data with info.py

def get_etf_data(symbols, period='2y'):
    """Download ETF data with comprehensive error handling"""
    data = {}
    successful_downloads = 0
    # print(f"📊 Downloading data for {len(symbols)} ETFs...")
    for i, symbol in enumerate(symbols):
        try:
            # print(f"  • Fetching {symbol}... ({i+1}/{len(symbols)})", end="")
            ticker = yf.Ticker(symbol)
            # Get historical data
            hist = ticker.history(period=period)
            if not hist.empty:
                # Get info with error handling
                try:
                    info = ticker.info
                except:
                    info = {}
                data[symbol] = {
                    'price_data': hist,
                    'info': info
                }
                successful_downloads += 1
                # print(" ✅")
            else:
                print(" ❌ No data")
        except Exception as e:
            print(f" ❌ Error: {str(e)[:50]}...")
            continue

    # print(f"✅ Successfully downloaded {successful_downloads}/{len(symbols)} ETFs\n")
    return data

get_data.py

import yfinance as yf
import pandas as pd
from datetime import datetime, timedelta
import logging
 
def get_data(symbols, start_date, end_date=None, frequency='daily'):
 
    """
    Fetches historical data for one or more ETFs using yfinance.
 
    Args:
        symbols (str or list of str): Ticker symbol(s) of the ETF(s).
        start (str): Start date for data retrieval (YYYY-MM-DD).
        end (str, optional): End date for data retrieval (YYYY-MM-DD). 
                              Defaults to yesterday's date if None.
        frequency (str, optional): Data frequency ('daily', 'weekly', 'monthly').
                                  Defaults to 'daily'.
 
    Returns:
        data_df: A MultiIndex DataFrame where each column is a DataFrame containing 
                            the historical data for a specific symbol. The index of
                            the result DataFrame starts with the latest_start_date.
        data_dict: A dictionary where keys are ETF symbols and values are DataFrames.
                            
                            Each DataFrame in each column is indexed by date, 
                            and contains the columns: 
                            ['Close', 'High', 'Low','Open', 'Volume']
                            
                            Note: 'Close' = 'Adj Close' if auto_adjust=True
        
    Raises:
        ValueError: If start date is >= end date.
        Exception: If an error occurs during data retrieval.
        
    """
    try:
        if frequency == 'daily':
            interval = "1d"
        elif frequency == 'weekly':
            interval = "1wk"
        elif frequency == "monthly":
            interval = "1mo"
 
        data = yf.download(symbols, start=start_date, end=end_date, interval=interval, progress=False, auto_adjust=True)
 
        # drop any columns with all NaNs
        data_df  = data.dropna(axis=1, how='all').dropna()
        # junk ETFs are droppped
        symbols = list(data_df['Close'].columns)
 
        # data is a multiindex dataframe where
        # start_date = latest_start_date, due to dropna() 
        
        # # Dictionary of frames
        data_dict = {s: data_df.xs(s, axis=1, level=1) for s in symbols}
        
    except yf.exceptions.YFTickerMissingError as yfe:
        logging.error(f"Yahoo Finance error for {sym}: {yfe}")
        pass
 
    data_df.columns = data_df.columns.swaplevel(0,1)
 
    return data_df, data_dict
 
if __name__ == '__main__':
    # Example usage:
    logging.basicConfig(level=logging.ERROR)
 
    start_date = '1990-01-01'
    end_date = '2023-03-31'  # or None for yesterday's date
 
    # Single ETF test
    symbols_single = 'SPY'
    data_df, data_dict = get_data(symbols_single, start_date, end_date, frequency='daily')
    data_single = data_df
    if not data_single.empty:
       print("Data for single ETF:\n", data_single.head(2))
       print(f"columns: {data_single.columns}")
       print(f"index: {data_single.index}")
    else:
        print("No data for single ETF")
 
    print('\n===================================\n\n')
 
    # Multiple ETFs test:
    symbols_multiple = ['SPY', 'QQQ', 'BND']
    data_multiple, data_dict = get_data(symbols_multiple, start_date, end_date, frequency='weekly')
    if not data_multiple.empty:
       print("\nData for multiple ETFs:\n", data_multiple)
       print(f"columns: {data_multiple.columns}")
       print(f"index: {data_multiple.index}")
    else:
       print("No data for multiple ETFs")
    # Test with default end date (yesterday)
 
    print('\n===================================\n\n')
 
    data_yesterday, data_dict = get_data(symbols_multiple, start_date, end_date, frequency='daily')
    if not data_yesterday.empty:
        print("\nData with default end date:\n", data_yesterday)
        print(f"columns: {data_yesterday.columns}")
        print(f"index: {data_yesterday.index}")
    else:
        print("No data with default end date")

yahoo data.py

from __future__ import print_function

import pandas as pd
import yfinance as yf

# tickers = ['VCVSX','VWINX','VWEHX','VGHCX','VFIIX','VWAHX','FGOVX','FFXSX']
tickers = ['BND','VOO','VEA','VWO','VB','IWN','GOVT','BIL']

start = '2000-01-01'
end = '2016-12-31'

df = yf.download(tickers, start, end).dropna()

df[:3]

yfinance_data.py

import pandas as pd
import yfinance as yf

# DAILY
QQQ_d_df = yf.download("QQQ", progress=False, auto_adjust=True)
# WEEKLY
QQQ_w_df = QQQ_d_df.resample("W").first()
# MONTHLY
QQQ_m_df = QQQ_d_df.resample("ME").last()
# QUARTERLY
QQQ_q_df = QQQ_d_df.resample("QE").last()
# YEARLY
QQQ_y_df = QQQ_d_df.resample("YE").last()