# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?P<Timestamp>\w{3}\s+\d{1,2}\s\d{1,2}:\d{2}:\d{2})\s(?P<A1>\w+)\s(?P<A2>[\S]+)\:\s(?P<A3>.*)"
test_str = ("Jan 9 01:04:49 syntax sshd(pam_unix)[21354]: authentication failure; logname= uid=0 euid=0 tty=NODEVssh ruser= rhost=120-123-141-4.hinet-ip.hinet.com \n\n"
"Jul 10 04:17:11 syntax su(pam_unix)[95367]: session opened for user abc by (uid=0)\n\n"
"May 1 14:06:19 syntax su(pam_unix)[95367]: session closed for user abc\n\n"
"Oct 23 18:08:26 syntax logrotate: ALERT exited abnormally with [1]\n\n"
"Jun 14 21:42:52 syntax su(pam_unix)[95367]: session opened for user cbx by (uid=0)")
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