def main():
client = ASnakeClient(baseurl='XXXX', username='******', password='******')
client.authorize()
changes = {
'linear_feet': ['Linear Feet', 'linear ft.', 'Linear Foot'],
'cubic_feet': ['Cubic Feet'],
'gigabytes': ['Gigabytes']
}
res_records = (client.get('repositories/2/resources',
params={'all_ids': True})).json()
found_records = set([])
for record in tqdm(res_records):
rec_uri = 'repositories/2/resources/{0}'.format(record)
res_record = client.get(rec_uri).json()
updated_record = deepcopy(res_record)
try:
extents = res_record['extents']
for ext_index, extent in enumerate(extents):
for key, value in changes.items():
if extent['extent_type'] in value:
updated_record['extents'][ext_index][
'extent_type'] = key
break
else:
pass
if res_record['extents'] != updated_record['extents']:
response = client.post(rec_uri, json=updated_record)
if response.status_code == 200:
logger.info('Extent change successfully pushed',
rec=record,
response=response)
found_records.add(record)
else:
logger.info('Extent change failed',
rec=record,
response=response)
else:
pass
except:
pass
print('{0} resource records checked; {1} records updated.'.format(
len(res_records), len(found_records)))
types.append(child_type)
unknown_count += 1
for indicator in indicators:
try:
del instance["sub_container"][indicator]
except Exception as e:
print("There was an error when deleting the unknown indicator: {}".format(e))
print(instance)
for child_type in types:
try:
del instance["sub_container"][child_type]
except Exception as e:
print("There was an error when deleting the unknown child/grandchild type: {}".format(e))
print(instance)
if indicators and types:
update_ao = client.post(node.uri, json=ao_json).json()
print(update_ao)
else:
indicators = []
types = []
for key, value in instance.items():
if "indicator_" in key:
if "unknown container" == value:
child_type = "type_" + str(key[-1])
indicators.append(key)
types.append(child_type)
unknown_count += 1
for indicator in indicators:
try:
del instance[indicator]
except Exception as e:
# print instructions
print(
'This script takes viafCorporateResults.csv and posts the organizations as corporate_entities to ArchivesSpace.'
)
input('Press Enter to continue...')
# This is where we connect to ArchivesSpace.
client = ASnakeClient()
client.authorize() # login, using default values
targetFile = 'viafCorporateResults.csv'
csv = csv.DictReader(open(targetFile))
orgList = []
for row in csv:
orgRecord = {}
# changed this since ASpace doesn't come with 'viaf' as an option for source out of the box.
source = 'naf' if row.get('lc') is not None else 'local'
orgRecord['names'] = [{
'primary_name': row['result'],
'sort_name': row['result'],
'source': source,
'authority_id': row['lc']
}]
post = client.post('/agents/corporate_entities', json=orgRecord).json()
print(post, '\n')
print("Check out your instance of ArchivesSpace to see what's new.")
def main(ID, path=None, accession=None):
if path == None:
if not os.path.isdir(defaultPath):
raise Exception("ERROR: default path " + defaultPath +
" does not exist.")
path = os.path.join(defaultPath, ID)
if not os.path.isdir(path):
raise Exception("ERROR: no " + ID +
" directory exists for ingest in " + defaultPath)
else:
if not os.path.isdir(path):
raise Exception("ERROR: " + str(path) + " is not a valid path.")
print("Reading " + path)
if accession == None:
print("Building SIP...")
SIP = SubmissionInformationPackage()
SIP.create(ID)
SIP.package(path)
print("SIP " + SIP.bagID + " created.")
