# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(?<postcode>|(?<outward>(?<area>\w{1,2}))(?<district>\d\w|\d{1,2}))(?:\s)?(?<inward>(?<sector>\d)(?<unit>\w\w))?"
test_str = ("W1J 7NT\n"
"DE12 8HJ\n"
"SW1A 1AA\n"
"HD7 5UZ\n"
"CH5 3QW\n"
"W2 1JB \n"
"PL7 1RF\n"
"EH99 1SB\n"
"G58 1SB\n"
"JE3 1EP\n\n"
"GIR 0AA")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE)
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