regex_covid.py

with open('all_abstracts_lemmas.txt', 'r', encoding = "utf-8") as f:
    lemma_text = f.read()

n = 4
word = r'\W*([\w]+)'
text_search_como = re.findall(r'{}\W*{}{}'.format(word*n,'(?:comorbid|comorbidity)',word*n),
                              lemma_text)
flatten_text_search = [element for sublist in text_search_como for element in sublist
                       if len(element) >3]