import re
regex = re.compile(r"<tagname((.|\n)(?!string))*?<\/tagname>", flags=re.IGNORECASE | re.MULTILINE)
test_str = ("<?xml version=\"1.0\" encoding=\"utf-8\"?>\n"
"<OdfBody Source=\"IDS\" DocumentCode=\"EQ0000000\" Serial=\"869\" Time=\"104139151\" CompetitionCode=\"PG2016\" Date=\"2016-09-02\" FeedFlag=\"P\" LogicalDate=\"2016-09-02\" DocumentType=\"DT_PARTIC\" Version=\"3\" >\n"
" <Competition Code=\"PG2016\">\n"
" <Participant Parent=\"1057257\" MainFunctionId=\"AA01\" OlympicSolidarity=\"N\" Organisation=\"AUT\" Code=\"1057257\" BirthDate=\"1977-12-15\" Nationality=\"AUT\" Status=\"ACTIVE\" TVName=\"Michael Martin KNAUDER\" GivenName=\"Michael Martin\" Gender=\"M\" TVInitialName=\"M.M. KNAUDER\" FamilyName=\"KNAUDER\" PrintName=\"KNAUDER Michael Martin\" PrintInitialName=\"KNAUDER MM\" Current=\"true\">\n"
" <Discipline IFId=\"10081843\" Code=\"EQ\">\n"
" <RegisteredEvent Event=\"001\" Class=\"GIA\" Gender=\"X\">\n"
" <EventEntry Value=\"H014452\" Type=\"ENTRY\" Code=\"HORSE_ID\"/>\n"
" <EventEntry Value=\"P 7\" Type=\"ENTRY\" Code=\"PROFILE\"/>\n"
" </RegisteredEvent>\n"
" <RegisteredEvent Event=\"401\" Class=\"GIA\" Gender=\"X\">\n"
" <EventEntry Value=\"H014452\" Type=\"ENTRY\" Code=\"HORSE\"/>\n"
" <EventEntry Value=\"P 7\" Type=\"ENTRY\" Code=\"PROFILE\"/>\n"
" </RegisteredEvent>\n"
" <RegisteredEvent Event=\"420\" Class=\"GIA\" Gender=\"X\">\n"
" <EventEntry Value=\"H014452\" Type=\"ENTRY\" Code=\"HORSE_ID\"/>\n"
" <EventEntry Value=\"P 7\" Type=\"ENTRY\" Code=\"PROFILE\"/>\n"
" </RegisteredEvent>\n"
" </Discipline>\n"
" </Participant>\n"
" <Participant Parent=\"1063065\" MainFunctionId=\"TM_OFFIC\" OlympicSolidarity=\"N\" Organisation=\"CZE\" Code=\"1063065\" BirthDate=\"1974-10-28\" Nationality=\"CZE\" Status=\"ACTIVE\" TVName=\"Lenka MATOSKOVA\" GivenName=\"Lenka\" Gender=\"W\" TVInitialName=\"L. MATOSKOVA\" FamilyName=\"MATOSKOVA\" PrintName=\"MATOSKOVA Lenka\" PrintInitialName=\"MATOSKOVA L\" Current=\"true\">\n"
" <Discipline Code=\"EQ\"/>\n"
" </Participant>\n"
" <Participant Parent=\"1096278\" MainFunctionId=\"AA01\" OlympicSolidarity=\"N\" Organisation=\"AUT\" Code=\"1096278\" BirthDate=\"1995-09-24\" Nationality=\"AUT\" Status=\"ACTIVE\" TVName=\"Julia SCIANCALEPORE\" GivenName=\"Julia\" Gender=\"W\" TVInitialName=\"J. SCIANCALEPORE\" FamilyName=\"SCIANCALEPORE\" PrintName=\"SCIANCALEPORE Julia\" PrintInitialName=\"SCIANCALEPORE J\" Current=\"true\">\n"
" <Discipline IFId=\"10108391\" Code=\"EQ\">\n"
" <RegisteredEvent Event=\"001\" Class=\"GIA\" Gender=\"X\">\n"
" <EventEntry Value=\"H014366\" Type=\"ENTRY\" Code=\"HORSE_ID\"/>\n"
" <EventEntry Value=\"P 12a\" Type=\"ENTRY\" Code=\"PROFILE\"/>\n"
" </RegisteredEvent>\n"
" <RegisteredEvent Event=\"401\" Class=\"GIA\" Gender=\"X\">\n"
" <EventEntry Value=\"H014366\" Type=\"ENTRY\" Code=\"HORSE\"/>\n"
" <EventEntry Value=\"P 12a\" Type=\"ENTRY\" Code=\"PROFILE\"/>\n"
" </RegisteredEvent>\n"
" <RegisteredEvent Event=\"420\" Class=\"GIA\" Gender=\"X\">\n"
" <EventEntry Value=\"H014366\" Type=\"ENTRY\" Code=\"HORSE_ID\"/>\n"
" <EventEntry Value=\"P 12a\" Type=\"ENTRY\" Code=\"PROFILE\"/>\n"
" </RegisteredEvent>\n"
" </Discipline>\n"
" </Participant>\n"
" </Competition>\n"
"</OdfBody>")
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