def parse_currency(currency_key, directory, name): # Type : 1 - Currency
print("Currency")
col = Mongo().create_collection("Currency", FDC.get_index_models())
with open(directory) as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')
print(currency_key)
hour = -1
fd = None
for row in csv_reader:
if len(row) < 2: # Check Data
continue
add_value = 0
if currency_key == "EURUSD":
date = DateHelper.str2date(row[0])
add_value = -1
else:
date = DateHelper.str2date(row[0]+row[1])
if hour != date.hour:
hour = date.hour
if fd is not None:
try:
col.insert(fd.get_currency())
except:
Logger().get_logger().error('Insert Error', exc_info=True)
fd = FinancialData(name, currency_key, date,
row[FDLocations.Currency_Open.value + add_value],
row[FDLocations.Currency_High.value + add_value],
row[FDLocations.Currency_Low.value + add_value],
row[FDLocations.Currency_Close.value + add_value])
else:
fd.add(row[FDLocations.Currency_High.value + add_value],
row[FDLocations.Currency_Low.value + add_value],
row[FDLocations.Currency_Close.value + add_value])
def parse_index_datetime(currency_key, directory, name, interval): # Type : 4 - Index
col = Mongo().create_collection("Index")
with open(directory) as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')
line_count = 0
print(currency_key)
hour = -1
hour_count = 0
fd = None
for row in csv_reader:
if len(row) < 2: # Check Data
continue
date = DateHelper.str2date(row[0] + row[1])
if hour != date.hour:
hour = date.hour
hour_count = 0
if fd is not None:
print(fd)
try:
col.insert(fd.get_index())
except:
Logger().get_logger().error('Insert Error', exc_info=True)
fd = FinancialData(name, currency_key, date,
row[FDLocations.IndexDateTime_Open.value],
row[FDLocations.IndexDateTime_High.value],
row[FDLocations.IndexDateTime_Low.value],
row[FDLocations.IndexDateTime_Close.value])
else:
fd.add(row[FDLocations.IndexDateTime_High.value],
row[FDLocations.IndexDateTime_Low.value],
row[FDLocations.IndexDateTime_Close.value])
hour_count += 1
line_count += 1
print(f'Processed {line_count} lines.')
def save_to_db(self):
mongo = Mongo()
try:
mongo.insert(self.row)
except Exception:
print(self.row)
Logger().get_logger().error('Insert Error', exc_info=True)
class WikiRecorder(object):
def __init__(self, collection_name="Wiki"):
self.col = Mongo().create_collection(collection_name,
WikiRecorder.get_index_models())
self.preprocessor = PreProcessing()
self.config = WikiRecorder.get_config()
self.total = 0
def collect_all(self):
name_list = self.config["Wiki"]["Corporations"]
for cor_name in name_list:
self.collect(cor_name)
def collect(self, title, page_id=None):
page = Wikipedia.get_page(title, pageid=page_id)
title = page.original_title
title_p = self.preprocessor.preprocess(title)
summary = page.summary
summary_p = self.preprocessor.preprocess(summary)
content = page.content
page_id = page.pageid
data = {
'title': title,
'title_p': title_p,
'summary': summary,
'summary_p': summary_p,
'content': content,
'page_id': page_id
}
print(data)
try:
self.col.insert(data)
except Exception as exception:
Logger().get_logger().error(type(exception).__name__,
exc_info=True)
@staticmethod
def get_index_models():
return [
IndexModel("title", name="index_title"),
IndexModel("page_id", name="index_page_id")
]
@staticmethod
def get_config():
pwd = os.path.dirname(os.path.abspath(__file__))
return json.load(open(pwd + '/config.json', 'r'))
def parse_stock(currency_key, directory, name, interval): # Type : 3 - Stock
print("Stock")
col = Mongo().create_collection("Stock", FDC.get_index_models())
with open(directory) as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')
print(currency_key)
for row in csv_reader:
if len(row) < 2: # Check Data
continue
date = DateHelper.str2date(row[0])
if interval == 60:
fd = FinancialData(name, currency_key, date,
row[FDLocations.Stock_Open.value],
row[FDLocations.Stock_High.value],
row[FDLocations.Stock_Low.value],
row[FDLocations.Stock_Close.value],
row[FDLocations.Stock_Volume.value],
row[FDLocations.Stock_Trade.value],
row[FDLocations.Stock_Avg.value])
col.insert(fd.get_stock())
else:
print("Not Handled !!!")
