# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\beng\W+(?:\w+\W+)sub\s?ita\b"
test_str = ("Lucifer S03e15 [XviD - Eng Mp3 - Sub Ita Eng] DLRip By Pir8 [CURA] Fede e Religioni\n"
"Lucifer S03e01-08 [XviD - Eng Mp3 - Sub Ita Eng] DLRip By Pir8 [CURA] Fede e Religioni SEASON PREMIERE\n"
"Young Sheldon S01e13 [SATRip 720p - H264 - Eng Ac3 - Sub Ita] HDTV by AVS\n"
"Young Sheldon S01e08 [Mux 1080p - H264 - Ita Eng Ac3 - Sub Ita Eng] WEBMux Morpheus")
matches = re.finditer(regex, test_str, 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