from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
from bs4 import BeautifulSoup
import time
import pandas as pd
from datetime import datetime, timedelta

# Calculate the end date, which is 5 days from now
end_date = datetime.now() + timedelta(days=5)

# Initialize an empty DataFrame to store the scraped data
df = pd.DataFrame()

# Loop from the start date to the end date
current_date = datetime(2023, 1, 1)  # start date
while current_date <= end_date:
    # Format the date in the required format
    date_string = current_date.strftime("%b%d.%Y").lower()
    # Create the URL
    url = f"https://www.forexfactory.com/calendar?day={date_string}"
    
    driver = None

    try:
        s = Service(ChromeDriverManager().install())
        driver = webdriver.Chrome(service=s)
        driver.get(url)

        time.sleep(10)  # sleep for 10 seconds

        page_source = driver.page_source

        html_data = page_source  # replace with the actual column name        
        soup = BeautifulSoup(html_data, 'html.parser')

        # Continue with your scraping code...
        # ...

        # Find all <td> elements with the specified class
        td_dates = soup.find_all('td', class_='calendar__cell calendar__date date')

        # Find all <td> elements with the specified class
        td_times = soup.find_all('td', class_='calendar__cell calendar__time time')
        
        # Extract the time from the <td> elements
        times = [td_element.get_text(strip=True) for td_element in td_times]

        # Repeat the date value to match the length of other lists
        dates = [td_dates[0].span.get_text(strip=True)] * len(times)

        # Extract the values from all occurrences
        for td_element in td_dates[1:]:
            span_element = td_element.find('span', class_='date')
            if span_element is not None:
                value = span_element.text.strip()
                dates.append(value)

        # Find all <td> elements with the specified class
        td_currency = soup.find_all('td', class_='calendar__cell calendar__currency currency')

        # Extract the currency values
        currencies = [td.get_text(strip=True) for td in td_currency]

        # Find all <td> elements with class starting with the specified string
        td_impacts = soup.find_all('td', class_=lambda value: value and value.startswith('calendar__cell calendar__impact impact calendar__impact'))

        # Extract the impact values from the <span> element
        impacts = [td.span['title'] for td in td_impacts]

        # Find all <td> elements with the specified class
        td_events = soup.find_all('td', class_='calendar__cell calendar__event event')

        # Extract the event titles from the <span> elements
        event_titles = [td_event.span.text.strip() for td_event in td_events]

        tr_details = soup.find_all('tr', class_='calendar__row calendar__expand')

        details_ids = [tr_element.get('data-eventid') for tr_element in tr_details]

        # Find all <td> elements with the specified class
        td_actuals = soup.find_all('td', class_='calendar__cell calendar__actual actual')

        # Extract the values from the <td> elements
        actual = [td_actual.get_text(strip=True) for td_actual in td_actuals]

        # Find all <td> elements with the specified class
        td_forecasts = soup.find_all('td', class_='calendar__cell calendar__forecast forecast')

        # Extract the forecast values from the <td> elements
        forecasts = [td_forecast.find('span', class_='calendar-forecast').get_text(strip=True) for td_forecast in td_forecasts]

        # Find all <td> elements with the specified class
        td_previous_values = soup.find_all('td', class_='calendar__cell calendar__previous previous')

        # Extract the previous values from the <td> elements
        previous = [td_previous.find('span', class_='calendar-previous').get_text(strip=True) for td_previous in td_previous_values]

        data = {
            'Date': dates,
            'Time': times,
            'Currency': currencies,
            'Impact': impacts,
            'Event Title': event_titles,
            'Details id': details_ids,
            'Actual': actual,
            'Forecast': forecasts,
            'Previous': previous
        }
        df = pd.concat([df, pd.DataFrame(data)], ignore_index=True)
    except Exception as e:
        print(f"An error occurred: {e}")
    finally:
        if driver is not None:
            driver.quit()

    # Increment the current_date by one day
    current_date += timedelta(days=1)

# Save the DataFrame to a CSV file
df.to_csv('Forex Factory Calendar.csv', index=False)