mail@pastecode.io avatar
7 months ago
1.5 kB
import requests
from bs4 import BeautifulSoup
import csv

# Send a GET request to the URL
url = 'https://www.alkitab.tn/list-105801/new-english-books/'
response = requests.get(url)

# Parse the HTML content using Beautiful Soup
soup = BeautifulSoup(response.content, 'html.parser')

# Find all div elements with class 'meta_produit col-md-10 col-xs-8 no-padding'
product_divs = soup.find_all('div', class_='meta_produit col-md-10 col-xs-8 no-padding')

# Create a CSV file to store the scraped data
with open('scraped_data.csv', 'w', newline='', encoding='utf-8') as csv_file:
    csv_writer = csv.writer(csv_file)

    # Write the headers to the CSV file
    csv_writer.writerow(['ISBN', 'Bookname', 'Price', 'Author', 'Editor'])

    # Loop through each product div and extract the relevant data
    for product_div in product_divs:
        # Extract the ISBN, Bookname, Price, Author, and Editor from the relevant div elements
        isbn = product_div.find('div', class_='hidden-xs').text.strip()
        bookname = product_div.find('h4', class_='livre_titre').text.strip()
        price = product_div.find('div', class_='item_prix ml-01  table_prix_livraison  paper ').text.strip()
        author = product_div.find('h6', class_='livre_auteur').text.strip()
        editor = product_div.find('div', class_='editeur').text.strip()
        # Write the extracted data to the CSV file
        csv_writer.writerow([isbn, bookname, price, author, editor])