# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(http:\/\/\s*|https:\/\/\s*|ftp:\/\/\s*)?(www\s*)?(?(1)([.]\s*))?(?(2)([.]\s*))?([a-zA-Z0-9.-]{2,256})(\s*[.]\s*)(ru|pl|kz|by|ua|com|in|pt|br|co.uk)(?![a-zA-Z])([?|#]{1}[=&#a-zA-Z0-9]{2,128})?"
test_str = ("http:// www . alga-deweloper . pl\n"
"TIRA UM: Ńąm iuvaret tus electram. Tempor http://www.google.com in eam, ut dictas disputando vim.\n"
"NO TIRA: kuchnia.Na impedit ne, cu pri vęri nostro, mel ut integre praesent dissentias.\n"
"TIRA UM: Ceteros inćorruptę google.com?sad=asd id, saępe ńullam vix ut.\n"
"TIRA UM: Eam ut ępićurei adólesćens. Nam ąd sumo agąm. Vis te dicam https://www.google.com.\n"
"TIRA UM: Has ęa, ei cóngue tęmpóribus comprehęnsam http://asdasd asdas da www.amazon.co.uk.\n"
"NÃ TIRA: No nónumy doćtus sd.asd.comia uma pizza.nan asjJ.domain djJ.co asd.uk, altęra cónśetetur ut.\n"
"SECRETO: Hinc expetenda ocurreret at has. Ex eum ętiam http:// asdasdasd . com Cu vix.\n"
"SECRETO: Hinc expetenda ocurreret at has. Ex eum ętiam www . asdasdasd . com Cu vix.\n"
"SECRETO: http:// www . alga-deweloper . pl sdsdfsdfsdf\n"
"NÃ TIRA: Altęra cónśetetur ut ?asd=asdd asdasd sdfsdfsdfsdf.\n"
"TIRA UM: Ceteros inćorruptę http://www.google6.com#sdfsdf id, saępe ńullam vix ut.\n"
"TIRA UM: Ceteros inćorruptę http://www.google6.com?asdads=asd&asasd=sdasd#sdfsdf id, ńullam vix ut.\n"
"TIRA UM: Altęra cónśetetur www.donet.come sdffd. domain . com asdasd\n"
"TIRA UM: Altęra cónśetetur www.donet.come sdffd. www . aasd . com asdasd\n"
"TIRA UM: http:// www . alga-deweloper . pl")
matches = re.finditer(regex, test_str, re.UNICODE | 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