deepblue_deposit.py

import csv
from dappr.dappr import DAPPr
from dappr.config import prod
from datetime import datetime
import os
import requests

accession_id = 170864 # 168861

csv_metadata = []
with open('170864_bhl_inventory_with_archival_object-with_mivideo_ids.csv', mode='r') as f:
    reader = csv.DictReader(f)
    for row in reader:  
        metadatum = {}
        metadatum['barcode'] = row['barcode']
        metadatum['archival_object_id'] = row['archival_object_id']
        # metadatum['archival_object_id'] = row['archival_object_link'].split('archival_object_')[-1]
        metadatum['kaltura_ids'] = row['mivideo_ids']
        metadatum['accessrestrict'] = row['access_restrictions']
        csv_metadata.append(metadatum)
        
archivesspace = {
    'base_url': '',
    'user': '',
    'password': '',
    'repository': 2
}

# logging to archivesspace and dspace
url = archivesspace['base_url'] + '/users/' + archivesspace['user'] + '/login?password=' + archivesspace['password']
response = requests.post(url)
token = response.json().get('session') 

deepblue = DAPPr(
    prod.get('base_url'),
    prod.get('email'),
    prod.get('password'), 
)  
        
print "deepblue deposit"
print "================"
for name in os.listdir(r"Q:\prod\aip_to_item-queue\Ready\\" + str(accession_id)): 
    
    aip_name = name
    aip_uuid = name[-36:]
    aip_barcode = name[0:14]
    
    print "\n  * depositing " + aip_name
    
    archival_object_id = [metadatum['archival_object_id'] for metadatum in csv_metadata if metadatum['barcode'] == aip_barcode][0]
    kaltura_ids = [metadatum['kaltura_ids'] for metadatum in csv_metadata if metadatum['barcode'] == aip_barcode][0]
    accessrestrict = [metadatum['accessrestrict'] for metadatum in csv_metadata if metadatum['barcode'] == aip_barcode][0]

    # getting metadata from archivesspace
    url = archivesspace['base_url'] + '/repositories/' + str(archivesspace['repository']) + '/archival_objects/' + str(archival_object_id)
    headers = {'X-ArchivesSpace-Session': token}
    response = requests.get(url, headers=headers)
    
    archival_object = response.json()
    
    print "\nmetadata..."
    title = archival_object['display_string']
    print "dc.title: " + title
   
    # optional
    description_abstract = ''
    for note in archival_object['notes']:
        if note['type'] == 'odd':
            description_abstract = note['subnotes'][0]['content']
    
    contributor_author = ''
    url = archivesspace['base_url'] + archival_object['resource']['ref']
    response = requests.get(url, headers=headers)
    resource = response.json()
    for linked_agent in resource['linked_agents'] :
        if linked_agent['role'] == 'creator':
            url = archivesspace['base_url'] + linked_agent['ref']
            response = requests.get(url, headers=headers)
            creator = response.json()
            contributor_author = creator['title']
    print "dc.contributor.author: " + contributor_author
    
    date_issued = str(datetime.now().year)
    print "dc.date.issued: " + date_issued
    
    rights_copyright = 'This content may be under copyright. Researchers are responsible for determining the appropriate use or reuse of materials. Please consult the collection finding aid or catalog record for more information.'
    print "dc.rights.copyright: " + rights_copyright
    
    relation_ispartofseries = []
    while archival_object.get('parent'):
        url = archivesspace['base_url'] + archival_object['parent']['ref']
        response = requests.get(url, headers=headers)
        parent_archival_object = response.json()
        relation_ispartofseries.append(parent_archival_object['display_string'].replace('<genreform normal="Photographs">', '').replace('</genreform>', '').replace('<title render="italic">', '').replace('</title>', ''))
        archival_object = parent_archival_object
    relation_ispartofseries.reverse()
    relation_ispartofseries = ' - '.join(relation_ispartofseries)
    print "dc.relation.ispartofseries: " + relation_ispartofseries
    
    # optional
    rights_access = ''
    if accessrestrict == 'reading room' and kaltura_ids:
        rights_access = 'Streaming Only: This recording may be protected by copyright law. Access to this material is restricted to the reading room of the Bentley Historical Library.'
    elif accessrestrict == 'reading room':
        rights_access = 'Access to this material is restricted to the reading room of the Bentley Historical Library.'
    print 'dc.rights.access: ' + rights_access
    
    identifier_videostreams = []
    if kaltura_ids:
        kaltura_ids = kaltura_ids.split('; ')
        player = 1455309001
        for kaltura_id in kaltura_ids:
            identifier_videostream = "https://cdnapisec.kaltura.com/p/1758271/sp/175827100/embedIframeJs/uiconf_id/29300931/partner_id/1758271?autoembed=true&entry_id=" + kaltura_id + "&playerId=kaltura_player_" + str(player) + "&cache_st=1455309475&width=400&height=330&flashvars[streamerType]=auto"
            identifier_videostreams.append(identifier_videostream)
            player += 1
            print 'dc.identifier.videostream: ' + identifier_videostream
    
