# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"name=\"(?P<name>\w+)\"\>[\w\<\/\.\>\d:]+documentation\>(?P<desc>[\w\s\.]+)\<\/"
test_str = "<xs:element name=\"ProductDescription\"><xs:annotation><xs:documentation>Provides the description of the product</xs:documentation></xs:annotation><xs:complexType><xs:sequence><xs:element name=\"ProductName\"><xs:annotation><xs:documentation>Provides a name for the product. (see list)</xs:documentation></xs:annotation><xs:simpleType><xs:restriction base=\"xs:token\"><xs:enumeration value=\"Barbie Doll\"/><xs:enumeration value=\"Ken Doll\"/></xs:restriction></xs:simpleType></xs:element><xs:element name=\"ProductSize\"><xs:annotation><xs:documentation>Describes the size of the product. (see list)</xs:documentation></xs:annotation><xs:simpleType><xs:restriction base=\"xs:token\"><xs:enumeration value=\"Small\"/><xs:enumeration value=\"Medium\"/><xs:enumeration value=\"Large\"/><xs:enumeration value=\"Dayum\"/></xs:restriction></xs:simpleType></xs:element></xs:sequence></xs:complexType></xs:element>"
matches = re.finditer(regex, test_str, re.MULTILINE)
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