# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(http(s)?:\/\/.)?(www\.)?(?:[-a-zA-Z0-9@:%_\+~#=]{1,63}\.)+[a-z]{2,6}\b((?:[-a-zA-Z0-9@:%_\+~#?&//=\"]+\.)*[-a-zA-Z0-9@:%_\+~#?&//=\"]+)?"
test_str = ("asfd http://gskinner.co.im asfd\n"
"asfd m.skinner.com asfd\n"
"asfd www.gskinner.com asfd\n"
"asfd http://www.gskinner.com asfd\n"
"asfd www.gskinner.com?a=1&b=2 asfd\n"
"asfd gskinner.com?a=\"1\"%203&b=2 asfd\n"
"asfd http://gskinner.com/a/b?c=3 asfd\n"
"asfd https://gskinner.com/a/b?c=3 asfd\n"
"asfd fdg.f.fg.gskinn.er.com/a/b?c=3 asfd\n"
"asfd ffgfgfgfgdfd/dfdfd.df asfd\n"
"asfd https://web.whatsapp.com/%F0%9F%8C%90/en asfd\n"
"asfd sdfsd://asdfw.asgd asfd\n"
"wealth.in..mutual sdf of 10k\n"
"wealth.Mutual,dfdfg sdf of 10k\n"
"wealth.Mutu/#index al of 10k\n"
"wealth.#MutualFundsSIP of 10k\n"
"wealth.$MutualFundsSIP of 10k\n")
matches = re.finditer(regex, test_str)
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