jknetl/lidl-price-scraper
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Detect discount

Browse Source
This commit is contained in:
Jakub Knetl
2024-01-30 18:14:32 +01:00
parent 7d9bf4a884
commit 3c0c748486
1 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
scrape.py
View File

@@ -10,15 +10,20 @@ def fetch_product_info(urls):
if response.status_code == 200: if response.status_code == 200:
soup = BeautifulSoup(response.text, 'html.parser') soup = BeautifulSoup(response.text, 'html.parser')
product_name = soup.find('h1', class_='keyfacts__title').text.strip() product_name = soup.find('h1', class_='keyfacts__title').text.strip()
product_price = soup.find('div', class_='m-price__price').text.strip() current_price = soup.find('div', class_='m-price__price').text.strip()
product_info.append([product_name, product_price, url]) 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: else:
print(f"Failed to fetch URL: {url}") print(f"Failed to fetch URL: {url}")
return product_info return product_info
def print_product_table(product_info): def print_product_table(product_info):
headers = ["Product Name", "Price", "URL"] headers = ["Product Name", "Price", "Discount", "original price", "URL"]
print(tabulate(product_info, headers=headers, tablefmt="grid")) print(tabulate(product_info, headers=headers, tablefmt="grid"))
if __name__ == "__main__": if __name__ == "__main__":