# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\(pp\.\s+\d+(?:[—–-]\d+)?\)|\b\d+(?:[—–-]\d+)?(?=\.)"
test_str = ("- Mitchell, J.A. (2017). Citation: Why is it so important. Mendeley Journal, 67(2), (pp. 81-95). \n\n"
"- Denhart, H. (2008). Deconstructing barriers: Perceptions of students labeled with learning disabilities in higher education. Journal of Learning Disabilities, 40,41, 483-497.\n\n"
"(pp. 81). \n"
"12-12\n"
"http://test.com/12-23\n\n"
"Usually the page numbers follow a commas and then there is a dot (like this: , 1-2. ) How can I change the code according to this? Same goes for when there is only one page listed , number. and the ` (pp. 12)` format.")
matches = re.finditer(regex, test_str, re.MULTILINE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# 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