# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"((?:\+39)|(?:0039))+[0-9. ]+"
test_str = ("Something here\n\n"
"and something here 9, but (I have something here as well), 123456, Hi guys!\n\n"
"+39.1234.325636 test +39.321.1234567 test 0039.1234.325636 test 0039.321.1234567\n\n"
"0039 1234 325636 test 0039 321 1234567\n\n"
"sex male | date of birth 16/12/1927 | nationality italian\n\n"
"some stuff")
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