updates

Author: ehanson8

extractMarcFields.py

@@ -0,0 +1,74 @@
+import json
+import csv
+import time
+
+def extractMarcField (tag):
+    dataFields = record['record']['datafield']
+    tagData = ''
+    for dataField in dataFields:
+        if dataField['tag'] == '910':
+            bibnum = dataField['subfield']
+            if isinstance(bibnum, basestring):
+                bibnum = bibnum
+            else:
+                bibnum = bibnum[0]
+    for dataField in dataFields:
+        if dataField['tag'] == tag:
+            value = dataField['subfield']
+            indicator1 = dataField['ind1']
+            indicator2 = dataField['ind2']
+            if isinstance(value, basestring):
+                tagData = value
+            else:
+                for subfield in value:
+                    tagData = tagData + subfield + ' '
+            f.writerow([bibnum]+[tag]+[indicator1]+[indicator2]+[tagData.encode('utf-8')])
+
+def extractMarcFieldStartsWith (digit):
+    dataFields = record['record']['datafield']
+
+    for dataField in dataFields:
+        if dataField['tag'] == '910':
+            bibnum = dataField['subfield']
+            if isinstance(bibnum, basestring):
+                bibnum = bibnum
+            else:
+                bibnum = bibnum[0]
+
+    for dataField in dataFields:
+        tagData = ''
+        if dataField['tag'].startswith(digit):
+            tagNumber = dataField['tag']
+            value = dataField['subfield']
+            indicator1 = dataField['ind1']
+            indicator2 = dataField['ind2']
+            if isinstance(value, basestring):
+                tagData = value
+            else:
+                for subfield in value:
+                    if isinstance(subfield, basestring):
+                        tagData = tagData + subfield + '--'
+            f.writerow([bibnum]+[tagNumber]+[indicator1]+[indicator2]+[tagData.encode('utf-8')])
+
+startTime = time.time()
+file = 'C:/Users/ehanson8/Downloads/combined.json'
+
+records = json.load(open(file))
+
+f=csv.writer(open('marcFields.csv', 'wb'))
+f.writerow(['bibnum']+['tag']+['indicator1']+['indicator2']+['value'])
+
+for record in records:
+    extractMarcFieldStartsWith('1')
+    extractMarcField('245')
+    extractMarcField('520')
+    extractMarcField('540')
+    extractMarcField('545')
+    extractMarcField('561')
+    extractMarcFieldStartsWith('6')
+    extractMarcFieldStartsWith('7')
+
+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)

getPropertiesFromResources.py

@@ -0,0 +1,96 @@
+import json
+import requests
+import secrets
+import time
+import csv
+
+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'}
+
+endpoint = '/repositories/3/resources?all_ids=true'
+
+ids = requests.get(baseURL + endpoint, headers=headers).json()
+
+f=csv.writer(open('resourceProperties.csv', 'wb'))
+f.writerow(['title']+['uri']+['bibnum']+['type']+['value'])
+
+total = len(ids)
+for id in ids:
+    print 'id', id, total, 'records remaining'
+    total = total - 1
+    endpoint = '/repositories/3/resources/'+str(id)
+    output = requests.get(baseURL + endpoint, headers=headers).json()
+
+    title = output['title'].encode('utf-8')
+    uri = output['uri']
+    try:
+        bibnum = output['user_defined']['real_1']
+    except:
+        bibnum = ''
+    try:
+        agents = output['linked_agents']
+        for agent in agents:
+            agentUri = agent['ref']
+            agentOutput = requests.get(baseURL + agentUri, headers=headers).json()
+            agentName = agentOutput['title']
+            f.writerow([title]+[uri]+[bibnum]+['name']+[agentName])
+    except:
+        pass
+    try:
+        subjects = output['subjects']
+        for subject in subjects:
+            subjectUri = subject['ref']
+            subjectOutput = requests.get(baseURL + subjectUri, headers=headers).json()
+            subjectName = subjectOutput['title']
+            f.writerow([title]+[uri]+[bibnum]+['subject']+[subjectName])
+    except:
+        pass
+    for note in output['notes']:
+        abstract = ''
+        scopecontent = ''
+        acqinfo = ''
+        custodhist = ''
+        try:
+            if note['type'] == 'abstract':
+                abstract = note['content'][0].encode('utf-8')
+
+                f.writerow([title]+[uri]+[bibnum]+['abstract']+[abstract])
+            if note['type'] == 'scopecontent':
+                scopecontentSubnotes = note['subnotes']
+                for subnote in scopecontentSubnotes:
+                    scopecontent = scopecontent + subnote['content'].encode('utf-8') + ' '
+                f.writerow([title]+[uri]+[bibnum]+['scopecontent']+[scopecontent])
+            if note['type'] == 'acqinfo':
+                acqinfoSubnotes = note['subnotes']
+                for subnote in acqinfoSubnotes:
+                    acqinfo = acqinfo + subnote['content'].encode('utf-8') + ' '
+                f.writerow([title]+[uri]+[bibnum]+['acqinfo']+[acqinfo])
+            if note['type'] == 'custodhist':
+                custodhistSubnotes = note['subnotes']
+                for subnote in custodhistSubnotes:
+                    custodhist = custodhist + subnote['content'].encode('utf-8') + ' '
+                f.writerow([title]+[uri]+[bibnum]+['custodhist']+[custodhist])
+            if note['type'] == 'bioghist':
+                custodhistSubnotes = note['subnotes']
+                for subnote in custodhistSubnotes:
+                    custodhist = custodhist + subnote['content'].encode('utf-8') + ' '
+                f.writerow([title]+[uri]+[bibnum]+['bioghist']+[custodhist])
+            if note['type'] == 'accessrestrict':
+                custodhistSubnotes = note['subnotes']
+                for subnote in custodhistSubnotes:
+                    custodhist = custodhist + subnote['content'].encode('utf-8') + ' '
+                f.writerow([title]+[uri]+[bibnum]+['accessrestrict']+[custodhist])
+        except:
+            f.writerow([title]+[uri]+[bibnum]+['']+[custodhist])
+
+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)