Files
lidl-price-scraper/scrape.py
2024-01-30 18:14:32 +01:00

37 lines
1.4 KiB
Python

import requests
from bs4 import BeautifulSoup
from tabulate import tabulate
def fetch_product_info(urls):
product_info = []
for url in urls:
response = requests.get(url)
if response.status_code == 200:
soup = BeautifulSoup(response.text, 'html.parser')
product_name = soup.find('h1', class_='keyfacts__title').text.strip()
current_price = soup.find('div', class_='m-price__price').text.strip()
original_price_element = soup.find('span', class_='m-price__rrp')
original_price = original_price_element.text.strip() if original_price_element else "-"
discount_element = soup.find('div', class_='m-price__label')
discount = discount_element.text.strip() if discount_element else "-"
product_info.append([product_name, current_price, discount, original_price, url])
else:
print(f"Failed to fetch URL: {url}")
return product_info
def print_product_table(product_info):
headers = ["Product Name", "Price", "Discount", "original price", "URL"]
print(tabulate(product_info, headers=headers, tablefmt="grid"))
if __name__ == "__main__":
urls = [
"https://www.lidl.cz/p/p100370600",
"https://www.lidl.cz/p/p100358513",
"https://www.lidl.cz/p/p100336045",
]
product_info = fetch_product_info(urls)
print_product_table(product_info)