# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?:[a-z0-9!#$%&'*+\/=?^_`{|}~-]+(?:\.[a-z0-9!#$%&'*+\/=?^_`{|}~-]+)*|\"(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21\x23-\x5b\x5d-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])*\")@(?:(?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\.)+[a-z0-9](?:[a-z0-9-]*[a-z0-9])?|\[(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?|[a-z0-9-]*[a-z0-9]:(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21-\x5a\x53-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])+)\])"
test_str = ("Valid email addresses\n"
"simple@example.com\n"
"\"user@name\"@example.com\n"
"very.common@example.com\n"
"disposable.style.email.with+symbol@example.com\n"
"other.email-with-hyphen@example.com\n"
"fully-qualified-domain@example.com\n"
"user.name+tag+sorting@example.com (may go to user.name@example.com inbox depending on mail server)\n"
"x@example.com (one-letter local-part)\n"
"example-indeed@strange-example.com\n"
"test/test@test.com (slashes are a printable character, and allowed)\n"
"admin@mailserver1 (local domain name with no TLD, although ICANN highly discourages dotless email addresses[10])\n"
"example@s.example (see the List of Internet top-level domains)\n"
"\" \"@example.org (space between the quotes)\n"
"\"john..doe\"@example.org (quoted double dot)\n"
"mailhost!username@example.org (bangified host route used for uucp mailers)\n"
"user%example.com@example.org (% escaped mail route to user@example.com via example.org)\n"
"user-@example.org (local part ending with non-alphanumeric character from the list of allowed printable characters)\n"
"postmaster@[123.123.123.123] (IP addresses are allowed instead of domains when in square brackets, but strongly discouraged)\n"
"postmaster@[IPv6:2001:0db8:85a3:0000:0000:8a2e:0370:7334] (IPv6 uses a different syntax)\n\n"
"Invalid email addresses\n"
"Abc.example.com (no @ character)\n"
"A@b@c@example.com (only one @ is allowed outside quotation marks)\n"
"a\"b(c)d,e:f;gi[j\\k]l@example.com (none of the special characters in this local-part are allowed outside quotation marks)\n"
"just\"not\"right@example.com (quoted strings must be dot separated or the only element making up the local-part)\n"
"this is\"not\\allowed@example.com (spaces, quotes, and backslashes may only exist when within quoted strings and preceded by a backslash)\n"
"this\\ still\\\"not\\\\allowed@example.com (even if escaped (preceded by a backslash), spaces, quotes, and backslashes must still be contained by quotes)\n"
"1234567890123456789012345678901234567890123456789012345678901234+x@example.com (local-part is longer than 64 characters)\n"
"i_like_underscore@but_its_not_allowed_in_this_part.example.com (Underscore is not allowed in domain part)\n"
"QA[icon]CHOCOLATE[icon]@test.com (icon characters)")
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