updates

Author: ehanson8

.gitignore

@@ -51,4 +51,6 @@ data/*
 !data/.keep
 .profile
 *.csv
-*.json
+*.json
+local/*
+*.xml

eadToCsv.py

@@ -62,18 +62,20 @@ def extractValuesFromComponentLevel (componentLevel):
         f.writerow([sortOrder]+[level]+[componentLevelLabel]+[containerType1]+[container1]+[containerType2]+[container2]+[unittitle]+[dateExpression]+[dateType]+[beginDate]+[endDate]+[scopecontent]+[containerId1]+[containerId2])
 
 filepath =  raw_input('Enter file path: ')
+filepath = ''
 fileName = raw_input('Enter file name: ')
+fileName = 'Coll.011.xml'
 xml = open(filepath+fileName)
 
 f=csv.writer(open(filepath+'eadFields.csv', 'wb'))
-f.writerow(['sortOrder']+['hierarchy']+['level']+['containerType1']+['container1']+['containerType2']+['container2']+['unittitle']+['dateexpression']+['datetype']+['begindate']+['enddate']+['scopecontent']+['containerId1']+['containerId2'])
+f.writerow(['sortOrder']+['hierarchy']+['level']+['containerType1']+['container1']+['containerType2']+['container2']+['unittitle']+['dateexpression']+['datetype']+['begindate']+['enddate']+['scopecontent']+['controlAccess']+['origination']+['containerId1']+['containerId2'])
 upperComponentLevels = BeautifulSoup(xml, 'lxml').find('dsc').find_all('c01')
 sortOrder = 0
 for upperComponentLevel in upperComponentLevels:
     componentLevelLabel = upperComponentLevel['level']
     unittitle = upperComponentLevel.find('did').find('unittitle').text.encode('utf-8')
     try:
-        unitdate = componentLevel.find('did').find('unitdate')
+        unitdate = upperComponentLevel.find('did').find('unitdate')
         dateExpression = unitdate.text.encode('utf-8').replace('\n','').replace('              ',' ').replace('            ',' ').encode('utf-8')
         try:
             dateType = unitdate['type']

extractMarcFields.py

@@ -1,6 +1,17 @@
 import json
 import requests
 import secrets
+import argparse
+
+parser = argparse.ArgumentParser()
+parser.add_argument('-u', '--uri', help='URI of the object to retreive. optional - if not provided, the script will ask for input')
+
+args = parser.parse_args()
+
+if args.uri:
+    uri = args.uri
+else:
+    uri = raw_input('Enter handle: ')
 
 baseURL = secrets.baseURL
 user = secrets.user
@@ -10,9 +21,8 @@
 session = auth["session"]
 headers = {'X-ArchivesSpace-Session':session, 'Content_Type':'application/json'}
 
-endpoint = '/repositories/3/resources/1126'
-
-output = requests.get(baseURL + endpoint, headers=headers).json()
-f=open('ASrecord.json', 'w')
+output = requests.get(baseURL + uri, headers=headers).json()
+uri = uri.replace('/repositories/3/','').replace('/','-')
+f=open(uri+'.json', 'w')
 results=(json.dump(output, f))
 f.close()

getSingleRecord.py

@@ -17,9 +17,11 @@
 endpoint = '/repositories/3/top_containers?all_ids=true'
 
 ids = requests.get(baseURL + endpoint, headers=headers).json()
+print len(ids)
 
 records = []
 for id in ids:
+    print id
     endpoint = '/repositories/3/top_containers/'+str(id)
     output = requests.get(baseURL + endpoint, headers=headers).json()
     records.append(output)

