# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<=by\n)\w.+"
test_str = ("MIT Sample:\n"
"SOME ASPECTS OF RADIATION INDUCED NUCLEATION IN WATER\n"
"by\n"
"Chih-Ping Tso\n"
"B.Tech., Loughborough University of Technology, United Kingdom\n"
"(1968)\n"
"Submitted in Partial Fulfillment of\n"
"the Requirements for the Degree of\n"
"Master of Science\n"
"at the\n"
"Massachusetts Institute of Technology\n"
"August 1970\n"
"Signature of Author\n"
"Department of Nuclear Engineering\n"
"Certified by\n"
"Thesis Supervisor\n"
"Accepted by\n"
"Chairman, Departmental Committee\n"
"Archives on Graduate Students\n"
"MASS. INST. TECH.\n"
"SEP 21 1970\n"
"LIBRARIES\n\n"
"----------------------------------------------\n"
"Virginia Tech Sample:\n"
"FORMATTING VARIABLES AND TYPEFACE VARIATIONS\n"
"OF\n"
"DOT-MATRIX PRINT AND THEIR EFFECT\n"
"ON\n"
"READING COMPREHENSION AND READING SPEED\n"
"by\n"
"James A. Holmes\n"
"Dissertation submitted to the Faculty of the\n"
"Virginia Polytechnic Institute and State University\n"
"in partial fulfillment of the requirements for the degree of\n"
"DOCTOR OF EDUCATION\n"
"in\n"
"Vocational and Technical Education\n"
"March, 1986\n"
"Blacksburg, Virginia")
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