def get_naa_record(self, cleaned_data):
current_user = self.user
system_user = User.objects.get(username='******')
url = cleaned_data['url']
try:
if 'dhistory' in url:
barcode = re.search(r'naa\/items\/(\d+)', url).group(1)
else:
barcode = re.search(r'Barcode=(\d+)', url).group(1)
except AttributeError:
self._errors['url'] = self.error_class(['Not a valid NAA url'])
return cleaned_data
rs = RSItemClient()
rsseries = RSSeriesClient()
item_details = rs.get_summary(barcode)
print (item_details)
dates = item_details['contents_dates']
citation = '{}, {}'.format(
item_details['series'],
item_details['control_symbol']
)
if item_details['digitised_status'] is True:
item_url = 'http://dhistory.org/archives/naa/items/{}/'.format(barcode)
else:
item_url = 'http://www.naa.gov.au/cgi-bin/Search?O=I&Number={}'.format(barcode)
series_details = rsseries.get_summary(item_details['series'])
repository, created = Repository.objects.get_or_create(
name='National Archives of Australia',
defaults={'added_by': system_user}
)
series_type = SourceType.objects.get(label='series')
series, created = Source.objects.get_or_create(
repository_item_id=item_details['series'],
source_type=series_type,
repository=repository,
defaults={
'added_by': system_user,
'title': series_details['title'],
'url': 'http://www.naa.gov.au/cgi-bin/Search?Number={}'.format(item_details['series'])
}
)
item_type = SourceType.objects.get(label='item')
cleaned_data['collection'] = series
cleaned_data['source_type'] = item_type
cleaned_data['collection_item_id'] = item_details['control_symbol']
cleaned_data['repository_item_id'] = item_details['identifier']
cleaned_data['title'] = item_details['title']
cleaned_data['publication_date'] = dates['start_date']['date']
cleaned_data['publication_date_month'] = dates['start_date']['month']
cleaned_data['publication_date_day'] = dates['start_date']['day']
cleaned_data['publication_date_end'] = dates['end_date']['date']
cleaned_data['publication_date_end_month'] = dates['end_date']['month']
cleaned_data['publication_date_end_day'] = dates['end_date']['day']
cleaned_data['pages'] = item_details['digitised_pages']
cleaned_data['citation'] = citation
cleaned_data['repository'] = repository
cleaned_data['url'] = item_url
cleaned_data['rdf_url'] = 'http://dhistory.org/archives/naa/items/{}/#file'.format(barcode)
if 'title' in self._errors:
del self._errors['title']
if 'source_type' in self._errors:
del self._errors['source_type']
return cleaned_data
def get_naa_record(self, cleaned_data):
system_user = User.objects.get(username='******')
url = cleaned_data['url']
try:
if 'dhistory' in url:
barcode = re.search(r'naa/items/(\d+)', url).group(1)
else:
barcode = re.search(r'Barcode=(\d+)', url).group(1)
except AttributeError:
self._errors['url'] = self.error_class(['Not a valid NAA url'])
return cleaned_data
rs = RSItemClient()
rsseries = RSSeriesClient()
try:
item_details = rs.get_summary(barcode)
except URLError as e:
self._errors['url'] = self.error_class(['Error accessing the url. Error: "{}"'.format(e.reason)])
return cleaned_data
except Exception as e:
self._errors['url'] = self.error_class(['Error accessing the url. Error: "{}"'.format(e)])
return cleaned_data
dates = item_details['contents_dates']
citation = '{}, {}'.format(
item_details['series'],
item_details['control_symbol']
)
if item_details['digitised_status'] is True:
item_url = 'http://dhistory.org/archives/naa/items/{}/'.format(barcode)
else:
item_url = 'http://www.naa.gov.au/cgi-bin/Search?O=I&Number={}'.format(barcode)
series_details = rsseries.get_summary(item_details['series'])
repository, created = Repository.objects.get_or_create(
name='National Archives of Australia',
defaults={'added_by': system_user}
)
series_type = SourceType.objects.get(label='series')
series, created = Source.objects.get_or_create(
repository_item_id=item_details['series'],
source_type=series_type,
repository=repository,
defaults={
'added_by': system_user,
'title': series_details['title'],
'url': 'http://www.naa.gov.au/cgi-bin/Search?Number={}'.format(item_details['series'])
}
)
item_type = SourceType.objects.get(label='item')
cleaned_data['collection'] = series
cleaned_data['source_type'] = item_type
cleaned_data['collection_item_id'] = item_details['control_symbol']
cleaned_data['repository_item_id'] = item_details['identifier']
cleaned_data['title'] = item_details['title']
cleaned_data['publication_date'] = dates['start_date']['date']
cleaned_data['publication_date_month'] = dates['start_date']['month']
cleaned_data['publication_date_day'] = dates['start_date']['day']
cleaned_data['publication_date_end'] = dates['end_date']['date']
cleaned_data['publication_date_end_month'] = dates['end_date']['month']
cleaned_data['publication_date_end_day'] = dates['end_date']['day']
cleaned_data['pages'] = item_details['digitised_pages']
cleaned_data['citation'] = citation
cleaned_data['repository'] = repository
cleaned_data['url'] = item_url
cleaned_data['rdf_url'] = 'http://dhistory.org/archives/naa/items/{}/#file'.format(barcode)
if 'title' in self._errors:
del self._errors['title']
if 'source_type' in self._errors:
del self._errors['source_type']
return cleaned_data
def get_naa_item(barcode):
rs = RSItemClient()
result = rs.get_summary(barcode, date_format='iso')
return jsonify({'result': result})
def get_naa_item(barcode):
rs = RSItemClient()
result = rs.get_summary(barcode, date_format='iso')
return jsonify({'result': result})
