Stock Scraping Tool

import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import pandas as pd
import matplotlib.pyplot as plt

def scrape_stock_data(stock_symbol):
    url = f'https://finance.yahoo.com/quote/{stock_symbol}'

    # Use a headless browser for dynamic content
    options = webdriver.ChromeOptions()
    options.add_argument('--headless')

    driver = webdriver.Chrome(options=options)
    driver.get(url)

    try:
        # Wait for the stock price to load (adjust timeout if needed)
        stock_price_element = WebDriverWait(driver, 10).until(
            EC.presence_of_element_located((By.CSS_SELECTOR, 'span[data-reactid*="50"]'))
            # You may need to modify the CSS selector based on your findings
        )

        stock_price = stock_price_element.text
        return {'stock_symbol': stock_symbol, 'stock_price': stock_price}
    except Exception as e:
        print(f"Failed to find stock price for {stock_symbol}: {e}")
        return None
    finally:
        driver.quit()

def analyze_stock_data(data_frame):
    # Perform statistical analysis using pandas
    # Example: Calculate the mean, standard deviation
    mean_price = data_frame['stock_price'].mean()
    std_dev_price = data_frame['stock_price'].std()

    return mean_price, std_dev_price

def visualize_data(data_frame):
    # Example: Create a simple bar plot
    data_frame.plot(x='stock_symbol', y='stock_price', kind='bar', title='Stock Prices')
    plt.show()

def main():
    stock_symbols = ['AAPL', 'GOOGL', 'MSFT']  # Add more symbols as needed
    stock_data_list = []

    for symbol in stock_symbols:
        stock_data = scrape_stock_data(symbol)
        if stock_data:
            stock_data_list.append(stock_data)

    # Create a pandas DataFrame from the collected data
    data_frame = pd.DataFrame(stock_data_list)

    # Check if the DataFrame is not empty before proceeding
    if not data_frame.empty:
        # Analyze and visualize the data
        mean_price, std_dev_price = analyze_stock_data(data_frame)
        print(f"Mean Stock Price: {mean_price}")
        print(f"Standard Deviation of Stock Price: {std_dev_price}")

        visualize_data(data_frame)
    else:
        print("No data available.")

if __name__ == "__main__":
    main()