Skip to content

Commit 5ebc405

Browse files
ehanson8ehanson8
authored
Merge pull request #11 from mjanowiecki/master
ASpace & readme updates
2 parents db10e49 + acebb2c commit 5ebc405

File tree

3 files changed

+181
-6
lines changed

3 files changed

+181
-6
lines changed

‎README.md‎

Lines changed: 5 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,7 @@ All of these scripts require a secrets.py file in the same directory that must c
77
baseURL='[ArchivesSpace API URL]'
88
user='[user name]'
99
password='[password]'
10+
repository='[repository]'
1011

1112
This secrets.py file will be ignored according to the repository's .gitignore file so that ArchivesSpace login details will not be inadvertently exposed through GitHub.
1213

@@ -39,7 +40,7 @@ Retrieves a count of archival objects associated with a particular resource. Upo
3940
Extracts all of the archival objects associated with a particular resource. Upon running the script, you will be prompted enter the resource ID (just the number, not the full URI).
4041

4142
#### [getArchivalObjectRefIdsForResource.py](/getArchivalObjectRefIdsForResource.py)
42-
Extracts the title, URI, ref_id, and date expression for all archival objects associated with a particular resource. Upon running the script, you will be prompted enter the resource ID (just the number, not the full URI).
43+
Extracts the title, URI, ref_id, date expression, and level for all archival objects associated with a particular resource. Upon running the script, you will be prompted enter the resource ID (just the number, not the full URI).
4344

4445
#### [getArrayPropertiesFromAgentsPeopleCSV.py](/getArrayPropertiesFromAgentsPeopleCSV.py)
4546
Retrieves specific properties, including proprerties that have arrays as values, from the JSON of ArchivesSpace agent_people records. In this example, the 'dates_of existence' property contains an array that must be iterated over. This requires a second level of iteration with 'for j in range (...)' on line 20, which is in addition to the iteration function 'for i in range (...)' on line 19, which was also found in the getPropertiesFromAgentsPeopleCSV.py script. As with the previous script, it also writes the properties' values into a CSV file which is specified in variable 'f' on line 17.
@@ -107,6 +108,9 @@ Prints the URIs to a CSV file of all resources in a repository without a bib num
107108
#### [searchForUnassociatedContainers.py](/searchForUnassociatedContainers.py)
108109
Prints the URIs to a CSV file of all top containers that are not associated with a resource or archival object.
109110

111+
#### [transferAoDatesToDos.py](/transferAoDatesToDos.py)
112+
Transfers the date from an archival object to any attached digital objects.
113+
110114
#### [unpublishArchivalObjectsByResource.py](/unpublishArchivalObjectsByResource.py)
111115
Unpublishes all archival objects associated with the specified resource. Upon running the script, you will be prompted enter the resource ID (just the number, not the full URI).
112116

‎getArchivalObjectRefIdsForResource.py‎

Lines changed: 10 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@ def findKey(d, key):
3737
resourceID= raw_input('Enter resource ID: ')
3838

3939
f=csv.writer(open('archivalObjectRefIdForResource.csv', 'wb'))
40-
f.writerow(['title']+['uri']+['ref_id']+['date'])
40+
f.writerow(['title']+['uri']+['ref_id']+['dateExpression']+['dataBegin']+['level'])
4141

4242
endpoint = '/repositories/'+repository+'/resources/'+resourceID+'/tree'
4343

@@ -51,16 +51,21 @@ def findKey(d, key):
5151
print 'downloading aos'
5252
for archivalObject in archivalObjects:
5353
output = requests.get(baseURL + archivalObject, headers=headers).json()
54-
print output
54+
print json.dumps(output)
5555
title = output['title']
5656
uri = output['uri']
5757
ref_id = output['ref_id']
58+
level = output['level']
5859
for date in output['dates']:
5960
try:
60-
date = date['expression']
61+
dateExpression = date['expression']
6162
except:
62-
date = ''
63-
f.writerow([title]+[uri]+[ref_id]+[date])
63+
dateExpression = ''
64+
try:
65+
dateBegin = date['begin']
66+
except:
67+
dateBegin = ''
68+
f.writerow([title]+[uri]+[ref_id]+[dateExpression]+[dateBegin]+[level])
6469

6570
elapsedTime = time.time() - startTime
6671
m, s = divmod(elapsedTime, 60)

