import requests from bs4 import BeautifulSoup import json import numpy as np import time from pprint import pprint from csv import writer def get_puzzle(difficulty): url = "https://www.nytimes.com/puzzles/sudoku/hard" page = requests.get(url) soup = BeautifulSoup(page.content, "html.parser") table = soup.find_all("div", {"class":"pz-game-screen"})[0] script = table.find_all("script", {"type":"text/javascript"}) text = script[0].get_text().split("=")[1] Dict = json.loads(text) grid = np.array( Dict[difficulty]["puzzle_data"]["puzzle"] ).reshape(9,9).tolist() puzzle_id = Dict[difficulty]["puzzle_id"] published = Dict[difficulty]["published"] print_date = Dict[difficulty]["print_date"] puzzle_data = "".join(str(x) for x in Dict[difficulty]["puzzle_data"]["puzzle"]) # List that we want to add as a new row csvrow = [difficulty,puzzle_id,published,print_date,puzzle_data] # Open our existing CSV file in append mode # Create a file object for this file with open('NYTSudoku.csv', 'a') as f_object: # Pass this file object to csv.writer() # and get a writer object writer_object = writer(f_object) # Pass the list as an argument into # the writerow() writer_object.writerow(csvrow) # Close the file object f_object.close() if __name__ == '__main__': get_puzzle("hard") get_puzzle("medium") get_puzzle("easy")