# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b[(A-H|J-N|P|R-Z|0-9)]{17}\b"
test_str = ("The VIN number on a vehicle is a 17 alpha-numeric characters and must NOT contain the letters I, O or Q (to avoid confusion with the similar looking digits). \n"
"So, for example, SALVA2AE4EH877322 is valid, but SALVO2AE4EH877322 is not.\n"
"By using the \\b word boundary token, we can match in quotes \"SALVA2AE4EH877482\", brackets (SALVA2AE4EH877998) or other boundaries that people may use <SALVA2AE4EH877002>\n\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