# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?:===Verb===|===Noun===|===Adjective===|===Adverb===)(.*?)====Translations===="
test_str = "<root><h level=\"2\" i=\"1\">==English==</h> <template lineStart=\"1\"><title>wikipedia</title><part><name>dab</name>=<value>overflow</value></part><part><name>lang</name>=<value>en</value></part></template> <h level=\"3\" i=\"2\">===Etymology===</h> From <template><title>prefix</title><part><name index=\"1\"/><value>over</value></part><part><name index=\"2\"/><value>flow</value></part><part><name>lang</name>=<value>en</value></part></template>. Literally corresponds to <template><title>term</title><part><name index=\"1\"/><value>superfluous</value></part><part><name>lang</name>=<value>en</value></part></template>, which is from Latin, rather than Germanic. <h level=\"3\" i=\"3\">===Pronunciation===</h> * <template><title>a</title><part><name index=\"1\"/><value>RP</value></part></template> ** <template><title>sense</title><part><name index=\"1\"/><value>noun</value></part></template> <template><title>enPR</title><part><name index=\"1\"/><value>ōʹvə-flō'</value></part></template>, <template><title>IPA</title><part><name index=\"1\"/><value>/ˈəʊvəˌfləʊ/</value></part><part><name>lang</name>=<value>en</value></part></template> ** <template><title>sense</title><part><name index=\"1\"/><value>verb</value></part></template> <template><title>enPR</title><part><name index=\"1\"/><value>ō'və-flōʹ</value></part></template>, <template><title>IPA</title><part><name index=\"1\"/><value>/ˌəʊvəˈfləʊ/</value></part><part><name>lang</name>=<value>en</value></part></template> * <template><title>a</title><part><name index=\"1\"/><value>GenAm</value></part></template> ** <template><title>sense</title><part><name index=\"1\"/><value>noun</value></part></template> <template><title>enPR</title><part><name index=\"1\"/><value>ōʹvər-flō'</value></part></template>, <template><title>IPA</title><part><name index=\"1\"/><value>/ˈoʊvɚˌfloʊ/</value></part><part><name>lang</name>=<value>en</value></part></template> ** <template><title>sense</title><part><name index=\"1\"/><value>verb</value></part></template> <template><title>enPR</title><part><name index=\"1\"/><value>ō'vər-flōʹ</value></part></template>, <template><title>IPA</title><part><name index=\"1\"/><value>/ˌoʊvɚˈfloʊ/</value></part><part><name>lang</name>=<value>en</value></part></template> * <template><title>rhymes</title><part><name index=\"1\"/><value>əʊ</value></part><part><name>lang</name>=<value>en</value></part></template> <h level=\"3\" i=\"4\">===Noun===</h> <template lineStart=\"1\"><title>en-noun</title></template> # The [[spillage]] resultant from overflow; [[excess]]. # [[outlet|Outlet]] for escape of excess material. # <template><title>context</title><part><name index=\"1\"/><value>computing</value></part><part><name>lang</name>=<value>en</value></part></template> The situation where a value exceeds the available [[numeric]] [[range]]. <h level=\"4\" i=\"5\">====Translations====</h> <template lineStart=\"1\"><title>trans-top</title><part><name index=\"1\"/><value>spillage</value>"
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