    # depositing
    collection_id = 206 # CHANGE
    
    item = {'name': title}
    
    print '\nposting collection item...'
    item = deepblue.post_collection_item(int(collection_id), item)
    item_id = item['id']
    item_handle = item['handle']
    
    metadata = [
        {'key': 'dc.title', 'value': title},
        {'key': 'dc.contributor.author', 'value': contributor_author},
        {'key': 'dc.date.issued', 'value': date_issued},
        {'key': 'dc.rights.copyright', 'value': rights_copyright},
        {'key': 'dc.relation.ispartofseries', 'value': relation_ispartofseries}
    ]
    if description_abstract:
        metadata.append({'key': 'dc.description.abstract', 'value': description_abstract})
    if rights_access:
        metadata.append({'key': 'dc.rights.access', 'value': rights_access})
    if identifier_videostreams:
        for identifier_videostream in identifier_videostreams:
            metadata.append({'key': 'dc.identifier.videostream', 'value': identifier_videostream})
    
    print "updating item metadata..."
    deepblue.put_item_metadata(int(item_id), metadata)
    
    for bitstream in os.listdir(os.path.join(r"Q:\prod\aip_to_item-queue\Ready\\" + str(accession_id), name)):
        if bitstream.startswith('objects'):
        
            print 'posting item "objects" bitstream...'
            bitstream = deepblue.post_item_bitstream(int(item_id), os.path.join(r"Q:\prod\aip_to_item-queue\Ready\\" + str(accession_id), name, bitstream))
            
            bitstream_id = bitstream['id']
                        
            bitstream['name'] = 'objects.zip'
            if accessrestrict == 'reading room':
                bitstream['description'] = 'Archival materials. Access restricted to Bentley staff.'
            
            print 'updating item "objects" bitstream...'
            deepblue.put_bitstream(int(bitstream_id), bitstream)
            
            print 'updating item "objects" bitstream policy if necessary...'
            if accessrestrict == 'reading room':
                deepblue.put_bitstream_policy(int(bitstream_id), [{"action": "READ", "rpType": "TYPE_CUSTOM", "groupId": 560}])
            
        elif bitstream.startswith('metadata'):
        
            print 'posting item "metadata" bitstream...'
            bitstream = deepblue.post_item_bitstream(int(item_id), os.path.join(r"Q:\prod\aip_to_item-queue\Ready\\" + str(accession_id), name, bitstream))
            
            bitstream_id = bitstream['id']
            
            bitstream['name'] = 'metadata.zip'
            bitstream['description'] = 'Administrative information. Access restricted to Bentley staff.'
            
            print 'updating item "metadata" bitstream...'
            deepblue.put_bitstream(int(bitstream_id), bitstream)
            
            print 'updating item "metadata" bitsream policy...'
            deepblue.put_bitstream_policy(int(bitstream_id), [{"action": "READ", "rpType": "TYPE_CUSTOM", "groupId": 560}])
    
    print 'posting item license...'
    deepblue.post_item_license(int(item_id))
    
    # updating archivespace
    url = archivesspace['base_url'] + '/repositories/' + str(archivesspace['repository']) + '/digital_objects'
    headers = {'X-ArchivesSpace-Session': token, 'Content-Type': 'application/json'}
    
    body = {
    "title": title,
    "publish": True,
    "digital_object_id": aip_barcode,
    "jsonmodel_type": "digital_object",
    "file_versions": [
        {
            "file_uri": 'http://hdl.handle.net/' + item_handle,
            'xlink_show_attribute': 'new',
            'xlink_actuate_attribute': 'onRequest'
        }
        ]
    }
    if kaltura_ids:
        body['publish'] = False
    
    print '\nposting digital object...'
    response = requests.post(url, headers=headers, json=body)
    
    digital_object = response.json()
    digital_object_uri = digital_object["uri"]
    
    url = archivesspace['base_url'] + '/repositories/' + str(archivesspace['repository']) + '/archival_objects/' + str(archival_object_id)
    response = requests.get(url, headers=headers)
    archival_object = response.json()
    
    instance = {
            "instance_type": "digital_object",
            "jsonmodel_type": "instance",
            "is_representative": False,
            "digital_object": {
                "ref": digital_object_uri
            }
        }
    archival_object['instances'].append(instance)
    
    print 'appending digital object to archival object...'
    response = requests.post(url, headers=headers, json=archival_object)