Untitled

import csv
import requests
from bs4 import BeautifulSoup
# create CSV file and write header row
with open("scraped_data.csv", "w", newline='') as csvfile:
    writer = csv.writer(csvfile)
    writer.writerow(['ISBN', 'Bookname', 'Price', 'Author', 'Editor'])
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])
import requests
from bs4 import BeautifulSoup
import csv
import time

# get url
url = "https://ceresbookshop.com/fr/s/4704/romans"
if url:
    print("got url")

# initiate page number
page_num = 1

while (page_num<470):
    try:
        # send GET request to current page
        response = requests.get(f"{url}?page={page_num}")

        # check if page exists
        if response.status_code == 200:
            # parse HTML content using BeautifulSoup
            soup = BeautifulSoup(response.content, 'html.parser')
            print(f"Page {page_num-1} opened.")

            # extract product links from page
            products = soup.find_all("div", class_="product_name")
            for product in products:
                link = product.find("a")["href"]

                # write link to CSV file
                with open("Books_links.csv", "a", newline='') as csvfile:
                    writer = csv.writer(csvfile)
                    writer.writerow([link])
                    print(f"Link written to CSV file: {link}")
           
                
            print(f"Scraping done! {page_num-1} pages scraped.")

            # move on to next page
            page_num += 1

            # add delay of 1 second
            time.sleep(1)

        else:
            print(f"Scraping stopped not 200! {page_num-1} pages scraped.")
            break


    except Exception as e:
        print(f"Encountered an exception: {e}")
        print(f"Will retry in 5 seconds...")
        time.sleep(5)