# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\+?\d{0,4}\s?\(?\+?\d{0,4}?\)?\s?[-., \s]?\d{0,4}[-., \s]?\d{0,4}?"
test_str = ("+21234567891\n"
"012345678913\n"
"+01234567891\n"
"0212 3456 7891\n"
"(+034) 1234 9132 0212\n"
"034 567 8910 1212\n"
"034 567 8912 1234\n"
"+1 230 4567 7894 \n"
"+44 123 3456 3445 \n"
"+21 234 5678 9134")
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