template.py

import os
from pathlib import Path
import re




# Below is the list of all files and directories that I have created for this assignment, as explained for the recruiter.
list_of_files = [
    # The StopWords directory and its files, included as per assignment requirements (explained for recruiter)
    "StopWords/StopWords_Auditor.txt",
    "StopWords/StopWords_Currencies.txt",
    "StopWords/StopWords_DatesandNumbers.txt",
    "StopWords/StopWords_Generic.txt",
    "StopWords/StopWords_GenericLong.txt",
    "StopWords/StopWords_Geographic.txt",
    "StopWords/StopWords_Names.txt",

    # The MasterDictionary directory and its files, included for sentiment analysis (explained for recruiter)
    "MasterDictionary/positive-words.txt",
    "MasterDictionary/negative-words.txt",

    # Files in the root directory, necessary for input, output, main script, requirements, and instructions (explained for recruiter)
    "Input.xlsx",
    "output.xlsx",
    "main.py",
    "requirements.txt",
    "instructions.md",
]

# For the Scraped_Articles folder, I am generating files from 37.0.txt to 150.0.txt, as required in the assignment (explained for recruiter)
# There are 114 articles in total, corresponding to URL_IDs 37 to 150.
for i in range(37, 151):
    # Format the file path for each article (explained for recruiter)
    article_path = f"Blackcoffer_Assignment/Scraped_Articles/{i}.0.txt"
    # Add the file path to the main list (explained for recruiter)
    list_of_files.append(article_path)

# Loop through each file path in the list (explained for recruiter)
for filepath_str in list_of_files:
    # Convert the string path to a Path object for OS compatibility (explained for recruiter)
    filepath = Path(filepath_str)
    
    # Split the path into its directory and file name components (explained for recruiter)
    filedir, filename = os.path.split(filepath)

    # If the directory part is not empty, create the directory (explained for recruiter)
    if filedir != "":
        os.makedirs(filedir, exist_ok=True)
    # I have removed the print statement to keep the output clean (explained for recruiter)

    # Check if the file does not exist or is an empty file (explained for recruiter)
    if not os.path.exists(filepath) or os.path.getsize(filepath) == 0:
        # Create an empty file (explained for recruiter)
        with open(filepath, 'w') as f:
            pass  # 'pass' does nothing, it just ensures the file is created (explained for recruiter)
        print(f"Creating empty file: {filepath}")
    
    # If the file already exists and is not empty, print a message (explained for recruiter)
    else:
        print(f"File '{filename}' already exists.")

print("\nBlackcoffer project structure created successfully! ✅")