Python: Clean Text

import re
from nltk.corpus import stopwords

# Ensure NLTK stopwords are downloaded
import nltk
nltk.download('stopwords')

def clean_text(text, custom_stopwords=None):
    """
    Clean the input text by removing file paths, metadata, stopwords, and custom keywords.

    Args:
        text (str): The input text to process.
        custom_stopwords (set, optional): A set of custom stopwords to remove. Defaults to None.

    Returns:
        str: The cleaned text.
    """
    # Step 1: Convert text to lowercase
    text = text.lower()

    # Step 2: Remove file paths using regex
    text = re.sub(r"[a-zA-Z]:\\[^ ]+", "", text)  # Remove Windows file paths
    text = re.sub(r"\/[^ ]+", "", text)          # Remove Unix-style file paths

    # Step 3: Remove numbers and special characters
    text = re.sub(r"\d+", "", text)              # Remove numbers
    text = re.sub(r"[^\w\s]", "", text)          # Remove punctuation and special characters

    # Step 4: Remove stopwords
    stop_words = set(stopwords.words('english'))
    if custom_stopwords:
        stop_words.update(custom_stopwords)

    tokens = text.split()
    filtered_tokens = [word for word in tokens if word not in stop_words]

    # Step 5: Join the tokens back into a single string
    return " ".join(filtered_tokens)

# Example usage
text = "who else going into the new year single 😊 c:\\ZE\\notebook\\DS2019 follow_rts_likes follow rts "
custom_stopwords = {"follow", "rts", "likes", "everyone", "retweets"}
cleaned_text = clean_text(text, custom_stopwords)
print(cleaned_text)