else:
print("Reading accession " + accession)
import asnake.logging as logging
from asnake.client import ASnakeClient
client = ASnakeClient()
client.authorize()
logging.setup_logging(stream=sys.stdout, level='INFO')
call = "repositories/2/search?page=1&aq={\"query\":{\"field\":\"identifier\", \"value\":\"" + accession + "\", \"jsonmodel_type\":\"field_query\"}}"
accessionResponse = client.get(call).json()
if len(accessionResponse["results"]) < 1:
raise Exception("ERROR: Could not find accession with ID: " +
accession)
else:
accessionObject = json.loads(
accessionResponse["results"][0]["json"])
if "id_1" in accessionObject.keys():
accessionID = accessionObject["id_0"] + "-" + accessionObject[
"id_1"]
if accession != accessionID:
raise Exception(
"ERROR: Could not find exact accession with ID: " +
accession)
if not "content_description" in accessionObject.keys():
raise Exception("ERROR: no content description in " +
accessionID + " accession, " +
accessionObject["uri"])
if len(accessionObject["related_resources"]) < 1:
raise Exception("ERROR: no related resource for " +
accessionID + " accession, " +
accessionObject["uri"])
else:
resource = client.get(
accessionObject["related_resources"][0]["ref"]).json()
creator = resource["title"]
if not ID.lower() == resource["id_0"].lower():
raise Exception("ERROR: accession " + accessionID +
" does not link to collection ID " + ID +
". Instead linked to " + resource["id_0"])
description = accessionObject["content_description"]
print("Building SIP...")
SIP = SubmissionInformationPackage()
SIP.create(ID)
SIP.package(path)
print("SIP " + SIP.bagID + " created.")
SIP.bag.info["Accession-Identifier"] = accessionID
SIP.bag.info["ArchivesSpace-URI"] = accessionObject["uri"]
SIP.bag.info["Records-Creator"] = creator
SIP.bag.info["Content-Description"] = description
if "condition_description" in accessionObject.keys():
SIP.bag.info["Condition-Description"] = accessionObject[
"condition_description"]
if "provenance" in accessionObject.keys():
SIP.bag.info["Provenance"] = accessionObject["provenance"]
if "general_note" in accessionObject.keys():
SIP.bag.info["General-Note"] = accessionObject[
"general_note"]
SIP.bag.info["Source-Location"] = path
SIP.bag.info[
"Transfer-Method"] = "https://github.com/UAlbanyArchives/ingest-processing-workflow/ingest.py"
print("Writing checksums...")
SIP.bag.save(manifests=True)
print("SIP Saved!")
# List files in txt for processing
print("(not) Listing files for processing...")
#listFiles(ID)
if accession == None:
SIP.extentLog(
"/media/SPE/DigitizationExtentTracker/DigitizationExtentTracker.xlsx"
)
print("Logged ingest to DigitizationExtentTracker.")
else:
print("Updating accession " + accessionID)
if "disposition" in accessionObject.keys():
accessionObject["disposition"] = accessionObject[
"disposition"] + "\n" + str(SIP.bagID)
else:
accessionObject["disposition"] = str(SIP.bagID)
totalSize = SIP.size()
inclusiveDates = SIP.dates()
extent = {
"jsonmodel_type": "extent",
"portion": "whole",
"number": str(totalSize[0]),
"extent_type": str(totalSize[1])
}
extentFiles = {
"jsonmodel_type": "extent",
"portion": "whole",
"number": str(totalSize[2]),
"extent_type": "Digital Files"
}
if inclusiveDates[0] == inclusiveDates[1]:
date = {
"jsonmodel_type": "date",
"date_type": "inclusive",
"label": "creation",
"begin": inclusiveDates[0],
"expression": inclusiveDates[0]
}
else:
date = {
"jsonmodel_type": "date",
"date_type": "inclusive",
"label": "creation",
"begin": inclusiveDates[0],
"end": inclusiveDates[1]
}
if "extents" in accessionObject.keys():
accessionObject["extents"].append(extent)
accessionObject["extents"].append(extentFiles)
else:
accessionObject["extents"] = [extent, extentFiles]
accessionObject["dates"].append(date)
updateAccession = client.post(accessionObject["uri"],
json=accessionObject)
if updateAccession.status_code == 200:
print("\tSuccessfully updated accession " + accessionID)
else:
print(updateAccession.text)
print("\tERROR " + str(updateAccession.status_code) +
"! Failed to update accession: " + accessionID)
return SIP
import json, csv, runtime
from asnake.client import ASnakeClient
# print instructions
print(
'This script replaces existing fauxcodes with real barcodes (linked in a separate csv file) in ArchivesSpace.'
)
input('Press Enter to connect to ArchivesSpace and post those barcodes...')
