def build(self, dump_data=False, dump_filename=None):
proceedings = DBLPParser()
proceedings_data = proceedings.parse_proceedings(
self.DBLP_LINK, self.no_track)
if dump_data == True and dump_filename != None:
self.dump_data(proceedings_data, dump_filename + "_DBLP_data")
print("Proceedings metadata has been dumped from DBLP!")
else:
print("'dump_filename' is missing!")
papers = PaperParser()
proceedings_book = {}
for no, track in enumerate(proceedings_data):
if no == 0:
proceedings_book[track] = [proceedings_data[track]]
else:
proceedings_book[track] = []
for doi in proceedings_data[track]:
status_code, paper = papers.parse_doi(doi)
if status_code == 200:
proceedings_book[track].append(paper)
print('{}. "{}" track DONE!\n'.format(no, track))
if dump_data == True and dump_filename != None:
self.dump_data(proceedings_book, dump_filename + "_book_data")
print("Proceedings book data has been dumped!")
book_builder = ProceedingsBookBuilder(file_name=self.TITLE)
book_builder.build_pdf_book(proceedings_book)
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)
Example usage @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 """
DATABASE=config['database']
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']))