Re Snippet for normalising whitespaces and new lines. source: http://textacy.readthedocs.io/en/latest/_modules/textacy/preprocess.html#normalize_whitespace

normalizeSpaces.py

import re

LINEBREAK_REGEX = re.compile(r'((\r\n)|[\n\v])+')

NONBREAKING_SPACE_REGEX = re.compile(r'(?!\n)\s+')

def normalize_whitespace(text):
    """
    Given ``text`` str, replace one or more spacings with a single space, and one
    or more linebreaks with a single newline. Also strip leading/trailing whitespace.
    """
    return NONBREAKING_SPACE_REGEX.sub(' ', LINEBREAK_REGEX.sub(r'\n', text)).strip()