# This is where we connect to ArchivesSpace. See authenticate.py
client = ASnakeClient()
client.authorize()
# open csv and generate dict
reader = csv.DictReader(open('barcodes.csv'))
# GET each top_container listed in top_containers and add to records
print('The following barcodes have been updated in ArchivesSpace:')
for row in reader:
uri = row['uri']
container = client.get(uri).json()
container['barcode'] = row['real']
post = client.post(uri, json=container).json()
print(post)
title=str(row['Title'])
identifier=str(row['Identifier'])
urlRaw=str(row['url']
# Have to clean the URL
url=urlRaw.replace("/api/items","/items/show")
# print(title+identifier+url)
# file_version = {
# "jsonmodel_type":"digital_object",
# "file_uri":url,
# "is_representative":False,
# "caption":title+" ["+url+"]",
# "use_statement":"Image-Service",
# "publish":True}
data = { "jsonmodel_type":"digital_object",
"file_versions": [{
"jsonmodel_type":"file_version",
"file_uri":url,
"is_representative":False,
"caption":title+" ["+url+"]",
"use_statement":"Image-Service",
"publish":True}],
"digital_object_id":identifier,
"title":title}
r = client.post('repositories/3/digital_objects', json.dumps(data))
print(json.dumps(data))
idList = []
for aID in accessions:
entry = client.get("repositories/2/accessions/" + str(aID)).json()
if entry["accession_date"].split("-")[0] == "2019":
idList.append(int(entry["id_1"]))
newID = max(idList) + 1
if len(str(newID)) == 1:
newID = "00" + str(newID)
elif len(str(newID)) == 2:
newID = "0" + str(newID)
print ("Creating new accession " + year + "-" + str(newID) + "...")
newAccession["id_0"] = year
newAccession["id_1"] = str(newID)
accessionID = year + "-" + str(newID)
updateAccession = client.post("repositories/2/accessions", json=newAccession)
if updateAccession.status_code == 200:
print ("\tSuccessfully updated accession " + newAccession["id_0"] + "-" + newAccession["id_1"])
else:
print ("\tERROR " + str(updateAccession.status_code) + "! Failed to update accession: " + newAccession["id_0"] + "-" + newAccession["id_1"])
print ("Waiting for new accession to be indexed...")
time.sleep(120)
print ("Ingesting records at " + path)
arrangementSwitch = False
arrangementsPath = "/media/Masters/Archives/arrangements"
arrangements = os.path.join(arrangementsPath, args.ID.upper())
if os.path.isdir(arrangements):
arrangementSwitch = True
# Remove normalized end date
try:
if date['end']:
print('normalized end date exists; will be removed')
date.pop('end')
update = True
except KeyError:
print('no normalized end date')
print()
print('Dates will be updated to:')
print(date)
print()
if update:
update = client.post(collectJson['uri'], json=collectJson)
print(update.status_code)
# Print all dates
num = collectJson['uri'].replace('/repositories/2/resources/', '')
collection = repo.resources(num)
for date in collection.dates:
date_type = ''
date_expression = ''
date_begin = ''
date_end = ''
try:
date_type = date.date_type
date_expression = date.expression
date_begin = date.begin
import json
import time
from asnake.client import ASnakeClient
startTime = time.time()
client = ASnakeClient()
client.authorize()
records = json.load(open('all_AOs.json'))
for record in records:
post = client.post('/repositories/3/archival_objects', json=record).json()
print(post)
elapsedTime = time.time() - startTime
m, s = divmod(elapsedTime, 60)
h, m = divmod(m, 60)
print('Total script run time: ', '%d:%02d:%02d' % (h, m, s))
from asnake.client import ASnakeClient
from secrets import *
as_username = input("ArchivesSpace username: "******"ArchivesSpace password: "******"repositories").json()
print("Publishing Digital Objects...", end='', flush=True)
for repo in repos:
digital_object = {}
dig_objs_per_repo = []
repo_digital_objects = client.get(repo["uri"] + "/digital_objects?all_ids=true").json()
for dig_obj_id in repo_digital_objects:
object_request = repo["uri"] + "/digital_objects/" + str(dig_obj_id) + "/publish"
try:
client.post(object_request)
except Exception as e:
print("Error found when requesting id: " + str(e) + "\n" + object_request)
# digital_object[dig_obj_id] = client.get(repo["uri"] + "/digital_objects/" + str(dig_obj_id)).json()
# dig_objs_per_repo.append(digital_object)
# repo_dig_objects[repo['name']] = dig_objs_per_repo
print("Done")
