script updates

Author: ehanson8

getArrayPropertiesFromAgentsPeopleCSV.py

@@ -2,6 +2,9 @@
 import requests
 import secrets
 import csv
+import time
+
+startTime = time.time()
 
 baseURL = secrets.baseURL
 user = secrets.user
@@ -10,12 +13,29 @@
 auth = requests.post(baseURL + '/users/'+user+'/login?password='+password).json()
 session = auth["session"]
 headers = {'X-ArchivesSpace-Session':session, 'Content_Type':'application/json'}
+print 'authenticated'
+
+endpoint = '/agents/people?all_ids=true'
+
+ids = requests.get(baseURL + endpoint, headers=headers).json()
+
+records = []
+for id in ids:
+    endpoint = '/agents/people/'+str(id)
+    output = requests.get(baseURL + endpoint, headers=headers).json()
+    records.append(output)
 
-endpoint = '/agents/people'
-arguments = '?page=1&page_size=3000'
-output = requests.get(baseURL + endpoint + arguments, headers=headers).json()
 f=csv.writer(open('asArrayResults.csv', 'wb'))
 f.writerow(['uri']+['begin']+['end']+['expression'])
-for i in range (0, len (output['results'])):
-	for j in range (0, len (output['results'][i]['dates_of_existence'])):
-		f.writerow([json.dumps(output['results'][i]['uri']).replace('"','')]+[json.dumps(output['results'][i]['dates_of_existence'][j].get('begin','none')).replace('"','')]+[json.dumps(output['results'][i]['dates_of_existence'][j].get('end','none')).replace('"','')]+[json.dumps(output['results'][i]['dates_of_existence'][j].get('expression','none')).replace('"','')])
+for i in range (0, len (records)):
+	for j in range (0, len (records[i]['dates_of_existence'])):
+		uri = records[i]['uri']
+		beginDate = records[i]['dates_of_existence'][j].get('begin','none')
+		endDate = records[i]['dates_of_existence'][j].get('end','none')
+		expressionDate = records[i]['dates_of_existence'][j].get('expression','none')
+		f.writerow([uri]+[beginDate]+[endDate]+[expressionDate])
+
+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)

getPropertiesFromAgentsPeopleCSV.py

@@ -2,6 +2,9 @@
 import requests
 import secrets
 import csv
+import time
+
+startTime = time.time()
 
 baseURL = secrets.baseURL
 user = secrets.user
@@ -12,10 +15,15 @@
 headers = {'X-ArchivesSpace-Session':session, 'Content_Type':'application/json'}
 print 'authenticated'
 
-endpoint = '/agents/people'
-arguments = '?page=1&page_size=3000'
-output = requests.get(baseURL + endpoint + arguments, headers=headers).json()
-records = output['results']
+endpoint = '/agents/people?all_ids=true'
+
+ids = requests.get(baseURL + endpoint, headers=headers).json()
+
+records = []
+for id in ids:
+    endpoint = '/agents/people/'+str(id)
+    output = requests.get(baseURL + endpoint, headers=headers).json()
+    records.append(output)
 
 f=csv.writer(open('asResults.csv', 'wb'))
 f.writerow(['uri']+['sort_name']+['authority_id'])
@@ -24,3 +32,8 @@
 	sort_name = records[i]['names'][0]['sort_name'].encode('utf-8')
 	authority_id = records[i]['names'][0].get('authority_id', '')
 	f.writerow([uri]+[sort_name]+[authority_id])
+
+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)

getResources.py

@@ -1,6 +1,9 @@
 import json
 import requests
 import secrets
+import time
+
+startTime = time.time()
 
 baseURL = secrets.baseURL
 user = secrets.user
@@ -9,10 +12,23 @@
 auth = requests.post(baseURL + '/users/'+user+'/login?password='+password).json()
 session = auth["session"]
 headers = {'X-ArchivesSpace-Session':session, 'Content_Type':'application/json'}
+print 'authenticated'
+
+endpoint = '/repositories/3/resources?all_ids=true'
 
-endpoint = '/repositories/3/resources?page=1&page_size=3000'
+ids = requests.get(baseURL + endpoint, headers=headers).json()
+
+records = []
+for id in ids:
+    endpoint = '/repositories/3/resources/'+str(id)
+    output = requests.get(baseURL + endpoint, headers=headers).json()
+    records.append(output)
 
-output = requests.get(baseURL + endpoint, headers=headers).json()
 f=open('resources.json', 'w')
-results=(json.dump(output['results'], f))
+json.dump(records, f)
 f.close()
+
+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)

searchArchivalObjectsByResource.py

@@ -1,6 +1,9 @@
 import json
 import requests
 import secrets
+import time
+
+startTime = time.time()
 
 baseURL = secrets.baseURL
 user = secrets.user
@@ -11,16 +14,15 @@
 headers = {'X-ArchivesSpace-Session':session}
 
 resourceNumber = '1051'#Update 'resourceNumber' with the resource number for which you wish to find all of the archival objects
-
-resource ='\"/repositories/3/resources/'+resourceNumber+'\"'
-payload = {'page': '1', 'page_size': '3000', 'q': resource }
+search ='\"/repositories/3/resources/'+resourceNumber+'\"'
+payload = {'page': '1', 'page_size': '5000', 'q': search, 'type[]': 'archival_object'}
 
 search = requests.get(baseURL+'/search', headers=headers, params=payload).json()
 arrayURI = []
+
 for i in range (0, len (search['results'])):
-    if search['results'][i]['jsonmodel_type'] == 'archival_object':
-        uri = search['results'][i]['uri']
-        arrayURI.append(uri)
+    uri = search['results'][i]['uri']
+    arrayURI.append(uri)
 
 f=open('asSearchResults.json', 'w')
 arrayJSON = []
@@ -29,3 +31,7 @@
     arrayJSON.append(output)
 
 json.dump(arrayJSON, f)
+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)