def _process_record(self, record, type):
'''
Process a specific record
'''
# Compose a name and an ID for the record
entity_name = re.sub(r'<a [^>]*>([^<]*)</a>', '\g<1>',
record[type]).replace('\n', '')
entity_url = re.search('href="([^"]*)"', record[type]).group(1)
entity_id = entity_url.replace('/', '')
if type == 'Topic':
entity_id = entity_id.replace('t', 'topic_')
entity = Topic(entity_name, entity_id)
if type == 'Event':
entity_id = entity_id.replace('e', 'event_')
entity = Event(entity_name, entity_id)
rdf_file = '%s.rdf' % entity_id
named_graph_resource = entity.named_graph()
# Open the file in the container and get last modification date
last_modification = None
if os.path.isfile('data/' +
rdf_file): # in self.zip_container.namelist():
#data = self.zip_container.read(rdf_file)
g = Graph()
g.parse('data/' + rdf_file, format='xml')
for _, _, date in g.triples(
(named_graph_resource, DCT['modified'], None)):
last_modification = isodate.parse_datetime(date)
# If not existent or out dated, generate
generate = False
if last_modification == None:
# If not existent, generate
print '\t[GEN] %s - %s' % (entity_id, entity_name)
generate = True
else:
delta = datetime.strptime(record['Date'],
"%d %b %Y") - last_modification
if delta.days > 0:
# If updated, update
print '\t[UPD] %s - %s' % (entity_id, entity_name)
generate = True
if not generate:
print '\t[OK] %s - %s' % (entity_id, entity_name)
return
# Process a topic
if type == 'Topic':
print record
pass
# Process an event
if type == 'Event':
entity.parse(record, entity_url)
# Save the CFP
f = open('data/' + entity_id + '_cfp.txt', 'w')
f.write(entity.get_cfp_data())
f.close()
# Save the RDF data
f = open('data/' + rdf_file, 'w')
f.write(entity.get_rdf_data())
f.close()
def _process_record(self, record, type):
'''
Process a specific record
'''
# Compose a name and an ID for the record
entity_name = re.sub(r'<a [^>]*>([^<]*)</a>', '\g<1>', record[type]).replace('\n', '')
entity_url = re.search('href="([^"]*)"', record[type]).group(1)
entity_id = entity_url.replace('/', '')
if type == 'Topic':
entity_id = entity_id.replace('t', 'topic_')
entity = Topic(entity_name, entity_id)
if type == 'Event':
entity_id = entity_id.replace('e', 'event_')
entity = Event(entity_name, entity_id)
rdf_file = '%s.rdf' % entity_id
named_graph_resource = entity.named_graph()
# Open the file in the container and get last modification date
last_modification = None
if os.path.isfile('data/' + rdf_file):# in self.zip_container.namelist():
#data = self.zip_container.read(rdf_file)
g = Graph()
g.parse('data/' + rdf_file, format='xml')
for _, _, date in g.triples((named_graph_resource, DCT['modified'], None)):
last_modification = isodate.parse_datetime(date)
# If not existent or out dated, generate
generate = False
if last_modification == None:
# If not existent, generate
print '\t[GEN] %s - %s' % (entity_id, entity_name)
generate = True
else:
delta = datetime.strptime(record['Date'], "%d %b %Y") - last_modification
if delta.days > 0:
# If updated, update
print '\t[UPD] %s - %s' % (entity_id, entity_name)
generate = True
if not generate:
print '\t[OK] %s - %s' % (entity_id, entity_name)
return
# Process a topic
if type == 'Topic':
print record
pass
# Process an event
if type == 'Event':
entity.parse(record, entity_url)
# Save the CFP
f = open('data/' + entity_id + '_cfp.txt', 'w')
f.write(entity.get_cfp_data())
f.close()
# Save the RDF data
f = open('data/' + rdf_file, 'w')
f.write(entity.get_rdf_data())
f.close()
# TODO process the list of cited topics, events and organizations
#self.zip_container.writestr(rdf_file, entity.get_rdf_data())
