Filtro de texto - Python Programming Exercise

# Python program to censor words in a text file

def load_censored_words(censor_file):
    """
    Load the list of words to be censored from the specified file.
    Each word is stored on a separate line.
    """
    try:
        with open(censor_file, 'r', encoding='utf-8') as file:
            # Read lines, strip whitespace, and return as a set
            return set(line.strip() for line in file if line.strip())
    except FileNotFoundError:
        print(f"Error: The censor file '{censor_file}' was not found.")
        return set()
    except Exception as e:
        print(f"Error: {str(e)}")
        return set()


def censor_text_file(input_file, output_file, censor_file):
    """
    Censor specified words in the input file and write the results to the output file.
    Replaces words found in the censor list with "[CENSORED]".
    """
    # Load the list of words to be censored
    censored_words = load_censored_words(censor_file)
    if not censored_words:
        print("No words to censor. Exiting.")
        return

    try:
        # Open the input and output files
        with open(input_file, 'r', encoding='utf-8') as infile, open(output_file, 'w', encoding='utf-8') as outfile:
            for line in infile:
                # Replace each censored word with "[CENSORED]"
                for word in censored_words:
                    line = line.replace(word, "[CENSORED]")
                # Write the censored line to the output file
                outfile.write(line)
        
        print(f"Censored text written to '{output_file}'.")
    except FileNotFoundError:
        print(f"Error: The input file '{input_file}' was not found.")
    except Exception as e:
        print(f"Error: {str(e)}")


# Example usage
if __name__ == "__main__":
    # File paths
    input_file = "example_text.txt"       # The text file to censor
    output_file = "censored_output.txt"  # The file to save the censored text
    censor_file = "censor_list.txt"      # The file containing words to censor

    censor_text_file(input_file, output_file, censor_file)

 Output

censor_list.txt:

badword
offensive
secret

example_text.txt:

This is a secret message.
Do not use badword or any offensive language here.

Output (censored_output.txt):

This is a [CENSORED] message.
Do not use [CENSORED] or any [CENSORED] language here.