# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\s*((?:\b(?:[djms]rs?|flam|liq|qr|st)\.|\b(?:[a-z]\.){2,}|\.\d[\d.]*|\.(?:com|net|org)\b|[^.?!])+(?:[.?!]+|$))"
test_str = ("Section 2.1. Classification of Subsatnces \n\n"
"Mr. and Mrs. Smith bought cheapsite.com for 1.5 million dollars, i.e. he paid a lot for it. Did he mind? Dr. Adam Jones Jr. thinks he didn't. In any case, this isn't true... Well, with a probability of .9 it isn't.However, this line wont do it. Qr. Test for Website.COM and Labs.ORG looks good.Creatively not working. t and finished. 9 to start. Highly Flammable Liquid Flam. H223 Liq. H334. \n"
"St. Bernard Dog was present.\n"
"The MW of gold is 100.1. Solubility is 40mg/L.")
subst = "$1\\n"
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.MULTILINE | re.IGNORECASE)
if result:
print (result)
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html