import re
regex = re.compile((r"(?ms)<PNR>([\w]+)<\/PNR>\n"))
test_str = ("<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"yes\"?>\n"
"<EGE_Booking>\n"
" <TripID>1004-3637-360</TripID>\n"
" <RecordLocator>1004-3637-360</RecordLocator>\n"
" <Travelers>\n"
" <Traveler>\n"
" <PerCode>13593199</PerCode>\n"
" <FirstName>Claude</FirstName>\n"
" <LastName>Christensson</LastName>\n"
" <ContactDetails>\n"
" <Email>claude.christensson@wirelesscar.com</Email>\n"
" <MobilePhone>46765537005</MobilePhone>\n"
" </ContactDetails>\n"
" <TravellerCostCenter>\n"
" <CostCenter Code=\"CC3\">\n"
" <Label>Employee ID</Label>\n"
" <Value>56524</Value>\n"
" </CostCenter>\n"
" <CostCenter Code=\"CC4\">\n"
" <Label>Global Department code</Label>\n"
" <Value>DI43400</Value>\n"
" </CostCenter>\n"
" </TravellerCostCenter>\n"
" </Traveler>\n"
" </Travelers>\n"
" <Segments>\n"
" <HotelSegment>\n"
" <HOTEL>\n"
" <TripItemID>5a7dc8f971ac0163f7563e7e</TripItemID>\n"
" <PNR>ABC1DS</PNR>\n"
" <Status>V</Status>\n"
" <CheckInDate>2018-02-13</CheckInDate>\n"
" <CheckOutDate>2018-02-14</CheckOutDate>\n"
" <Vendor SupplierType=\"11281422\">Genting Hotel</Vendor>\n"
" <PropertyName>Genting Hotel</PropertyName>\n"
" <Location>\n"
" <Name>Pendigo Way, England, B40 1PU</Name>\n"
" <City>Birmingham</City>\n"
" <Country Code=\"GBR\">Storbritannien</Country>\n"
" </Location>\n"
" <ConfirmationCode>982674693</ConfirmationCode>\n"
" <Cost>\n"
" <Amount>751.08</Amount>\n"
" <Currency Code=\"SEK\">Swedish Krona</Currency>\n"
" </Cost>\n"
" <OutOfPolicyReasons/>\n"
" </HOTEL>\n"
" <HOTEL>\n"
" <TripItemID>5a7dc8f971ac0163f7563e7e</TripItemID>\n"
" <PNR>55545261643</PNR>\n"
" <Status>V</Status>\n"
" <CheckInDate>2018-02-13</CheckInDate>\n"
" <CheckOutDate>2018-02-14</CheckOutDate>\n"
" <Vendor SupplierType=\"11281422\">Genting Hotel</Vendor>\n"
" <PropertyName>Genting Hotel</PropertyName>\n"
" <Location>\n"
" <Name>Pendigo Way, England, B40 1PU</Name>\n"
" <City>Birmingham</City>\n"
" <Country Code=\"GBR\">Storbritannien</Country>\n"
" </Location>\n"
" <ConfirmationCode>982674693</ConfirmationCode>\n"
" <Cost>\n"
" <Amount>751.08</Amount>\n"
" <Currency Code=\"SEK\">Swedish Krona</Currency>\n"
" </Cost>\n"
" <OutOfPolicyReasons/>\n"
" </HOTEL>\n"
" </HotelSegment>\n"
" </Segments>\n"
" <Invoicing>\n"
" <CompanyCode>28781</CompanyCode>\n"
" <ClientNumber>28781</ClientNumber>\n"
" <ClientRequisition>claude.christensson@wirelesscar.com</ClientRequisition>\n"
" <ClientReference>689100277</ClientReference>\n"
" <ClientCostCenter>\n"
" <CostCenter Code=\"CC1\">\n"
" <Label>Legal Entity</Label>\n"
" <Value>WirelessCar Sweden AB</Value>\n"
" </CostCenter>\n"
" <CostCenter Code=\"CC2\">\n"
" <Label>Cost Center</Label>\n"
" <Value>989502</Value>\n"
" </CostCenter>\n"
" </ClientCostCenter>\n"
" </Invoicing>\n"
"</EGE_Booking>\n")
matches = regex.finditer(test_str)
for match_num, match in enumerate(matches, start=1):
print(f"Match {match_num} was found at {match.start()}-{match.end()}: {match.group()}")
for group_num, group in enumerate(match.groups(), start=1):
print(f"Group {group_num} found at {match.start(group_num)}-{match.end(group_num)}: {group}")
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