# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^Invoice Nr\.?\s*(?<arvenumber>[^\W_]+)[\s_]"
test_str = ("...\n"
"Some nr_11687767_ other 101308591\n"
"Invoice Nr.\n"
"M230714_some text\n"
"Kirjeldus\n"
"...\n"
"Sometimes it is terminated by newline\n\n"
"...\n"
"This nr_11687767_KMKR_EE101308591\n"
"Invoice Nr.\n"
"M230714\n"
"01.05.2023\n"
"Item\n"
"...\n"
"or by other white space delimiter :\n\n"
"...\n"
"Some nr_11687767_ Text\n"
"Invoice Nr M230714 Date 01.05.2023\n"
"Desc\n"
"...")
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