import os import json import time import subprocess import shutil from datetime import datetime from zoneinfo import ZoneInfo import concurrent.futures # Set the timezone to "America/Monterrey" os.environ['TZ'] = 'America/Monterrey' os.system("") # enables ansi escape characters in terminal tz=ZoneInfo("America/Monterrey") STOP_WHILE = False # Define color codes RESET = "\033[0m" BOLD = "\033[1m" GREEN = "\033[92m" RED = "\033[91m" CYAN = "\033[96m" MASTER_FILE = ["cava", "gourmet"] def remove_dir_and_contents(dir_path): if os.path.isdir(dir_path): shutil.rmtree(dir_path) print(f"Directory {dir_path} and all its contents removed successfully.") else: print(f"Directory {dir_path} does not exist or is not a directory.") def copy_directory(src, dst): # Check if the source directory exists if os.path.exists(src): # If the destination directory exists, delete it first if os.path.exists(dst): shutil.rmtree(dst) # Remove the destination directory and its contents shutil.copytree(src, dst) # Copy the entire directory tree from src to dst print(f"Copied {src} to {dst}") else: print(f"Source directory {src} does not exist") remove_dir_and_contents(f"results_gourmet") remove_dir_and_contents(f"results_cava") # remove_dir_and_contents("gourmet") # remove_dir_and_contents("cava") os.makedirs(f"results_gourmet", exist_ok=True) os.makedirs(f"results_cava", exist_ok=True) os.makedirs(f"gourmet", exist_ok=True) os.makedirs(f"cava", exist_ok=True) def start_files(file_type='', index_step=1, start_index=0): def update_json_file(file_path, categoria_real_value): # Step 1: Read the JSON data with open(file_path, "r") as f: file_data = json.load(f) # Step 2: Update the data if "inventario" in file_data: file_data["categoria_real"] = categoria_real_value # Step 3: Write the updated data back to the file with open(file_path, "w") as f: json.dump(file_data, f, indent=4) # Optional: indent for readability # Load the JSON list from the file print(f"{GREEN}Starting {file_type} at {index_step} in {start_index} {RESET}") with open(f"array/master_{file_type}.json", "r") as f: data_list = json.load(f) # Load the single cookie from the cookie.txt file cookie_file = r'./cookien.txt' # Function to get results for a given index def get_results(i=0): # Check if the file exists and contains the 'inventario' field file_path = f"results_{file_type}/file_{i}.json" if os.path.exists(file_path): with open(file_path, "r") as f: try: file_data = json.load(f) if "inventario" in file_data: print(f"{GREEN}File {file_path} already contains 'inventario'. Skipping...{RESET}") return except json.JSONDecodeError: print(f"Failed to parse JSON for index {i}") # Get the "codigo" from the list codigo = data_list[i][1] # Prepare the curl equivalent request using the subprocess curl_command = [ 'curl', '-k', '-s', '-A', 'Mozilla/5.0 (Linux; Android 11; SAMSUNG SM-G973U) AppleWebKit/537.36 (KHTML, like Gecko) SamsungBrowser/14.2 Chrome/87.0.4280.141 Mobile Safari/537.36', '-b', 'cookien.txt', f'https://www.intracomer.com.mx/simaEspecialWeb/AuditarServlet?_param=22&tipoReporte=2&codigo={codigo}' ] result = subprocess.run(curl_command, capture_output=True, text=True, encoding="utf-8") # Check if the result is valid JSON try: data = json.loads(result.stdout) data["seccion_numero"] = data_list[i][0] data["categoria_real"] = data_list[i][2] # Write the data to the file with open(file_path, "w") as f: end_time = datetime.now(tz) print(f"{GREEN}Done index {i}, Barcode: {data_list[i][1]}{RESET}, {RED}in {file_type}{RESET} {RED}{end_time.strftime('%Y-%m-%d %H:%M:%S')}{RESET}") json.dump(data, f) except json.JSONDecodeError: print(f"Failed to parse JSON for index {i} {RED} in {file_type}{RESET} Retrying...") # time.sleept(0.1) # get_results(i) # Loop through the list, fetching results for every index with the given step for i in range(start_index, len(data_list), index_step): get_results(i) return True def merge_files(file_type = ''): stop = False data = [] rol_zero = [] rol_negative = [] no_rol_negative = [] real_list_rol = [] list_zauto = [] real_list = [] ntest = [] end_time = datetime.now(tz) # Directory containing the JSON files directory = f"results_{file_type}" # Process JSON files for i in range(99999): file_path = os.path.join(directory, f"file_{i}.json") if os.path.exists(file_path): with open(file_path, "r") as f: arr = json.load(f) data.append(arr) else: continue # Process the collected data for curr in data: if curr is not None and "resurtido" in curr and "inventario" in curr: rol = curr["resurtido"] != "SIN RESURTIDO" norol = curr["resurtido"] == "SIN RESURTIDO" rol_zero_auto = curr["resurtido"] == "Automatico" and curr["inventario"] == 0 if int(curr["inventario"]) == 0 and curr["resurtido"] == "Automatico": rol_zero.append(curr) elif int(curr["inventario"]) < 0 and norol: no_rol_negative.append(curr) elif rol: real_list_rol.append(curr) if int(curr["inventario"]) < 0: rol_negative.append(curr) if int(curr["inventario"]) < int(curr["capacidadEmpaque"]) and curr["resurtido"] == "Automatico" and curr["promedioLinea"] > 0.3: ntest.append(curr) if int(curr["inventario"]) < (int(curr["capacidadEmpaque"]) * 4) and curr["resurtido"] == "Automatico" and curr["promedioLinea"] > 1: ntest.append(curr) real_list.append(curr) ntest.sort(key=lambda x: float(x.get("promedioLinea", 0)), reverse=True) # Write the results to a JSON file with open(f"{file_type}/result.json", "w") as f: json.dump(real_list, f, indent=2) # Write the results to a JSON fil with open(f"{file_type}/rol_empty.json", "w") as f: json.dump(rol_zero, f, indent=2) with open(f"{file_type}/negatives.json", "w") as f: json.dump(rol_negative, f, indent=2) with open(f"{file_type}/faltantes.json", "w") as f: json.dump(ntest, f, indent=2) end_time = datetime.now(tz) print(f"{CYAN}MERGED {file_type} at {RESET}{RED}{end_time.strftime('%Y-%m-%d %H:%M:%S')}{RESET}") return True # Main loop def run_tasks(): start_time = datetime.now(tz) print(f"{CYAN}Started processing at {RESET}{RED}{start_time.strftime('%Y-%m-%d %H:%M:%S')}{RESET}") with concurrent.futures.ThreadPoolExecutor(max_workers=18) as executor: futures = [ executor.submit(start_files, 'gourmet', 8, 0), executor.submit(start_files, 'gourmet', 8, 1), executor.submit(start_files, 'gourmet', 8, 2), executor.submit(start_files, 'gourmet', 8, 3), executor.submit(start_files, 'gourmet', 8, 4), executor.submit(start_files, 'gourmet', 8, 5), executor.submit(start_files, 'gourmet', 8, 6), executor.submit(start_files, 'gourmet', 8, 7), executor.submit(start_files, 'cava', 8, 0), executor.submit(start_files, 'cava', 8, 1), executor.submit(start_files, 'cava', 8, 2), executor.submit(start_files, 'cava', 8, 3), executor.submit(start_files, 'cava', 8, 4), executor.submit(start_files, 'cava', 8, 5), executor.submit(start_files, 'cava', 8, 6), executor.submit(start_files, 'cava', 8, 7), ] done, not_done = concurrent.futures.wait(futures, return_when=concurrent.futures.ALL_COMPLETED) # Check when all futures are done if not not_done: # If 'not_done' is empty, all tasks are done merge_files('gourmet') merge_files('cava') print("All futures are completed.") # Optionally process results if needed for future in done: try: result = future.result() # Get the result of each future except Exception as exc: print(f"Task generated an exception: {exc}") # Wait for all tasks to complete # for future in concurrent.futures.as_completed(futures): # future.result() end_time = datetime.now(tz) print(f"{CYAN}Script finished at {RESET}{RED}{end_time.strftime('%Y-%m-%d %H:%M:%S')}{RESET}") STOP_WHILE = False def merge_all(): merge_files('abarrotes') def is_time_to_stop(): now = datetime.now(tz) globals()["STOP_WHILE"] = True return now.hour > 12 and now.minute > 50 and now.hour < 3 and now.minute < 59 def is_time_to_run(): now = datetime.now(tz) return now.hour > 3 and now.minute > 0 and now.hour < 15 and now.minute < 59 COUNT_DOWN = 0 master_data_list1 = [] with open(f"array/master_{MASTER_FILE[0]}.json", "r") as f: master_data_list1 = json.load(f) master_data_list2 = [] with open(f"array/master_{MASTER_FILE[1]}.json", "r") as f: master_data_list2 = json.load(f) def count_files_in_folder(folder_path): try: # List all items in the folder all_items = os.listdir(folder_path) # Count only the files file_count = sum(1 for item in all_items if os.path.isfile(os.path.join(folder_path, item))) return file_count except FileNotFoundError: return "The folder does not exist." except Exception as e: return f"An error occurred: {e}" while True: if count_files_in_folder(f"results_{MASTER_FILE[0]}") >= len(master_data_list1) and count_files_in_folder(f"results_{MASTER_FILE[1]}") >= len(master_data_list2): break else: run_tasks()