‎transferAoDatesToDos.py‎

Lines changed: 166 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,166 @@
1+
import json
2+
import requests
3+
import secrets
4+
import time
5+
import csv
6+
7+
secretsVersion = raw_input('To edit production server, enter the name of the secrets file: ')
8+
if secretsVersion != '':
9+
try:
10+
secrets = __import__(secretsVersion)
11+
print 'Editing Production'
12+
except ImportError:
13+
print 'Editing Development'
14+
else:
15+
print 'Editing Development'
16+
17+
startTime = time.time()
18+
19+
baseURL = secrets.baseURL
20+
user = secrets.user
21+
password = secrets.password
22+
repository = secrets.repository
23+
24+
auth = requests.post(baseURL + '/users/'+user+'/login?password='+password).json()
25+
session = auth["session"]
26+
headers = {'X-ArchivesSpace-Session':session, 'Content_Type':'application/json'}
27+
print 'authenticated'
28+
29+
endpoint = '/repositories/'+repository+'/archival_objects?all_ids=true'
30+
31+
ids = requests.get(baseURL + endpoint, headers=headers).json()
32+
ids.reverse()
33+
print len(ids)
34+
35+
## Generates a text file of AOs with DOs. Takes 2+ hours to generate so this code block is separate so the main portion of the script can be run more quickly.
36+
37+
# f=csv.writer(open('archivalObjectsWithDigitalObjects.csv', 'wb'))
38+
# f.writerow(['uri'])
39+
# doAos = []
40+
#
41+
# for id in ids:
42+
# endpoint = '/repositories/'+repository+'/archival_objects/'+str(id)
43+
# output = requests.get(baseURL + endpoint, headers=headers).json()
44+
# try:
45+
# dates = output['dates']
46+
# except:
47+
# dates = ''
48+
# uri = output['uri']
49+
# instances = output['instances']
50+
# for instance in instances:
51+
# if instance['instance_type'] == 'digital_object':
52+
# doUri = instance['digital_object']['ref']
53+
# print doUri
54+
# f.writerow([uri])
55+
# doAos.append(uri)
56+
#
57+
# f2=open('archivalObjectsWithDigitalObjectsList.txt', 'wb')
58+
# f2.write(json.dumps(doAos))
59+
60+
f=csv.writer(open('DigitalObjectsDatesEdited.csv', 'wb'))
61+
f.writerow(['doUri']+['oldBegin']+['oldEnd']+['oldExpression']+['oldLabel']+['aoUri']+['newBegin']+['newEnd']+['newExpression']+['newLabel']+['post'])
62+
63+
doAos = json.load(open('archivalObjectsWithDigitalObjectsList.txt', 'rb'))
64+
for doAo in doAos:
65+
print doAo
66+
aoBegin = ''
67+
aoExpression = ''
68+
aoLabel = ''
69+
aoEnd = ''
70+
doBegin = ''
71+
doExpression = ''
72+
doLabel = ''
73+
doEnd = ''
74+
aoOutput = requests.get(baseURL + doAo, headers=headers).json()
75+
try:
76+
aoDates = aoOutput['dates']
77+
for aoDate in aoDates:
78+
try:
79+
aoBegin = aoDate['begin']
80+
except:
81+
aoBegin = ''
82+
try:
83+
aoEnd = aoDate['end']
84+
except:
85+
aoEnd = ''
86+
try:
87+
aoExpression = aoDate['expression']
88+
except:
89+
aoExpression = ''
90+
try:
91+
aoLabel = aoDate['label']
92+
except:
93+
aoLabel = ''
94+
except:
95+
aoBegin = ''
96+
aoExpression = ''
97+
aoLabel = ''
98+
aoEnd = ''
99+
try:
100+
instances = aoOutput['instances']
101+
except:
102+
continue
103+
for instance in instances:
104+
if instance['instance_type'] == 'digital_object':
105+
if aoBegin+aoExpression+aoLabel != '':
106+
doUri = instance['digital_object']['ref']
107+
doOutput = requests.get(baseURL + str(doUri), headers=headers).json()
108+
print 'moving date from AO to DO'
109+
doDates = doOutput['dates']
110+
if doDates == []:
111+
print 'no date', doDates
112+
doBegin = ''
113+
doExpression = ''
114+
doLabel = ''
115+
doEnd = ''
116+
doDates = []
117+
doDate = {}
118+
doDate['begin'] = aoBegin
119+
doDate['expression'] = aoExpression
120+
doDate['label'] = aoLabel
121+
doDate['date_type'] = 'single'
122+
if aoEnd != '':
123+
doDate['end'] = aoEnd
124+
doDate['date_type'] = 'range'
125+
doDates.append(doDate)
126+
doOutput['dates'] = doDates
127+
output = json.dumps(doOutput)
128+
doPost = requests.post(baseURL + doUri, headers=headers, data=output).json()
129+
print doPost
130+
else:
131+
print 'existing date', doDates
132+
for doDate in doDates:
133+
try:
134+
doBegin = doDate['begin']
135+
except:
136+
doBegin = ''
137+
try:
138+
doEnd = doDate['end']
139+
except:
140+
doEnd = ''
141+
try:
142+
doExpression = doDate['expression']
143+
except:
144+
doExpression = ''
145+
try:
146+
doLabel = doDate['label']
147+
except:
148+
doLabel = ''
149+
if aoBegin != '':
150+
doDate['begin'] = aoBegin
151+
if aoExpression != '':
152+
doDate['expression'] = aoExpression
153+
if aoLabel != '':
154+
doDate['label'] = aoLabel
155+
if aoEnd != '':
156+
doDate['end'] = aoEnd
157+
doOutput['dates'] = doDates
158+
output = json.dumps(doOutput)
159+
doPost = requests.post(baseURL + doUri, headers=headers, data=output).json()
160+
print doPost
161+
f.writerow([doUri]+[doBegin]+[doEnd]+[doExpression]+[doLabel]+[doAo]+[aoBegin]+[aoEnd]+[aoExpression]+[aoLabel]+[doPost])
162+
163+
elapsedTime = time.time() - startTime
164+
m, s = divmod(elapsedTime, 60)
165+
h, m = divmod(m, 60)
166+
print 'Total script run time: ', '%d:%02d:%02d' % (h, m, s)

0 commit comments

Comments
 (0)