# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(\S)[ \t]*(?:\r\n|\n)[ \t]*(\S)"
test_str = ("Random Data, Company\n"
"2015\n\n"
"This is a sentence that has line \n"
"break in the middle of it due to extracting from a PDF.\n\n"
"How do I support\n"
"3 line sentence \n"
"breaks please?\n\n"
"HEADER HERE\n\n"
"The first sentence will \n"
"match. However, this line will not match\n"
"for some reason \n"
"that I cannot figure out.\n\n"
"Portfolio: \n"
"http://DoNotMatchMeBecauseIHaveAPeriodInMe.com \n\n"
"Full Name \n"
"San Francisco, CA \n"
"94000\n\n"
"1500 testing a number as the first word in\n"
"a broken sentence.\n\n"
"Match sentences with capital letters on the next line like \n"
"Wi-Fi.\n\n"
"This line has \n"
"trailing spaces after exclamation mark! \n")
subst = "\\1 \\2"
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0)
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