Last active
November 27, 2018 13:09
-
-
Save alicefuzier/964ed4cd9257cb3058a28a197f310339 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
import json | |
from elasticsearch import Elasticsearch | |
es = Elasticsearch(['https://user:password@host:443/']) | |
page = es.search( | |
index = 'indexname', | |
doc_type = 'work', | |
scroll = '2m', | |
size = 1000, | |
body = { | |
"query" : { | |
"bool": { | |
"must": [ | |
{} | |
], | |
"filter": [ | |
{"term" : { "type" : "IdentifiedWork" }}, | |
{"terms" : { "items.agent.locations.locationType.id" : ["iiif-image"] }}, | |
{"terms" : { "workType.id" : ["q","k"] }} | |
] | |
} | |
} | |
}) | |
sid = page['_scroll_id'] | |
scroll_size = page['hits']['total'] | |
file = "v2-miro-ids.txt" | |
def extract_miro_id(identifiers): | |
for identifier in identifiers: | |
if identifier['identifierType']['id'] == 'miro-image-number': | |
id = identifier['value'] | |
if not id: | |
raise Exception("there is no miro id!") | |
return id | |
def get_miro_ids(page): | |
return [extract_miro_id([hit['_source']['sourceIdentifier']] + hit['_source']['otherIdentifiers']) for hit in page['hits']['hits']] | |
with open(file,"a") as f: | |
miro_ids = get_miro_ids(page) | |
f.write(json.dumps(miro_ids)+"\n") | |
while (scroll_size > 0): | |
print("Scrolling...") | |
page = es.scroll(scroll_id = sid, scroll = '2m') | |
sid = page['_scroll_id'] | |
scroll_size = len(page['hits']['hits']) | |
miro_ids = get_miro_ids(page) | |
f.write(json.dumps(miro_ids)+"\n") | |
print("Done!") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment