# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b[A-Za-z0-9]*[A-Z][A-Za-z0-9]+\b"
test_str = ("Buveinės adresas: Konstitucijos pr. 20A, 03502 Vilnius\n"
"Telefonai:\n"
"1884 arba +370 5 268 4444 (Privatiems klientams)\n"
"1633 arba +370 5 268 4422 (Verslo klientams)\n"
"Faksas: (8 5) 258 2700\n"
"El. paštas: info@swedbank.lt\n"
"Įmonės kodas: 112029651\n"
"PVM mokėtojo kodas: LT120296515\n"
"Banko sąskaita: LT55 7300 0100 0000 0036\n"
"Banko kodas: 73000\n"
"SWIFT kodas: HABALT22")
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