Last active
October 6, 2023 14:59
-
-
Save hmldd/44d12d3a61a8d8077a3091c4ff7b9307 to your computer and use it in GitHub Desktop.
Example of Elasticsearch scrolling using Python client
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
# coding:utf-8 | |
from elasticsearch import Elasticsearch | |
import json | |
# Define config | |
host = "127.0.0.1" | |
port = 9200 | |
timeout = 1000 | |
index = "index" | |
doc_type = "type" | |
size = 1000 | |
body = {} | |
# Init Elasticsearch instance | |
es = Elasticsearch( | |
[ | |
{ | |
'host': host, | |
'port': port | |
} | |
], | |
timeout=timeout | |
) | |
# Process hits here | |
def process_hits(hits): | |
for item in hits: | |
print(json.dumps(item, indent=2)) | |
# Check index exists | |
if not es.indices.exists(index=index): | |
print("Index " + index + " not exists") | |
exit() | |
# Init scroll by search | |
data = es.search( | |
index=index, | |
doc_type=doc_type, | |
scroll='2m', | |
size=size, | |
body=body | |
) | |
# Get the scroll ID | |
sid = data['_scroll_id'] | |
scroll_size = len(data['hits']['hits']) | |
while scroll_size > 0: | |
"Scrolling..." | |
# Before scroll, process current batch of hits | |
process_hits(data['hits']['hits']) | |
data = es.scroll(scroll_id=sid, scroll='2m') | |
# Update the scroll ID | |
sid = data['_scroll_id'] | |
# Get the number of results that returned in the last scroll | |
scroll_size = len(data['hits']['hits']) | |
es.clear_scroll(scroll_id=sid) |
Thanks for the gist.
I also found an answer on SOF talking about the helper function scan
that abstracts away the scroll logic.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Thank you for your feedback, I have updated the gist.