from bs4 import BeautifulSoup

import csv

   

# Define the base URL pattern with page numbers

base_url = "http://www.cgv.co.kr/movies/?lt=1&ft=0&page={}"

   

# Initialize a CSV file for writing

with open('movie_ticket_sales.csv', 'w', newline='', encoding='utf-8') as csvfile:

csvwriter = csv.writer(csvfile)

csvwriter.writerow(['Title', 'Ticket Sales Percentage']) # Write the header row

   

# Loop through the first 10 pages

for page_num in range(1, 11):

url = base_url.format(page_num)

   

# Send an HTTP GET request

response = requests.get(url)

   

# Check if the request was successful

if response.status_code == 200:

soup = BeautifulSoup(response.text, 'html.parser')

   

# Find all elements with class "goodsTxInfo"

goods_elements = soup.find_all(class_='goodsTxInfo')

   

# Extract and write the titles and ticket sales percentages to the CSV file

for goods in goods_elements:

title = goods.find('strong', class_='title').text.strip()

ticket_sales = goods.find('div', class_='percent').text.strip()

csvwriter.writerow([title, ticket_sales])

print(f"Page {page_num} scraped successfully.")

else:

print(f"Failed to scrape page {page_num}.")

   

print("Scraping complete. Data saved in 'movie_ticket_sales.csv'.")