# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"CEF:(?<cef_cefVersion>\d+)\|(?<deviceVendor>[^|]*)\|(?<deviceProduct>[^|]*)\|(?<deviceVersion>[^|]*)\|(?<deviceEventClassId>[^|]*)\|(?<name>[^|]*)\|(?<severity>[^|]*)"
test_str = ("CEF:0|NombreDeFabricante|NombreDeProducto|1.0|IdentificadorTipoEvento|NombreEvento|High| eventId=6642904107 type=2 mrt=1435653826633 sessionId=0 generatorID=qn7nr00BABCAAWmHK722fQ\\=\\= catdt=Sinkhole modelConfidence=0 severity=0 relevance=10 assetCriticality=0 priority=3 art=1435653847001 cat=Bot deviceSeverity=Warning act=Mevade rt=1435653777000 shost=HostOrigen src=IPOrigen sourceZoneID=MfdHjJR0BABCAT9DSiOoDxQ\\=\\= sourceZoneURI=/All Zones/ArcSight System/Public Address Space Zones/RIPE NCC/62.0.0.0-62.255.255.255 (RIPE NCC) sourceGeoCountryCode=ES sourceGeoLocationInfo=NombreCiudad slong=-3.xxx slat=43.xxx sourceGeoPostalCode=xxxxx sourceGeoRegionCode=xx dhost=HostDestino dst=IPDestino destinationZoneID=Mokee5CcBABCGKZ5Updd27g\\=\\= destinationZoneURI=/All Zones/ArcSight System/Public Address Space Zones/RIPE NCC/193.0.0.0-195.255.255.255 (RIPE NCC) dpt=80 destinationGeoCountryCode=PT destinationGeoLocationInfo=NombreCiudad dlong=-9.xxx dlat=38.xxx destinationGeoPostalCode=xxx destinationGeoRegionCode=xx fname=Conexiones maliciosas filePath=/Ruta al fname/Conexiones maliciosas fileType=Rule request=http://HostDestino/policy ruleThreadId=SeiiQ04BABD9xHYRcACZnw\\=\\= cs1=Unknown cs2=<Resource URI\\=\"/xxxxxxxxxxx/Conexiones maliciosas\" ID\\=\"5ATikaUQBABDArjxMSXCuNQ\\=\\=\"/> cs6=CFYDHANP cn1=6739 flexNumber1=8 locality=1 cs1Label=Nombre ASN cs2Label=Configuration Resource ahost=xxxx.incibe.es agt=xxx.xxx.xxx.xxx av=5.1.2.5857.0 atz=Europe/Madrid aid=qn7nr00BABCAAWmHK722fQ\\=\\= at=superagent_ng dvchost=xxxx.incibe.es dvc=xxx.xxx.xxx.xxx deviceZoneID=Mbp432AABABCDUVpYAT3UdQ\\=\\= deviceZoneURI=/All Zones/ArcSight System/Private Address Space Zones/RFC1918: 172.16.0.0-172.31.255.255 deviceZoneExternalID=RFC1918: 172.16.0.0-172.31.255.255 deviceAssetId=4W0dT8T4BABCAV5TwjQThbw\\=\\= dtz=Europe/Madrid deviceFacility=Rules Engine eventAnnotationStageUpdateTime=1435653827604 eventAnnotationModificationTime=1435653827604 eventAnnotationAuditTrail=1,1435635335503,root,Queued,,,,\\n eventAnnotationVersion=1 eventAnnotationFlags=0 eventAnnotationEndTime=1435653777000 eventAnnotationManagerReceiptTime=1435653826633 _cefVer=0.1 ad.arcSightEventPath=3PUhT8T4BABCAYJTwjQThbw\\=\\= baseEventIds=6642903984\n"
"CEF:0|NombreDeFabricante|NombreDeProducto|1.0|IdentificadorTipoEvento|NombreEvento|High| eventId=6642904107 type=2 mrt=1435653826633 sessionId=0 generatorID=qn7nr00BABCAAWmHK722fQ\\=\\= catdt=Sinkhole modelConfidence=0 severity=0 relevance=10 assetCriticality=0 priority=3 art=1435653847001 cat=Bot deviceSeverity=Warning act=Mevade rt=1435653777000 shost=HostOrigen src=IPOrigen sourceZoneID=MfdHjJR0BABCAT9DSiOoDxQ\\=\\= sourceZoneURI=/All Zones/ArcSight System/Public Address Space Zones/RIPE NCC/62.0.0.0-62.255.255.255 (RIPE NCC) sourceGeoCountryCode=ES sourceGeoLocationInfo=NombreCiudad slong=-3.xxx slat=43.xxx sourceGeoPostalCode=xxxxx sourceGeoRegionCode=xx dhost=HostDestino dst=IPDestino destinationZoneID=Mokee5CcBABCGKZ5Updd27g\\=\\= destinationZoneURI=/All Zones/ArcSight System/Public Address Space Zones/RIPE NCC/193.0.0.0-195.255.255.255 (RIPE NCC) dpt=80 destinationGeoCountryCode=PT destinationGeoLocationInfo=NombreCiudad dlong=-9.xxx dlat=38.xxx destinationGeoPostalCode=xxx destinationGeoRegionCode=xx fname=Conexiones maliciosas filePath=/Ruta al fname/Conexiones maliciosas fileType=Rule request=http://HostDestino/policy ruleThreadId=SeiiQ04BABD9xHYRcACZnw\\=\\= cs1=Unknown cs2=<Resource URI\\=\"/xxxxxxxxxxx/Conexiones maliciosas\" ID\\=\"5ATikaUQBABDArjxMSXCuNQ\\=\\=\"/> cs6=CFYDHANP cn1=6739 flexNumber1=8 locality=1 cs1Label=Nombre ASN cs2Label=Configuration Resource ahost=xxxx.incibe.es agt=xxx.xxx.xxx.xxx av=5.1.2.5857.0 atz=Europe/Madrid aid=qn7nr00BABCAAWmHK722fQ\\=\\= at=superagent_ng dvchost=xxxx.incibe.es dvc=xxx.xxx.xxx.xxx deviceZoneID=Mbp432AABABCDUVpYAT3UdQ\\=\\= deviceZoneURI=/All Zones/ArcSight System/Private Address Space Zones/RFC1918: 172.16.0.0-172.31.255.255 deviceZoneExternalID=RFC1918: 172.16.0.0-172.31.255.255 deviceAssetId=4W0dT8T4BABCAV5TwjQThbw\\=\\= dtz=Europe/Madrid deviceFacility=Rules Engine eventAnnotationStageUpdateTime=1435653827604 eventAnnotationModificationTime=1435653827604 eventAnnotationAuditTrail=1,1435635335503,root,Queued,,,,\\n eventAnnotationVersion=1 eventAnnotationFlags=0 eventAnnotationEndTime=1435653777000 eventAnnotationManagerReceiptTime=1435653826633 _cefVer=0.1 ad.arcSightEventPath=3PUhT8T4BABCAYJTwjQThbw\\=\\= baseEventIds=6642903984\n")
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