# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?=.*?\d{3}( |-|.)?\d{4})((?:\+?(?:1)(?:\1|\s*?))?(?:(?:\d{3}\s*?)|(?:\((?:\d{3})\)\s*?))\1?(?:\d{3})\1?(?:\d{4})(?:\s*?(?:#|(?:ext\.?))(?:\d{1,5}))?)\b"
test_str = ("+1-855-419-0101 #807\n"
"1-855-419-0101 ext807\n"
"Tél.: 450-419-0100 #807\n"
"1 877 776-5743\n"
"1 877 776 5743 patate\n"
"1 877 776 57433\n"
"1 877 776 5743\n"
"3877 776 5743\n"
"514 555 9457\n"
"(514)555-9457\n"
"(514) 555-9457 Ext.333\n"
"15145557984\n"
"514.795.7777")
matches = re.finditer(regex, test_str, 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