# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b[\w-]+(?:\.[\w-]+){2,}\b"
test_str = ("Received: by with SMTP id gx4so163592215ieb.1\n"
" for mail-ie0-x247.google.com <myemailaddress@gmail.com>; Mon, 01 Jun mail-ie0-x247.google.com 2015 18:34:50 -0700 (PDT)\n\n"
"max.google.com\n"
"Received: from localhost (localhost.localdomain [127.0.0.1])\n"
"by mail.server.com (Postfix) with ESMTP id 822B1190A4AF\n"
"for <alex@example.com>; Tue, 17 Feb 2015 13:13:54 +0000 (UTC)\n\n\n"
"Received: from [x.x.x.x] by mail.kampl.com (Cipher TLSv1.2:AES-SHA:128) (MDaemon PRO v15.0.1)\n\n"
"b-app05-06.boldchat.com\n"
"ns126a.ba1.enops.net\n"
"ms-out.evernote.com \n"
"obeml1.aerlingus.com\n"
"NHQSDFEXCHUB01.nam.coair.com\n"
"ncsmcexchub01.nam.coair.com\n"
"o1.em.thetaoofbadass.com\n\n"
"b-app05-06.boldchat.com\n"
"ns126a.ba1.enops.net\n"
"NHQSDFEXCHUB01.nam.coair.com\n"
"ncsmcexchub01.nam.coair.com\n\n"
"mta2l1.trans.r.grouponmail.co.uk\n"
"---...---.--.--.---.")
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