Python script for scraping product data from a website using Selenium WebDriver. It automates the search process for a list of product codes on https://www.plaisio.gr/ and saves the results in a CSV file. The script utilizes Chrome WebDriver and includes error handling for cases where no search results are found. The code is organized into funct…

plaisio.py

import csv
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from webdriver_manager.chrome import ChromeDriverManager

CODES = [
    # List of product codes to search for
    3991016, 3990583, 4176618, 4176596, 3853780, 4079914, 4080688, 4080718, 4172930, 4006402,
    3860795, 4006399, 3989178, 4108108, 4111656, 3578224, 4141210, 3903907, 4234413, 3846229,
    3820912, 3177998, 4033213, 3530795, 4048350, 3530728, 3522385, 3843378, 3731448, 4018567,
    3808769, 4148525, 3889262, 4111648, 3935450, 3919161, 3787591, 3023966, 2488167, 2049546,
    2417405, 1352407, 3899330, 3899373, 3899438, 4186060, 4180747, 4180739, 4180720, 4101162,
    4101170, 4100700, 3794644, 3862135, 4238745, 4238737, 3950778, 3950743, 3901793, 3885690
]

def scrape_product_data(driver, codes):
    # Open a CSV file to store the scraped data
    with open("product_results.csv", "w", newline="", encoding="utf-8") as csv_file:
        writer = csv.writer(csv_file)
        writer.writerow(["code", "product_title", "product_link", "product_price"])  # Header

        # Open the website in Chrome
        driver.get("https://www.plaisio.gr/")
        # Find the search input field
        search_input = driver.find_element(By.CLASS_NAME, "search-input")

        print(f"Searching for {len(codes)} products...")

        for code in codes:
            # Clear the search input and enter the product code
            search_input.clear()
            search_input.send_keys(str(code))
            search_input.send_keys(Keys.RETURN)

            # Wait until the search results container is visible
            wait = WebDriverWait(driver, 10)
            search_results = wait.until(EC.visibility_of_element_located((By.CLASS_NAME, "search-results__articles.border-right")))

            try:
                # Find the first search result
                first_li = search_results.find_element(By.TAG_NAME, "li")
                # Extract the product title and link
                product_title = first_li.find_element(By.CLASS_NAME, "description").find_element(By.CLASS_NAME, "ais-Highlight").text
                product_link = first_li.find_element(By.TAG_NAME, "a").get_attribute("href")
                # Extract the product price
                product_price_element = first_li.find_element(By.CLASS_NAME, "prices")
                product_price = product_price_element.find_element(By.CLASS_NAME, "current-price").text
            except:
                # If no search results found, leave the fields empty
                product_title = ""
                product_link = ""
                product_price = ""

            # Write the results to the CSV file
            writer.writerow([code, product_title, product_link, product_price])

def main():
    # Set up Chrome WebDriver
    driver = webdriver.Chrome(ChromeDriverManager().install())
    driver.maximize_window()
    # Scrape product data
    scrape_product_data(driver, CODES)
    # Close the browser
    driver.quit()

if __name__ == "__main__":
    main()