# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"C*(at){2,}"
test_str = ("Now we are looking for the pattern of zero or more capital \"C\"s followed by the letters \"at\" repeated two or more times. This means that we'll always match the pattern \"atat\", but if there is also one or more capital \"C\"s in front of the \"atat\", then we'll match it to.\n"
"This pattern will not match \"Cat\" since the \"at\" is not repeated.\n"
"It will match the first five letters of \"Catatonic\" since that fits our pattern.\n"
"It will the match the four letters after the \"c\" in \"catatonic\".\n"
"It will match all of the following: \"CCCCCCCCCCCCCCCCCCCatat\"")
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