# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"§§\s*((?:Satz|Abs\.|Nr\.|\d+[a-z]?|und|[\s,])+)(?<=\w)"
test_str = ("\n\n"
"Die Anzahl der §§ 12 Abs. 5, 13a, 14 Satz 1 und 8 variieren\n"
" From this string I want to get the part 12 Abs. 5, 13a, 14 Satz 1 und 8. The string could also be \n"
"Für die §§ 15a, 18 Abs. 5, 21 und 23 Satz 3 trifft dies nicht zu\n"
" Here I want to get 15a, 18 Abs. 5, 21 und 23 Satz 3")
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