I have the following python script. In my python script i run it to convert some pdfs to excel. When i run it i enter the filename which the folders with the pdfs exist and i press enter and my script proceed the pdf files and return me a structured excel file.

我有以下的Python脚本。在我的python脚本中，我运行它来将一些pdf转换为EXCEL。当我运行它时，我输入带有pdf的文件夹所在的文件名，然后按Enter，我的脚本继续处理pdf文件，并返回给我一个结构化的Excel文件。

I tried to convert the py file to an exe file using the following commands

我尝试使用以下命令将py文件转换为exe文件

pip install pyinstaller 
pyinstaller --onefile myscript.py

When i execute this i am getting back an exe file but when i run it a cmd pop up window open and close very quickly without giving me the opportunity to enter the folder name.
Can anyone help on that ?

当我执行此命令时，我得到的是一个可执行文件，但当我运行它时，一个cmd弹出窗口很快就会打开和关闭，但我没有机会输入文件夹名。有人能帮上忙吗？

This is the python script.

这是一个python脚本。

import pandas as pd
import re
import os
from datetime import date
import datetime
import tkinter as tk
from tkinter import simpledialog

def get_folder_name():
    root = tk.Tk()
    root.withdraw()  # Hide the main window
    folder = simpledialog.askstring("Folder Name", "Enter the folder name (e.g.,  23.08.2023):")
    return folder



def process_pdfs_and_generate_excel(base_directory, folder):
    dfs = []
    folder_path = os.path.join(base_directory, folder)
    if not os.path.exists(folder_path):
        print(f"Folder '{folder}' does not exist.")
        return None

    for root, _, files in os.walk(folder_path):
        for filename in files:
            if filename.endswith('.txt'):
                filepath = os.path.join(root, filename)
                with open(filepath, 'r') as file:
                    lines = file.readlines()

                start_line = 18
                weighted_average_line_index = None
                for i, line in enumerate(lines[start_line:], start=start_line):
                    if "WEIGHTED AVERAGE" in line:
                        weighted_average_line_index = i
                        break

                if weighted_average_line_index is not None:
                    table_data = [line.strip().split('|') for line in lines[start_line:weighted_average_line_index] if '|' in line]

                    column_names = ['ARRIVAL_DATE', 'CONTAINER_NO', 'GR_QTY', 'LOT_NUMBER', 'OTHER_PAPERS', 'MOISTURE', 'PROHIBITIVE', 'File Name', 'Folder Name', 'EXCEL_FILE_ID']
                    mapped_data = {}
                    for column_name, index in zip(column_names, [2, 3, 5, 6, 7, 8, 9, None, None, None]):
                        mapped_data[column_name] = []
                        for row in table_data:
                            if column_name == 'Folder Name':
                                mapped_data[column_name].append(folder)
                            elif column_name == 'File Name':
                                mapped_data[column_name].append(filename)
                            elif column_name == 'EXCEL_FILE_ID':
                                mapped_data[column_name].append(f'PT_EKAMAS_{folder}')
                            elif len(row) > index:
                                mapped_data[column_name].append(row[index].strip())
                            else:
                                mapped_data[column_name].append('')

                    invoice_pattern = r"Invoice No\.\s*:\s*(\d+)"
                    invoice_no = ''
                    for line in lines:
                        invoice_match = re.search(invoice_pattern, line)
                        if invoice_match:
                            invoice_no = invoice_match.group(1)
                            break

                    ordered_grade_column = 'ORDERED_GRADE'
                    ordered_quality_column = 'ORDERED_QUALITY'
                    ordered_grade_pattern = r"Material No\.\s*:\s*\d+\s*-\s*(.*?);"
                    ordered_quality_pattern = r"Material No\.\s*:\s*\d+\s*-\s*.*?;\s*(.*?)\s*,"
                    ordered_grade = ''
                    ordered_quality = ''
                    if len(lines) >= 7:
                        ordered_grade_match = re.search(ordered_grade_pattern, lines[6])
                        ordered_quality_match = re.search(ordered_quality_pattern, lines[6])
                        if ordered_grade_match:
                            ordered_grade = ordered_grade_match.group(1).strip()
                        if ordered_quality_match:
                            ordered_quality = ordered_quality_match.group(1).strip()

                    entity_line = lines[5].strip()
                    entity_match = re.search(r"Vendor No\.\s*:\s*(.*)", entity_line)
                    entity = entity_match.group(1).strip().split(' - ')[-1] if entity_match else ''

                    if 'UK' in entity:
                        entity = 'UK'
                    elif 'GREECE' in entity:
                        entity = 'GR'
                    elif 'ITALY' in entity:
                        entity = 'IT'
                    elif 'LAUSANNE' in entity:
                        entity = 'CH'
                    elif 'VIPA RECYCLING (IRELAND) LTD' in entity:
                        entity = 'IE'

                    mapped_data['Entity'] = [entity] * len(table_data)
                    mapped_data['Invoice No'] = [invoice_no] * len(table_data)
                    mapped_data[ordered_grade_column] = [ordered_grade] * len(table_data)
                    mapped_data[ordered_quality_column] = [ordered_quality] * len(table_data)

                    df = pd.DataFrame(mapped_data)
                    dfs.append(df)

    result_df = pd.concat(dfs, ignore_index=True)

    formatted_date = datetime.datetime.now().strftime('%Y%m%d_%H%M%S')

    # Construct the folder path with the date
    folder_date = datetime.datetime.now().strftime('%Y%m%d')
    folder_path = os.path.join(base_directory, 'claims', folder_date)

    os.makedirs(folder_path, exist_ok=True)

    # Construct the Excel file path
    excel_filename = f'mycust{folder}_{formatted_date}.xlsx'
    excel_filepath = os.path.join(folder_path, excel_filename)

    # Add a new column with the name of the output Excel file
    result_df['EXCEL_FILE_NAME'] = excel_filename
    
    result_df['CONTAINER_NO'] = result_df['CONTAINER_NO'].apply(lambda x: re.search(r"/(.*?)/", x).group(1) if "/" in x else None)

    result_df.to_excel(excel_filepath, index=False)


    
    return excel_filepath

if __name__ == "__main__":
    base_directory = 'mydirectory'
    
    # Get the folder name from the user using the GUI
    folder = get_folder_name()
    
    if folder:
        excel_filepath = process_pdfs_and_generate_excel(base_directory, folder)
        if excel_filepath:
            print(f"Excel file saved at: {excel_filepath}")
    
    # Add an input prompt to keep the command prompt window open
    input("Press Enter to exit...")

__name__ is "__main__" only when the script is directly executed. Under an executable, chances are that it isn't using __name__ as __main__ and so the source inside may not be getting run.

只有当脚本直接执行时，__name__才是“__main__”。在可执行文件下，它可能没有使用__name__作为__main__，因此内部的源代码可能不会运行。

Try to eliminate that if __name__ == "main" check and it should be good if the rest steps are fine.

尝试取消IF__NAME__==“Main”检查，如果其余步骤都很好，则应该很好。