# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(^.*?(?:Lane|Street|Boulevard|Crescent|Place|Road|Highway|Avenue|Drive|Circuit|Parade|Telopea|Nicklin Way|Terrace|Square|Court|Close|Endeavour Way|Esplanade|East|The Centreway|Mall|Quay|Gateway|Low Way|Point|Rd|Morinda|Way|Ave|St|South Steyne|Broadway|HQ|Expressway|Street|Castlereagh|Meadow Way|Track|Kulkyne Way|Narabang Way|Bank)),(?:)? ?(.*?),? ?([A-Z]{2,3}),? ?(\d{,4})$"
test_str = ("139 McKinnon Road, PINELANDS, NT, 829\n"
"108 East Point Road, Fannie Bay, NT, 820\n"
"3-11 Hamilton Street, Townsville City, QLD, 4810\n"
"40 17 Geranium Street, THE GARDENS, NT, 820\n"
"1, 3, 5 Demeter Street & 12 Hermes Avenue ROUSE HILL NSW 2155\n"
"Lot 9 Island Point Road, ST GEORGES BASIN, NSW, 2540\n"
"31 Stephen Street SOUTH TOOWOOMBA QLD 4350\n"
"316 Sturt Street and 511 Flinders Street, Townsville City, QLD, 4810")
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