# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<=\w)(?<!\w-\w)(?: ?-+ ?)+(?=\w)(?!\w-\w)"
test_str = ("<!-- The following should match. Not the dashes in the comment tag, obviously ;P -->\n"
"<h2 class=\"chapter_title\">Chapter 01 -- The Beginning</h2>\n"
"<h2 class=\"chapter_title\">Chapter 02 - The Reckoning</h2>\n"
"<h2 class=\"chapter_title\">Chapter 03 - - The Aftermath</h2>\n"
"<h2 class=\"chapter_title\">Chapter 04--The Conclusion</h2>\n"
"<p>I was having the usual - cheeseburger and a cold beer.</p>\n\n"
"<!-- The following should not match -->\n"
"<p>I was wearing a t-shirt.</p>\n"
"<p>It was a drunken mix-up</p>\n"
"<p>---</p>\n"
"<p>-----</p>\n"
"<p>- - -</p>\n"
"<p> - - </p>\n"
"<p> - - - </p>\n")
subst = "—"
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.MULTILINE)
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