import os import json import time import subprocess import shutil from datetime import datetime from zoneinfo import ZoneInfo import concurrent.futures import argparse import json parser = argparse.ArgumentParser() parser.add_argument('-f', '--file', help='The file to make custom') parser.add_argument('-o', '--output', help='The output to make custom') parser.add_argument('-m', '--merge', help='The output to make custom') parser.add_argument('-r', '--rem', help='The output to make custom') args = parser.parse_args() arg_val = args.file out_val = args.output rem_val = args.rem or 0 merge_val = args.merge or 0 error_retries_times = 0 # Set the timezone to "America/Monterrey" os.environ['TZ'] = 'America/Monterrey' tz=ZoneInfo("America/Monterrey") os.system("") # enables ansi escape characters in terminal STOP_WHILE = False CUSTOM_NAME_CODE = "perfumeria" if arg_val: CUSTOM_NAME_CODE = arg_val # Define color codes RESET = "\033[0m" BOLD = "\033[1m" GREEN = "\033[92m" RED = "\033[91m" CYAN = "\033[96m" 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") if rem_val: remove_dir_and_contents(f"results_{CUSTOM_NAME_CODE}") # remove_dir_and_contents(f"{CUSTOM_NAME_CODE}") os.makedirs(f"results_{CUSTOM_NAME_CODE}", exist_ok=True) os.makedirs(f"{CUSTOM_NAME_CODE}", exist_ok=True) def start_files(file_type='', index_step=1, start_index=0): # 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) # Function to parse the single-line cookie from the cookie.txt file def load_cookie_from_file(cookie_file): with open(cookie_file, "r") as f: line = f.readline().strip() if line.startswith("#"): parts = line.split("\t") if len(parts) >= 7: cookie_name = parts[5] cookie_value = parts[6] return {cookie_name: cookie_value} return {} # Load the single cookie from the cookie.txt file cookie_file = r'./cookie.txt' cookies = load_cookie_from_file(cookie_file) # Function to get results for a given index def get_results(i=0): if globals()["error_retries_times"] > 5: print("Sleeping due to many retries") time.sleep(20) globals()["error_retries_times"] = int(globals()["error_retries_times"]) - 1 get_results(i) return # 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] data["pasillo"] = data_list[i][3] # data["proveedor"] = data_list[i][3] data["pedir"] = data_list[i][3] # 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: globals()["error_retries_times"] = globals()["error_retries_times"]+1 print(f"Failed to parse JSON for index {i} , Retried? {globals()["error_retries_times"]}") # 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) #time.sleep(1) # Sleep for 1 second between requests return True def merge_files(file_type = ''): stop = False data = [] rol_zero = [] rol_negative = [] no_rol_negative = [] real_list_rol = [] list_zauto = [] real_list = [] falta_res = [] # Directory containing the JSON files directory = f"results_{file_type}" # Process JSON files for i in range(13000): 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 ntest = curr["inventario"] <= curr["capacidadEmpaque"] and curr["resurtido"] != "SIN RESURTIDO" and curr["promedioLinea"] > 0.3 if int(curr["inventario"]) == 0 and curr["resurtido"] == "Automatico": rol_zero.append(curr) if int(curr["inventario"]) < 0: rol_negative.append(curr) if int(curr["inventario"]) < 0 and norol: no_rol_negative.append(curr) if rol: real_list_rol.append(curr) if rol_zero_auto: list_zauto.append(curr) if ntest: falta_res.append(curr) if curr["inventario"] == 0 and curr["resurtido"]== "Automatico": falta_res.append(curr) real_list.append(curr) falta_res.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) with open(f"{file_type}/negatives.json", "w") as f: json.dump(rol_negative, f, indent=2) with open(f"{file_type}/rol_empty.json", "w") as f: json.dump(rol_zero, f, indent=2) with open(f"{file_type}/faltantes.json", "w") as f: json.dump(falta_res, 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(custom_handler = "custom"): 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=14) as executor: futures = [ executor.submit(start_files, custom_handler, 13, 0), # Even indices: 0, 2, 4... executor.submit(start_files, custom_handler, 13, 1), # Odd indices: 1, 3, 5... executor.submit(start_files, custom_handler, 13, 2), # Odd indices: 1, 3, 5... executor.submit(start_files, custom_handler, 13, 3), # Odd indices: 1, 3, 5... executor.submit(start_files, custom_handler, 13, 4), # Odd indices: 1, 3, 5... executor.submit(start_files, custom_handler, 13, 5), # Odd indices: 1, 3, 5... executor.submit(start_files, custom_handler, 13, 6), # Odd indices: 1, 3, 5... executor.submit(start_files, custom_handler, 13, 7), # Odd indices: 1, 3, 5... executor.submit(start_files, custom_handler, 13, 8), # Odd indices: 1, 3, 5... executor.submit(start_files, custom_handler, 13, 9), # Odd indices: 1, 3, 5... executor.submit(start_files, custom_handler, 13, 10), # Odd indices: 1, 3, 5... executor.submit(start_files, custom_handler, 13, 11), # Odd indices: 1, 3, 5... executor.submit(start_files, custom_handler, 13, 12), # Odd indices: 1, 3, 5... ] 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 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}") def is_time_to_stop(): now = datetime.now(tz) return now.hour > 3 and now.minute > 0 and now.hour < 14 and now.minute < 59 Main_Loop = 0 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}" master_data_list = [] with open(f"array/master_{CUSTOM_NAME_CODE}.json", "r") as f: master_data_list = json.load(f) print(f"{count_files_in_folder(f"results_{CUSTOM_NAME_CODE}")}") while True: if merge_val: print("Merging...") merge_files(f'{CUSTOM_NAME_CODE}') break if count_files_in_folder(f"results_{CUSTOM_NAME_CODE}") >= len(master_data_list): merge_files(f'{CUSTOM_NAME_CODE}') break else: run_tasks(f"{CUSTOM_NAME_CODE}")