def __init__(self, *args, **kargs):
password = kargs.pop('_mypassword')
host = kargs.pop('_myhost')
username = kargs.pop('_username')
database = kargs.pop('_database')
xml_path = kargs.pop('_xmlpath')
Application.__init__(self, *args, **kargs)
assert not hasattr(self, '_password')
assert not hasattr(self, '_host')
assert not hasattr(self, '_username')
self._db=DBLPDatabaseDriver(host=host,
username=username,
password=password,
database=database,
create_db_on_start=True)
self._db.create_table()
parser = DBLPParser(xml_path)
parser.visit()
parser.push_to_db(self._db)
@author: Weiyi Wang @contact: [email protected] @date: 11/8/2015 """ from dblp_parser import DBLPParser from rdf_driver import RDFDriver """ Level 1: Load DBLP data to RDFLib and do simple query given a publication name, list its detailed information """ print("=========LEVEL 1========") parser = DBLPParser("data/dblp_t100.xml") parser.visit() # Parse the data and store in python print("Converting to rdf data..\n") driver = RDFDriver() driver.add_documents(parser.publications) # Store the data to RDF format print("Querying the detail of publication 'On Parallel Integer Sorting'") res = driver.query_by_title('On Parallel Integer Sorting') for row in res: print row """ Level 2: turn the DBLP (XML) into RDF format, add query like given author A, provide all of her co-authors together with the corresponding publication information """ print("\n\n=========LEVEL 2========")
HOST=config['host']
USERNAME=config['username']
from dblp_dbdriver import DBLPDatabaseDriver
from dblp_parser import DBLPParser
import pprint
db = DBLPDatabaseDriver(host=HOST,password=PASSWORD,
database=DATABASE,
username=USERNAME,
create_db_on_start=False)
db.create_table()
parser = DBLPParser(config['xmlpath'])
parser.visit()
parser.push_to_db(db)
print('\n\n----------Listing Co-Authors-------------')
pprint.pprint(db.query_coauthor('Eike Best'))
print('\n\n----------Querying by title-------------')
pprint.pprint(db.query_by_name('Extended multi bottom-up tree transducers.'))
print('\n\n----------Querying by author-------------')
pprint.pprint(db.query_by_author('Eike Best'))
print('\n\n----------Querying by keywords-------------')
pprint.pprint(db.query_keywords(['multi', 'space']))
print('\n\n----------Querying by two authors-------------')
