# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"([\d]{2}\/[\d]{2}\/[\d]{4})[\s]([\d]{2}:[\d]{2}:[\d]{2}\.[\d]{2})\sid:\s([\d]{4})\sseq:\s([\d]{4})[\s<>]*type:\s([\da-f]{4})\slen:[\s]*([\d]{2})\s([\w]*)"
test_str = ("05/23/2017 14:19:57.96 id: 0001 seq: 0001 < type: 0009 len: 10 CMD_CHECK_PROTOCOL version: 7\n"
"05/23/2017 14:19:57.96 id: 0001 seq: 0001 > type: 8001 len: 72 ANS_OK \n"
"05/23/2017 14:19:58.07 id: 0001 seq: 0002 < type: 0001 len: 91 CMD_AUTH sender: 0 type: 4 id: 'admin'\n"
"05/23/2017 14:19:58.07 id: 0001 seq: 0002 > type: 8002 len: 10 ANS_ERR err_code: 0x1\n"
"05/23/2017 14:19:58.07 id: 0001 seq: 0001 > type: 000f len: 12 CMD_DISCONNECT reason: 3\n"
"05/23/2017 14:20:01.91 id: 0002 seq: 0003 < type: 0009 len: 10 CMD_CHECK_PROTOCOL version: 7\n"
"05/23/2017 14:20:01.91 id: 0002 seq: 0003 > type: 8001 len: 72 ANS_OK \n"
"05/23/2017 14:20:01.92 id: 0002 seq: 0004 < type: 0001 len: 91 CMD_AUTH sender: 0 type: 4 id: 'admin'\n"
"05/23/2017 14:20:01.92 id: 0002 seq: 0004 > type: 8002 len: 10 ANS_ERR err_code: 0x1\n"
"05/23/2017 14:20:01.92 id: 0002 seq: 0001 > type: 000f len: 12 CMD_DISCONNECT reason: 3\n"
"05/23/2017 14:24:53.27 id: 0003 seq: 0001 < type: 0009 len: 10 CMD_CHECK_PROTOCOL version: 7\n"
"05/23/2017 14:24:53.27 id: 0003 seq: 0001 > type: 8001 len: 72 ANS_OK \n"
"05/23/2017 14:24:53.32 id: 0003 seq: 0002 < type: 0001 len: 91 CMD_AUTH sender: 0 type: 4 id: 'Admin'\n"
"05/23/2017 14:24:53.32 id: 0003 seq: 0002 > type: 8001 len: 15 ANS_OK \n"
"05/23/2017 14:24:53.37 id: 0003 seq: 0003 < type: 0100 len: 16 CMD_USER_LIST limit: 0 offset: 0\n"
"05/23/2017 14:24:53.37 id: 0003 seq: 0003 > type: 8001 len: 499 ANS_OK \n"
"05/23/2017 14:24:53.40 id: 0003 seq: 0004 < type: 000d len: 10 CMD_SVR_GET_PARAMS parameter_id: 0")
matches = re.finditer(regex, test_str)
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