def get_object(self, object_number):
log.info('Getting object: %s', object_number)
resp = self.api_call('collection/%s' % object_number)
if not resp['artObject']:
raise NotFound
return 'application/json', json.dumps(resp['artObject'])
def get_all_results(self):
"""Retrieves all available items in a result set.
:returns: a generator that yields a tuple for each record,
a tuple consists of the content-type and the content as a string.
"""
# Perform an initial call to get the total number of results in
# the result set
resp = self.opensearch_call({'q': self.query, 'count': 0})
total_results = int(resp.find('.//channel/opensearch:totalResults',
namespaces=resp.nsmap).text)
start_index = 1
page_delay = self.source_definition.get('opensearch_delay', 1)
while start_index <= total_results:
sleep(page_delay)
log.info('Getting results for %s from %s' % (
self.query, start_index,))
try:
resp = self.opensearch_call({
'q': self.query,
'count': self.per_page_count,
'startIndex': start_index
})
except requests.exceptions.HTTPError as e:
log.exception('Error getting results for %s from %s' % (
self.query, start_index,))
start_index += self.per_page_count
continue
except etree.XMLSyntaxError as e:
log.exception('Error parsing XML for %s from %s' % (
self.query, start_index,))
start_index += self.per_page_count
continue
# Create a copy of the tree without any items
itemless_tree = deepcopy(resp)
for item in itemless_tree.xpath('.//channel/item'):
item.getparent().remove(item)
# Construct a tree that only includes the item we are iterating over
for item in resp.xpath('.//channel/item'):
single_item_tree = deepcopy(itemless_tree)
single_item_tree.find('./channel').append(item)
yield 'application/xml', etree.tostring(single_item_tree)
start_index += self.per_page_count
def get_collection_objects(self):
# Perform an initial call to get the total number of results
resp = self.api_call('collection/', params={'p': 0, 'ps': 1})
total_items = resp['count']
# Calculate the total number of pages that are available
total_pages = int(ceil(total_items / float(self.items_per_page)))
log.info('Total collection items to fetch %s (%s pages)', total_items, total_pages)
for p in xrange(0, total_pages):
log.info('Getting collection items page %s of %s', p, total_pages)
resp = self.api_call('collection/', params={
'p': p,
'ps': self.items_per_page
})
for item in resp['artObjects']:
yield item
def get_collection_objects(self):
# Perform an initial call to get the total number of results
resp = self.api_call('collection/', params={'p': 0, 'ps': 1})
total_items = resp['count']
# Calculate the total number of pages that are available
total_pages = int(ceil(total_items / float(self.items_per_page)))
log.info('Total collection items to fetch %s (%s pages)', total_items,
total_pages)
for p in xrange(0, total_pages):
log.info('Getting collection items page %s of %s', p, total_pages)
resp = self.api_call('collection/',
params={
'p': p,
'ps': self.items_per_page
})
for item in resp['artObjects']:
yield item
def get_object(self, item):
log.info('Getting object: %s', item['id'].split('/')[-1])
return 'application/json', json.dumps(item)