getTopContainers.py

@@ -0,0 +1,41 @@
+import json
+import requests
+import secrets
+import csv
+
+targetFile = raw_input('Enter file name: ')
+targetRecord = raw_input('Enter record type and id (e.g. \'accessions/2049\'): ')
+
+baseURL = secrets.baseURL
+user = secrets.user
+password = secrets.password
+
+auth = requests.post(baseURL + '/users/'+user+'/login?password='+password).json()
+session = auth["session"]
+headers = {'X-ArchivesSpace-Session':session, 'Content_Type':'application/json'}
+
+csv = csv.DictReader(open(targetFile))
+
+asRecord = requests.get(baseURL+'/repositories/3/'+targetRecord, headers=headers).json()
+print baseURL+'/repositories/3/'+targetRecord
+f=open(targetRecord+'asRecordBackup.json', 'w')
+json.dump(asRecord, f)
+instanceArray = asRecord['instances']
+
+for row in csv:
+    uri = row['uri']
+    print uri
+    top_container = {}
+    top_container['ref'] = uri
+    sub_container = {}
+    sub_container['top_container'] = top_container
+    instance = {}
+    instance['sub_container'] = sub_container
+    instance['instance_type'] = 'mixed_materials'
+    instanceArray.append(instance)
+asRecord['instances'] = instanceArray
+f2=open(targetRecord+'asRecordModified.json', 'w')
+json.dump(asRecord, f2)
+asRecord = json.dumps(asRecord)
+post = requests.post(baseURL+'/repositories/3/'+targetRecord, headers=headers, data=asRecord).json()
+print post

postContainersToRecords.py

@@ -0,0 +1,89 @@
+import json
+import requests
+import secrets
+import time
+import csv
+from datetime import datetime
+
+def addUriLink (key, valueSource):
+    uri = '/repositories/3/resources/'+row['ResourceUri']
+    value = row[valueSource]
+    print value
+    asRecord = requests.get(baseURL+uri, headers=headers).json()
+    updatedRecord = asRecord
+    if key == 'subjects':
+        subjects = updatedRecord['subjects']
+        originalSubjects = updatedRecord['subjects']
+        subject = {}
+        subject['ref'] = value
+        if subject not in subjects:
+            subjects.append(subject)
+            updatedRecord['subjects'] = subjects
+            print updatedRecord['subjects']
+            updatedRecord = json.dumps(updatedRecord)
+            print baseURL + uri
+            post = requests.post(baseURL + uri, headers=headers, data=updatedRecord).json()
+            print post
+            f.writerow([uri]+[subjects]+[post])
+        else:
+            print 'no update'
+            f.writerow([uri]+['no update']+[])
+    elif key == 'linked_agents':
+        agents = updatedRecord['linked_agents']
+        print 'originalAgents'
+        print agents
+        originalAgents = updatedRecord['linked_agents']
+        agent = {}
+        agent['terms'] = []
+        agent['ref'] = value
+        if row['tag'].startswith('1'):
+            agent['role'] = 'creator'
+        elif row['tag'].startswith('7'):
+            agent['role'] = 'creator'
+        elif row['tag'].startswith('6'):
+            agent['role'] = 'subject'
+        else:
+            'print error'
+            f.writerow([uri]+['tag error']+[])
+        if agent not in agents:
+            agents.append(agent)
+            print 'updatedAgents'
+            print agents
+            updatedRecord['linked_agents'] = agents
+            updatedRecord = json.dumps(updatedRecord)
+            print baseURL + uri
+            post = requests.post(baseURL + uri, headers=headers, data=updatedRecord).json()
+            print post
+            f.writerow([uri]+[agents]+[post])
+        else:
+            print 'no update'
+            print agent
+            f.writerow([uri]+['no update']+[])
+    else:
+        'print error'
+        f.writerow([uri]+['error']+[])
+
+startTime = time.time()
+
+baseURL = secrets.baseURL
+user = secrets.user
+password = secrets.password
+
+auth = requests.post(baseURL + '/users/'+user+'/login?password='+password).json()
+session = auth["session"]
+headers = {'X-ArchivesSpace-Session':session, 'Content_Type':'application/json'}
+
+filename = raw_input('Enter filename (including \'.csv\'): ')
+
+f=csv.writer(open(filename+'Post'+datetime.now().strftime('%Y-%m-%d %H.%M.%S')+'.csv', 'wb'))
+f.writerow(['uri']+['links']+['post'])
+
+with open(filename) as csvfile:
+    reader = csv.DictReader(csvfile)
+    for row in reader:
+        addUriLink ('linked_agents', 'agentUri')
+        #addUriLink ('subjects', 'SubjectUri')
+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)