# print(json_data)
})
# Can't use get_paged because this endpoint returns raw Solr
results = client.get(endpoint, params={
'aq': advanced_query
}).json()["response"]["docs"]
# populate top_containers with the ids of each top_container in search results
top_containers = []
for value in gen_dict_extract('id', results):
top_containers.append(value)
# GET each top_container listed in top_containers and add to records
records = []
for top_container in top_containers:
output = client.get(top_container).json()
records.append(output)
# have user enter container profile id
profile_id = input(
'Enter container profile ID (I am going to enter 9. You can select another value, as long that ID is in your instance of ArchivesSpace.): '
)
# Add container profile to records and post
print('The following records have been updated in ArchivesSpace:')
for record in records:
record['container_profile'] = {'ref': '/container_profiles/' + profile_id}
jsonLine = record
uri = record['uri']
post = client.post(uri, json=jsonLine).json()
print(post)
from openpyxl import load_workbook
from secrets import *
from asnake.aspace import ASpace
from asnake.client import ASnakeClient
aspace = ASpace(baseurl=as_api, username=as_un, password=as_pw)
client = ASnakeClient(baseurl=as_api, username=as_un, password=as_pw)
client.authorize()
resource_id = input("Enter ASpace URI: ")
excel_filepath = input("Enter full filepath for spreadsheet: ")
wb = load_workbook(excel_filepath)
sheet = wb.active
for row in sheet.iter_rows(min_row=2, values_only=True):
archival_object = client.get(row[0]).json()
print("Converting: {} > {} ... ".format(
archival_object["instances"][0]["sub_container"]["indicator_2"],
row[5]),
end='',
flush=True)
archival_object["instances"][0]["sub_container"]["indicator_2"] = str(
row[5])
update_ao = client.post(row[0], json=archival_object)
print("Done. Response: {}".format(update_ao.json()))
# Note: if this script is re-run to create new digital objects or updated to include additional rows
# (e.g. after changing the do object IDs, or if you attempt to add another row that references a preceding archival object)
# then only the most-recently created digital objects will be linked
# and the previously-created digital objects will be orphaned records.
# Parse csv and update ArchivesSpace.
for row in csv_dict:
file_uri = row['fileuri']
title = row['title']
digital_object_id = row['objectid']
ref_ID = row['refID']
# Construct new digital object from csv
doRecord = {'title': title, 'digital_object_id': digital_object_id, 'publish': False}
doRecord['file_versions'] = [{'file_uri': file_uri, 'publish': False, 'file_format_name': 'jpeg'}]
doPost = client.post('/repositories/2/digital_objects', json=doRecord).json()
print(doPost)
# Store uri of newly posted digital objects because we'll need it
uri = doPost['uri']
# Find AOs based on refIDs supplied in csv
AOQuery = json.dumps({
"query": {
"jsonmodel_type":"boolean_query",
"op":"AND",
"subqueries":[
{
"jsonmodel_type":"field_query",
"field":"primary_type",
"value":"archival_object",
"literal":True
},
repository_processing_note)
raw_input = input("Proceed anyway? y/n?")
if raw_input == "n":
break
else:
pass
except:
pass
#Test for unpublished nodes, only proceed with publish and export if no unpublished nodes
if has_unpublished_nodes() == False:
#If the finding aid status is already set to publish, just export the EAD
if "published" in publish_status:
# Set publish to 'true' for all levels, components, notes, etc. Same as clicking "publish all" in staff UI
resource_publish_all = aspace_client.post(resource_uri +
'/publish')
print(eadID + ' | resource and all children set to published')
#Pause for 10 seconds so publish action takes effect...maybe?
print(eadid +
" | Pausing for 10 seconds to index publish action...")
time.sleep(10.0)
print(eadID + " | Exporting EAD file...")
ead = aspace_client.get(id_uri_string + '.xml' +
export_options).text
f = io.open(destination + eadID + '.xml',
mode='w',
encoding='utf-8')
f.write(ead)
f.close()
print(eadID + '.xml'
' | ' + resource_id + ' | ' + aspace_id_short + ' | ' +
print("Logged into: " + repo['name'])
print("Getting list of resources...")
