Simple script that uses selenium to replicate browser behavior to save data in an excel format

scape.py

# Install the required packages as below
# On Windows: pip install selenium webdriver_manager pandas
# On Mac: pip3 install selenium webdriver_manager pandas
import datetime
import pandas as pd
import time
from selenium import webdriver
from selenium.webdriver.common.by import By
from webdriver_manager.chrome import ChromeDriverManager

# Generate today's date in a format that the frontend website will accept
def today():
    today = datetime.datetime.today()

    # format the date as "MM/DD/YYYY"
    date_string = today.strftime("%m/%d/%Y")

    return date_string

# Initialize a new Chrome browser instance
driver = webdriver.Chrome(ChromeDriverManager().install())

# Navigate to localhost:3000 and input the login details
driver.get("http://localhost:3000")
time.sleep(1)

email_input = driver.find_element(By.XPATH, "//input[@name='email']")
email_input.send_keys("ishmam@something.com")

password_input = driver.find_element(By.XPATH, "//input[@name='password']")
password_input.send_keys("something")
time.sleep(1)

submit_button = driver.find_element(By.CSS_SELECTOR, "button[type='submit']")
submit_button.click()
time.sleep(1)

# In the redirected webpage, click on a specific button based on the button text
transformed_data_button = driver.find_element(By.XPATH, "//button[contains(text(), 'Transformed data')]")
transformed_data_button.click()
time.sleep(1)

# In the redirected webpage, enter the date in the date input
date_picker = driver.find_element(By.TAG_NAME, "input")
date_picker.click()
date_picker.send_keys(today())

# Iterate through all the rows of table data and store it
all_rows = driver.find_elements(By.TAG_NAME, 'tr')
all_data = []

for row in all_rows:
    split_data = row.text.split(' ')
    if len(split_data) == 5:
        all_data.append(split_data)

# Create a Pandas dataframe from the data
df = pd.DataFrame(all_data, columns=['#', 'Name', 'Sales Quantity', 'Sale Locations', 'Total Revenue'])

# Save the dataframe as an Excel file
df.to_excel('output.xlsx', index=False)

# close the browser
driver.quit()