Created
August 18, 2021 16:48
-
-
Save muhammadddev/2901d95af03977968de7731c41678365 to your computer and use it in GitHub Desktop.
Retrieve all the documents from an Elasticsearch index
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import json | |
import time | |
import pandas as pd | |
from elasticsearch import Elasticsearch | |
from elasticsearch.helpers import scan | |
start_time = time.time() | |
ELS_CONNECTION_STR = "http://elastic:changeme@localhost:9200/" # YOUR CONNECTION STRING | |
QUERY = {"query": {"match_all": {}}} | |
INDEX_NAME = "YOUR_INDEX_NAME" | |
print("Creating client instance of Elasticsearch") | |
elastic_client = Elasticsearch( | |
ELS_CONNECTION_STR, | |
timeout=30, | |
max_retries=10, | |
retry_on_timeout=True, | |
) | |
print("Making API call to Elasticsearch.") | |
# for more options and configuration see: https://elasticsearch-py.readthedocs.io/en/master/helpers.html#scan | |
response = scan(elastic_client, query=QUERY, index=INDEX_NAME) | |
doc_data = [] | |
for i, result in enumerate(response): | |
print(f"{i}") | |
doc_data.append(result["_source"]) | |
docs = pd.DataFrame(doc_data) | |
print("Exporting Pandas objects to different file types.") | |
docs.to_json("bakcup.json") | |
docs.to_csv("bakcup.csv") | |
print("Time elapsed:", time.time() - start_time) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment