calc_ibov.py

import time
import yfinance
import dryscrape
from bs4 import BeautifulSoup
import pandas as pd

def get_b3_html():
    url = 'https://sistemaswebb3-listados.b3.com.br/indexPage/day/IBOV?language=pt-br'
    session = dryscrape.Session()
    session.visit(url)
    time.sleep(10) # make sure it loads properly
    session.render('b3_1.png') # show what is loaded 1
    
    select = session.at_xpath('//*[@id="selectPage"]')
    select.set("120")
    select.select_option()
    time.sleep(10) # make sure it loads properly
    session.render('b3_2.png') # show what is loaded 2

    response = session.body()
    with open('b3.html', 'w') as fp:
        # Cache
        fp.write(response)

    return response

def get_df(html):
    soup = BeautifulSoup(html, 'html.parser')
    table = soup.find('table')
    df = pd.read_html(
        str(table),
        decimal=',',
        thousands='.',
        )[0]

    mask = df['Código'].isin(['Quantidade Teórica Total', 'Redutor'])
    comp, redutor = df[~mask], df[mask]
    
    # for yfinance
    comp['Código'] = comp['Código'] + '.SA'
    comp.set_index("Código", inplace=True)
    redutor.set_index("Código", inplace=True)

    # Cache
    comp.to_pickle('composition.df')
    redutor.to_pickle('redutor.df')
    
    return comp, redutor

def get_market_data():
    market_data = yfinance.download(
        tickers = comp.index.tolist(),
        start="2021-04-14",
        end="2021-04-16",
        interval = '1d',
        treads = False
    )
    return market_data


html = get_b3_html()
comp, redutor = get_df(html)
market_data = get_market_data()

ibov_index = comp['Qtde. Teórica'] * market_data['Close'].loc['2021-04-15']
ibov = ibov_index.sum() / redutor['Qtde. Teórica'].loc['Redutor']

print('%.2f' % ibov)