Last active
November 7, 2021 17:22
-
-
Save ruthgrace/7a7689caeb8a8054ad21faa552fe1bf0 to your computer and use it in GitHub Desktop.
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
# To run this script make a directory called elasticsearch for your data. | |
# Note that this script won't work if your data is too big for local disk. | |
import pickle | |
from elasticsearch import Elasticsearch | |
### CHANGE THESE CONSTANTS TO MATCH THE ELASTICSEARCH CLUSTER YOU'RE MIGRATING FROM ### | |
ES_HOST = "example.elasticsearch.url.com" | |
ES_PORT = 9200 | |
ES_INDEX = "my_index_name" | |
ES_DOC_TYPE = "feed" | |
# Make the page size smaller if your documents are large. | |
PAGE_SIZE = 1000 | |
# Fill out the query below for the data you want to migrate. | |
query = { | |
"query": { | |
"range": { | |
"event_creation_time": { | |
"gte": some_start_time, | |
"lte": some_end_time, | |
} | |
} | |
} | |
} | |
### | |
es = Elasticsearch([{'host': ES_HOST, 'port': ES_PORT}]) | |
all_search_hits = [] | |
page = es.search( | |
index=ES_INDEX, | |
doc_type=ES_DOC_TYPE, | |
scroll='2m', | |
sort='_doc', | |
size=PAGE_SIZE, | |
body=query) | |
sid = page['_scroll_id'] | |
scroll_size = page['hits']['total'] | |
hits = page["hits"]["hits"] | |
counter = 0 | |
while scroll_size > 0: | |
output = open("elasticsearch/elasticsearch_" + str(counter) + ".pickle", "w") | |
pickle.dump(hits,output) | |
output.close() | |
page = es.scroll(scroll_id=sid, scroll='2m') | |
sid = page['_scroll_id'] | |
scroll_size = len(page['hits']['hits']) | |
hits = page["hits"]["hits"] | |
counter += 1 | |
output=open("elasticsearch/elasticsearch_" + str(counter) + ".pickle", "w") | |
pickle.dump(hits,output) | |
output.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment