import re
parentheticals = [ r"\(laughter\)", r"\(applause\)", 
                   r"\(music\)", r"\(video\)" ]

def clean_parens(text):
    new_text = text
    for rgx_match in parentheticals:
        new_text = re.sub(rgx_match, ' ', new_text, flags=re.IGNORECASE)
    return new_text
    
from sklearn.feature_extraction.text import CountVectorizer

CountVectorizer()
from sklearn.feature_extraction.text import CountVectorizer
corpus = ['This is the first document.',
           'This document is the second document.', 
           'And this is the third one. (laughter)',
           'Is this the first document?'] 
vectorizer = CountVectorizer(preprocessor=clean_parens)
X = vectorizer.fit_transform(corpus) 
print(vectorizer.get_feature_names())

# ['And', 'Is', 'This', 'document', 'first', 'is', 'one', 'second', 'the', 'third', 'this']