site Valor da Globo

get_dolar_site_globo.py

import pandas as pd
from bs4 import BeautifulSoup
import win32com.client as win32
from requests import get
import lxml.html
from pprint import pprint

url = 'https://valor.globo.com/'
# html = urlopen(url)
response = get(url)
html = response.text
soup = lxml.html.fromstring(html)
bs = BeautifulSoup(html, 'lxml')
tabela = bs.select('section-data_table tr')
tr = bs.find_all('tr')
soup.xpath('//section[@class="section-data"][2]/div[2]//table//tbody//tr/td/text()')
for r in soup.xpath('//section[@class="section-data"][2]/div[2]//table'):
    cabecalho = r.xpath('thead//tr//th//text()')
    for i in r.xpath('tbody//tr'):
        linha = ''.join(str(i.xpath('td/text()')).split(','))
        if 'Dólar' in linha:
            name = linha.split("'")[1]
            compra = linha.split("'")[3]
            venda = linha.split("'")[5]
            variacao = linha.split("'")[7]
            pprint(f"{name}.: COMPRA: {compra} - VENDA: {venda} - VARIAÇÃO: {variacao}")

# dolarc = tr[1].text
# dolart = tr[2].text
# valorc = tr[3].text
#
# dolar1 = []
# dolar2 = []
# valor1 = []
#
# for tabela in tabela:
#     dolar1 = dolarc.contents[1]
#     dolar2 = dolart.contents[2]
#     valorc = dolart.contents[0]

# df = pd.DataFrame({"Dolar Comercial": compra,"Dolar Turismo":venda,})
# print(df.head())