# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(\(?(0{1,2}|\+)\d{1,2}\)?)?(([ -]*\d+){8,20})+"
test_str = ("\n\n"
"https://asd.com/20441235534-aaaaaaaaaaa-\n\n"
"202460676\n\n"
"aasdasd 202460676\n\n"
"https://asd.com/20441235534\n\n\n"
"202460676-\n\n\n\n"
"10 text\n"
"1234 text\n"
"text 123\n\n"
"00491234567890\n"
"+491234567890\n\n"
"0123-4567890\n\n"
"0123 4567 789\n"
"0123 456 7890\n"
"0123 45 67 789\n\n"
"+490123 4567 789\n"
"+490123 456 7890\n"
"+49 123 45 67 789\n\n"
"123 4567 789\n"
"123 456 7890\n"
"123 45 67 789\n\n\n"
"+49 1234567890\n"
"+491234567890\n\n"
"0049 1234567890\n"
"0049 1234 567 890\n\n"
"(0049)1234567890\n"
"(+49)1234567890\n\n"
"(0049) 1234567890\n"
"(+49) 1234567890\n\n\n\n"
"text text (0049) 1234567890 text text\n"
"text text (+49) 1234567890 text text")
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