-
Notifications
You must be signed in to change notification settings - Fork 0
/
data_collect.py
61 lines (42 loc) · 1.97 KB
/
data_collect.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
import yfinance as yf
from datetime import datetime, timedelta
import pandas as pd
def get_data(symbol, path):
# Fetch stock data for Barclays PLC
stock = yf.Ticker(symbol)
today = datetime.today()
startdate = today - timedelta(days=7800)
yesterday = today - timedelta(days=1)
# Get historical market data for Barclays PLC
data = stock.history(start=startdate, end=yesterday)
# Extract relevant information: Open, High, Low, Close, Volume
stock_data = data[['Open', 'High', 'Low', 'Close', 'Volume']]
# File save
stock_data.to_csv(path)
def update(start_datetime, end_datetime, symbol, file_path):
# Fetch stock data for Barclays PLC
stock = yf.Ticker(symbol)
# Get yesterday stock data
data = stock.history(start=start_datetime, end=end_datetime)
if data.empty:
pass
else:
try:
existing_data = pd.read_csv(file_path)
existing_data['Date'] = pd.to_datetime(existing_data['Date'], utc=True)
existing_data['Date'] = existing_data['Date'].dt.tz_localize(None).dt.date
latest_date_in_csv = existing_data['Date'].max()
# Filter new data that is greater than the latest date in CSV
data.reset_index(inplace=True) # Resetting index to use the 'Date' column
data['Date'] = data['Date'].dt.date # Ensuring 'Date' is in date format
new_data = data[data['Date'] > latest_date_in_csv]
if not new_data.empty:
new_data = new_data[['Date', 'Open', 'High', 'Low', 'Close', 'Volume']]
new_data.to_csv(file_path, mode='a', header=False, index=False)
print("New data appended to the CSV.")
else:
print("No new data to append.")
except FileNotFoundError:
data.to_csv(file_path, mode='w', header=True, index=False)
print("CSV file created with new data.")
get_data('BARC.L', 'test.csv')