get_miro_ids.py

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!")