Convert Elasticsearch search result to Bulk data

search2bulk.py

#!/usr/bin/env python
import json
import sys
import os

def read_search(in_file_name):
    with open(in_file_name, 'r') as json_file:
        docs = json.load(json_file)
        return docs

def create_action(action, index, type, id):
    return {action: {"_index" : index, "_type": type, "_id": id}}

def write_bulk(docs, action, out_file_name):
    with open(out_file_name, 'w') as out_file:
        for doc in docs:
            index = doc["_index"]
            type = doc["_type"]
            id = doc["_id"]
            json.dump(create_action(action, index, type, id), out_file)
            out_file.write('\n')
            if action == "index":
                source = doc["_source"]
                json.dump(source, out_file)
                out_file.write('\n')


if __name__ == '__main__':
    if len(sys.argv) < 4:
        print "Usage: search2bulk.py [delete|index] search.json bulk.json"
        quit(1)
    action = sys.argv[1]
    in_file_name = sys.argv[2]
    out_file_name = sys.argv[3]
    docs = read_search(in_file_name)
    write_bulk(docs, action, out_file_name)