def _process_event(self, record):
# Get the event id, its name and its last modification date
event_name = re.sub(r'<a [^>]*>([^<]*)</a>', '\g<1>', record['Event'], flags=re.IGNORECASE).replace('\n', '')
event_id = re.search('href="([^"]*)"', record['Event']).group(1)[1:-1]
event_last_update_date = datetime.strptime(record['Date'], "%d %b %Y")
event = Event(event_id)
# Get the last modification date from the end point
server_version_date = self.triple_store.get_last_version_date(event)
# Check the status of the event in the triple store
if server_version_date == None or (event_last_update_date - server_version_date).days > 0:
# The event is not in the triple store or needs to be updated
print '\t[UPD] %s - %s' % (event_id, event_name)
# Add the topics not already existing
for t in event.get_topics():
topic = Topic(t)
if self.triple_store.get_last_version_date(topic) == None:
try:
print '\t\t[UPD-TOPIC] %s' % t
topic.load_data()
self.triple_store.save_rdf_data(topic)
except:
# It's ok if we miss one
pass
# Update the data about all the persons concerned
for p in event.get_persons():
try:
print '\t\t[UPD-PERSON] %s' % p
person = Person(p)
person.load_data()
self.triple_store.save_rdf_data(person)
except:
# It's ok if we miss one
pass
# Save the RDF data of the event
event.load_data()
self.triple_store.save_rdf_data(event)
# Save the CFP from the call
file = open(self.data_directory + '/' + event.get_resource_name() + '_cfp.txt', 'w')
file.write(event.get_cfp_data())
file.close()
else:
# The server version is up to date
print '\t[OK] %s - %s' % (event_id, event_name)
'''
Created on 30 Jun 2011
@author: cgueret
'''
import re
from objects.persons import Person
from objects.events import Event
if __name__ == '__main__':
dates = {
'August 24-26, 2011', 'October 31-November 3, 2011',
'September 5, 2011'
}
for d in dates:
parts = re.search(
'(?P<begin>[^-,]*)(-(?P<end>[^,]*))?, (?P<year>\d{4})',
d).groupdict()
print parts
print Person('p/alistair')
print Person('p/cui_tao')
#print Person('p/alistair_<a href')
event = Event('e/16470')
event.load_data()
print event.get_rdf_data()
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()
'''
Created on 30 Jun 2011
@author: cgueret
'''
import re
from objects.persons import Person
from objects.events import Event
if __name__ == '__main__':
dates = {'August 24-26, 2011','October 31-November 3, 2011', 'September 5, 2011'}
for d in dates:
parts = re.search('(?P<begin>[^-,]*)(-(?P<end>[^,]*))?, (?P<year>\d{4})', d).groupdict()
print parts
print Person('p/alistair')
print Person('p/cui_tao')
#print Person('p/alistair_<a href')
event = Event('e/16470')
event.load_data()
print event.get_rdf_data()
