# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
^(
(?:\(?
(?:00|\+)
(?:[1-4]\d\d|[1-9]\d?)
\)?)?
[\-\.\ \\\/]?
)?
(
(?:\(?\d{1,}\)?
[\-\.\ \\\/]?){0,}
)
(?:
[\-\.\ \\\/]?
(?:
#|
ext\.?|
extension|
x
)
[\-\.\ \\\/]?
(\d+)
)?$
"""
test_str = ("08142 655456-712\n"
"0049 8142 655456-712\n"
"0049 (8142) 655456\n"
"+49 (8142) 655456\n"
"+49(8142)655456\n"
"+49 8142 655456\n"
"(+351) 282 43 50 50\n"
"90191919908\n"
"555-8909\n"
"001 6867684\n"
"001 6867684x1\n"
"1 (234) 567-8901\n"
"1-234-567-8901 x1234\n"
"1-234-567-8901 ext1234\n"
"1-234 567.89/01 ext.1234\n"
"1(234)5678901x1234\n"
"(123)8575973\n"
"(0055)(123)8575973\n")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE | re.VERBOSE)
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