# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<=\s|\A)([^\s=]+)=(.*?)(?=(?:\s[^\s=]+=|$))"
test_str = "eventId=588622 app=HTTP in=5326 out=5326 categorySignificance=/Normal categoryBehavior=/Communicate/Query categoryDeviceGroup=/Application catdt=Web Cache categoryOutcome=/Success categoryObject=/Host/Application/Service art=1359127995713 cat=Access Log deviceSeverity=2 rt=1359127975000 src=1.1.1.1 sourceZoneURI=/All Zones/ArcSight System/Public Address Space Zones/US Department of Defense dst=208.85.40.20 destinationZoneURI=/All Zones/ArcSight System/Public Address Space Zones/ARIN/204.0.0.0-209.255.255.255 (ARIN) dpt=80 fileType=application/json; request=http://www.pandora.com/json/music/artist/justin-moore?explicit\\=false requestMethod=GET requestClientApplication=Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.142 Safari/535.19 cs2=false cs3=http://www.pandora.com/ cs5=Default cs1Label=Virus Name cs2Label=AV Enabled cs3Label=Referrer cs4Label=URL Category cs5Label=Policy cs6Label=Reputation ahost=ndeusemslvarc04.gold.rtgold.nima.mil agt=214.28.240.186 agentZoneURI=/All Zones/ArcSight System/Public Address Space Zones/US Department of Defense av=5.2.7.6474.0 atz=GMT aid=3DLoiRDsBABCAA9FvE1htRg\\=\\= at=syslog dvchost=xxx-xxx-xxx dtz=GMT _cefVer=0.1 ad.charset=utf-8"
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