', action='store_true')
    parser.add_argument('--dont-clear-index', dest='clear_index', action='store_false')
    parser.set_defaults(clear_index=True)

    parser.add_argument('datafile')



    args = parser.parse_args()

    _, fileext = os.path.splitext(args.datafile)
    process_file(filetype=fileext, **vars(args))