# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^[0-9\)\(\s+-]+(\s?(?:x|extension|ext\.)\s?[0-9-]+)?$"
test_str = ("555-555-5555\n"
"555-555-5555 x55555\n"
"555-555-5555x55555\n"
"555-555-5555 extension 55555\n"
"555-555-5555 ext. 55555\n"
"(555) 555-5555\n"
"5555555555\n"
"555-5555\n"
"5555555\n"
"1-800-CONTACTS\n"
"1-800-555-5555\n"
"Hello world\n"
"(555-555-5555\n"
"0-999-0349300\n"
"+43 984-899-46515\n"
"+43 some bogus\n"
"939403 03904 aosdf\n")
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