import pandas as pd
# remember to 'pip install wikipedia', as it isn't preloaded in anaconda for example
import wikipedia as wp

# scraping the wiki page, specifically the 'current constituents'
html = wp.page("Swiss_Market_Index#Current_constituents").html().encode("UTF-8")
try: 
    df = pd.read_html(html)[1]  # Try 2nd table first as most pages contain contents table first
except IndexError:
    df = pd.read_html(html)[0]
print(df.to_string())

# this will save the SMI constituents table from wikipedia to a .csv file for further use
df.to_csv('SMI_constituents.csv')
print('saved SMI constituents to SMI_constituents.csv')

# import python data science and utility libraries
import os, sys, itertools, urllib, io
import datetime as dt
import pandas as pd
import pandas_datareader as dr
import numpy as np

# create data sub-directory inside the current directory - this is where we will be putting the smi constituents data
data_directory = './data'
if not os.path.exists(data_directory): os.makedirs(data_directory)

# Import the SMI constituents from our wikipedia scraped .csv file
smi_constituents = pd.read_table(r'SMI_constituents.csv', encoding="UTF-8", delimiter=',')
print(smi_constituents['Ticker'])

# Define ticker symbols of the SMI constituents to be retrieved from the Yahoo finance API: symbols = ['']
symbols = smi_constituents['Ticker'] 

# Determine and print the number of SMI constituents ticker symbols:
# determine number of input stock ticker symbols
no_input_stocks = len(symbols)

# print number of input stock ticker symboks
print(no_input_stocks)

# period we want to get price data for
start_date = '2000-01-01'
end_date = '2021-02-19'

#######
stock_data_price = dr.data.DataReader('^SSMI', data_source='yahoo', start=start_date, end=end_date)

# remove all columns other than the adjusted closing price
stock_data_price = stock_data_price.drop(columns=['High', 'Open', 'Low', 'Close', 'Volume'])

# Rename the adjusted closing price column according to the SMI:
stock_data_price = stock_data_price.rename(columns={'Adj Close': "^SSMI"})
#######

# iterate over distinct ticker symbols
for symbol in symbols:
    
    # retrieve market data of current ticker symbol
    symbol_data = dr.data.DataReader('' + str(symbol) + '.SW', data_source='yahoo', start=start_date, end=end_date)
    
    print('Retrieving ' + str(symbol) + '')
    
    # collect the adjusted daily closing price of current ticker symbol
    stock_data_price['' + str(symbol) + '.SW'] = symbol_data['Adj Close']

# Inspect the first 10 rows of the retrieved SMI constituents daily adjusted closing price data:
print(stock_data_price.head(10))

# define the filename of the data to be saved
filename = 'smi_daily_closing.csv'

# save retrieved data to local data directory
stock_data_price.to_csv(os.path.join(data_directory, filename), sep=';', encoding='utf-8')

# import python data science and utility libraries
import os, sys, itertools, urllib, io
import datetime as dt
import pandas as pd
import pandas_datareader as dr
import numpy as np

# create data sub-directory inside the current directory - this is where we will be putting the smi constituents data
data_directory = './data'
if not os.path.exists(data_directory): os.makedirs(data_directory)

# Import the SMI constituents from our wikipedia scraped .csv file
smi_constituents = pd.read_table(r'SMI_constituents.csv', encoding="UTF-8", delimiter=',')
print(smi_constituents['Ticker'])

# Define ticker symbols of the SMI constituents to be retrieved from the Yahoo finance API: symbols = ['']
symbols = smi_constituents['Ticker'] 

# Determine and print the number of SMI constituents ticker symbols:
# determine number of input stock ticker symbols
no_input_stocks = len(symbols)

# print number of input stock ticker symboks
print(no_input_stocks)

# period we want to get price data for
start_date = '2000-01-01'
end_date = '2021-02-19'

# iterate over distinct ticker symbols
for symbol in symbols:
    
    # retrieve market data of current ticker symbol
    symbol_data = dr.data.DataReader('' + str(symbol) + '.SW', data_source='yahoo', start=start_date, end=end_date)
    print('Retrieving ' + str(symbol) + '')
    # This will save each ticker / symbol to a separate file
    filename = '' + str(symbol) + '-data.csv'
    symbol_data.to_csv(os.path.join(data_directory, filename), sep=';', encoding='utf-8')