# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(\d+:\d{4}) (\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}\.\d{3}) ([A-Za-z\n]+) (.*?)(?=\n\d+:|$)"
test_str = ("5376:0084 2015-08-07 13:51:29.103 Error ### Error Message ###\n"
"5376:0084 2015-08-07 13:51:35.545 Error Discarding invalid session\n"
" System.Web.Services.Protocols.SoapException: Verify Session ID failed\n"
" at System.Web.Services.Protocols.SoapHttpClientProtocol.ReadResponse(SoapClientMessage message, WebResponse response, Stream responseStream, Boolean asyncCall)\n"
" at System.Web.Services.Protocols.SoapHttpClientProtocol.Invoke(String methodName, Object[] parameters)\n"
"5376:0084 2015-08-07 13:51:36.013 Error ### Error Message ###")
matches = re.finditer(regex, test_str, re.DOTALL)
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