resources_list = aspace_client.get(
"repositories/2/resources?all_ids=true").json()
resources_sorted = sorted(resources_list, reverse=True)
for resource in resources_sorted:
try:
resource_json = aspace_client.get("repositories/2/resources/" +
str(resource)).json()
#print (resource_json)
resource_uri = resource_json['uri']
print("updating: " + resource_uri)
resource_update = aspace_client.post(resource_json['uri'],
json=resource_json)
response = resource_update.json()
logger.info('update_resource',
action='updating-resource',
data={
'resource_uri': resource_uri,
'response': response
})
print(response['status'])
except:
print("ERROR")
pass
print("All Done with Resources...")
print("Getting list of archival_objects...")
ao_list = aspace_client.get(
import json, time, runtime
from asnake.client import ASnakeClient
from asnake.client.web_client import ASnakeAuthError
# Create a client
client = ASnakeClient()
client.authorize() # login, using default values
# print instructions
print ("This script will add the container_profiles included in a separate json file to ArchivesSpace.")
input("Press Enter to continue...")
# post container_profiles
print ("The following container profiles have been added to ArchivesSpace:")
jsonfile = open("containerProfiles.json")
jsonfile = json.load(jsonfile)
for container_profile in jsonfile:
post = client.post("/container_profiles", json=container_profile).json()
print (post)
print ("You've just completed your first API POST. Congratulations!")
except:
properDates = ''
viafid = response['viafID']
except:
label = ''
viafid = ''
if viafid != '':
links = json.loads(
requests.get('http://viaf.org/viaf/' + viafid +
'/justlinks.json').text)
viafid = 'http://viaf.org/viaf/' + viafid
toPost = {
"lock_version":
lockVersion,
"names": [{
"primary_name": properPrimary.strip(),
"rest_of_name": properSecondary.strip(),
"dates": properDates.strip(),
"sort_name": properName,
"authorized": True,
"is_display_name": True,
"source": "viaf",
"rules": "dacs",
"name_order": "inverted",
"jsonmodel_type": "name_person",
"authority_id": viafid
}]
}
post = client.post(uri, json=toPost).json()
print(post)
str(len(children_of_fake_wrapper_component_dict)) +
" Direct Children of Wrapper Component")
row.append(
str(len(children_of_fake_wrapper_component_dict)) +
" children of Wrapper AO")
print("Reposting children as direct children of resource...")
#Capture any error responses and save to output CSV report
success_ao_keys_list = []
fail_ao_keys_list = []
for key, value in children_of_fake_wrapper_component_dict.items():
#Repost AOs as direct children of Resource (to flatten the tree) based on Dict info
update_resource = aspace_client.post(resource_object.uri +
'/accept_children',
params={
'children[]': key,
'position': value
}).json()
try:
if update_resource['status'] == "Updated":
print("Status: " + update_resource['status'])
success_ao_keys_list.append(key)
else:
print("NOT UPDATED")
fail_ao_keys_list.append(key)
except:
print("ERROR REPOSTING AO")
fail_ao_keys_list.append(key)
if len(fail_ao_keys_list) != 0:
row.append("ERROR Posting AOs: " + str(fail_ao_keys_list))
print('Digital object already exists.')
else:
doPost['digital_object_id'] = doid
doPost['title'] = 'Web crawl of ' + crawl['original']
doPost['dates'] = [{
'expression': crawl['timestamp'],
'date_type': 'single',
'label': 'creation'
}]
doPost['file_versions'] = [{
'file_uri': crawl['filename'],
'checksum': crawl['digest'],
'checksum_method': 'sha-1'
}]
if doPost != {}:
post = client.post('/repositories/2/digital_objects',
json=doPost).json()
print(post)
doItem = {}
doItem['digital_object'] = {'ref': post['uri']}
doItem['instance_type'] = 'digital_object'
newInstances.append(doItem)
aoGet = client.get(uri).json()
existingInstances = aoGet['instances']
existingInstances = existingInstances + newInstances
aoGet['instances'] = existingInstances
aoUpdate = client.post(uri, json=aoGet).json()
print('The following archival objects have been updated in ArchivesSpace:')
print(aoUpdate)
# TO DO LATER
# Parse dates for ArchivesSpace record, push to AOs above
