# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<!^|\n|[.!?] )[A-Z\d][A-Za-z\d]*(?: (?:of )?[A-Z\d][A-Za-z\d]*)*"
test_str = ("My name is Sam Helsen or Sam H Helsen son of M Helsen working at 3M technologies as the President of Sales.\n"
"The first word in a sentence won't match. A capitalized word followed by \"of\" and another capitalized word will be matched: Foo of Bar. Not if the 2nd word is lowercase though: Foo of bar.\n"
"Words starting with digits will be matched even if not capitalized: 123foo.")
matches = re.finditer(regex, test_str)
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