# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<=\d{3}\s)([A-Za-z\.]*)\s([A-Za-z\.]*)"
test_str = ("009 G Nantpaipakdee 38 955 722 650-240-0111\n"
"002 Eugénie Romette 432 734 782\n"
"005 Christina Pandullo 410-527-8241 410-527-8158\n"
"020 Joe Smith 410-771-7815 410-527-8771\n"
"030 K Kordysiewicz 42 239 3875\n"
"300 Cecile A. Wattiez 432 736 683\n"
"305 Do not use")
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