# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\blocation:\s*((?:(?!location:|unit|format).)+) (?:format )?unit (?:(?!location:).)+\b12345566\b"
test_str = ("location: Paris format unit no serial no 12345. location: New York format unit no serial no 45764. location: Delhi format unit no serial no 34573.\n\n"
"Location: FD130 New York GA Unit Serial Purchase Order Sales Order Make Model Amount Tax Total 12345566 Location: FD130 Roswell GA Unit Serial Purchase Order Sales Order Make Model Amount Tax Total 0130029964 \n\n")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE)
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