pablohfreitas

import selenium
import time
import pandas as pd
import numpy as np
from time import sleep
from selenium import webdriver as wb
from tqdm import tqdm

import warnings
from warnings import simplefilter

pablohfreitas

mlinks = pd.read_excel('C:/Users/Pablo Henrique/dataset_PremierLeague.xlsx')
mlinks.drop(['Unnamed: 0'], axis=1, inplace=True)
mlinks.head()

pablohfreitas

#Website link
wd = wb.Chrome(executable_path=r'C:/Users/Pablo Henrique/chromedriver.exe')
wd.get('https://www.premierleague.com/')

pablohfreitas

# Cria uma lista com os links de cada partida
list_mlinks = mlinks['link_match']

# Cria dois objetos vazios, onde armazenaremos os resultados obtidos
data_matches = []
data_h2h = []

# Inicia o loop para percorrer todos os links
for link in tqdm(list_mlinks):
    wd.get(link) #acessa o link da partida