# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<ssn>(?<!\d{1})\d{3}[\s-]+\d{2}[\s-]+\d{4}(?!\d{1})|(?<!\d{1})\d{9}(?!\d{1}))|(?<creditCard>(?<![0-9]{1})(?:4[0-9]{12}(?:[0-9]{3})?|\d{4}[\s-]+\d{4}[\s-]+\d{4}[\s-]+\d{4}|\d{4}\d{4}\d{4}\d{4}|(?:5[1-5][0-9]{2}|222[1-9]|22[3-9][0-9]|2[3-6][0-9]{2}|27[01][0-9]|2720)[0-9]{12}|3[47][0-9]{13}|3(?:0[0-5]|[68][0-9])[0-9]{11}|6(?:011|5[0-9]{2})[0-9]{12}|(?:2131|1800|35\d{3})\d{11})(?![0-9]{1}))"
test_str = ("113-01-1111\n"
"213 81 1111\n"
"1553 01 1111\n"
"153 01 1111\n"
"153 01 11113\n"
"153-01-1111\n"
" 153-01-1111 \n"
"1313 01 11511\n\n"
"153-01-1111\n"
" 153-01-1111 \n"
"\\n113-01-1111 \n"
"\\t113-01-11114\n"
"\\t113-01-1111\\t\n"
"\\t 113-01-1111\\t\n"
"\\t113-01-1111 4\n"
"\\t113-01-11114\n"
"\\t113-01-1111\n\n"
"Robert Aragon 489‑36‑8350 4929‑3813‑3266‑4295\n"
"Ashley Borden 514‑14‑8905 5370‑4638‑8881‑3020\n"
"Thomas Conley 690‑05‑5315 4916‑4811‑5814‑8111")
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