# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
^((?<ShowNameA>.*[^ (_.]) [ (_.]+ (?!720p|1080p|264|265)
(
# Shows with preceding Year
#(?<ShowYearA>\d{4}) ([ (_.]+ (
(?<ShowYearA>(?:19|20)\d{2}) ([ (_.]+ (
(?<SeasonA>\d{1,2})x(?<EpisodeA>\d{1,2})
|(?<SeasonB>[0-3]?[0-9])(?<EpisodeB>\d{2})
|S(?<SeasonC>\d{1,2})E(?<EpisodeC>\d{1,2}) ) )?
| # Shows without preceding Year
(?<!\d{4})(
S(?<SeasonD>\d{1,2})E(?<EpisodeD>\d{1,2})
|(?<SeasonF>[0-3]?[0-9])(?<EpisodeF>\d{2})
|(?<SeasonE>\d{1,2})x(?<EpisodeE>\d{1,2}))
)
|(?<ShowNameB>.+))
"""
test_str = ("666.Park.Avenue.S01E04.HDTV.x264-LOL.[VTV].mp4\n"
"Rick and Morty S01E01 - Pilot [1080p] [h.265].mkv\n"
"The.4400.204.mkv\n"
"The Flash (2014) - S01E05 - City of Heroes\n"
"family.guy.1316.hdtv-lol.mp4\n"
"castle.2009.722.hdtv-lol.mp4\n"
"Orange.Is.The.New.Black.S01E01.720p.WEBRip.AAC2.0.H.264-Abjex.mkv\n"
"Top.Gear.2013.20x03.720p.HDTV.x264-FoV.mkv\n"
"archer.2009.S04E13\n"
"louie.506.hdtv-lol.mp4\n"
"Sense8.S01E05.Art.Is.Like.Religion.WEBRip.x264-SNEAkY.mp4\n"
"The.Leftovers.S01E03.HDTV.x264-KILLERS.mp4\n"
"space 1999 1975\n"
"Top.Gear.20x03.720p.HDTV.x264-FoV.mkv\n"
"Space: 1999 (1975)\n"
"Space.1999.1975.S01E01\n"
"marvels.agents.of.s.h.i.e.l.d.s01e13.720p.hdtv.x264-killers.mkv\n"
"Supernatural.S10E12.720p.HDTV.X264-DIMENSION.mkv\n"
"12.Monkeys.S01E09.720p.HDTV.x264-KILLERS.mkv\n"
"space 1999.(1975)\n"
"Space.1999.S01E01\n"
"v.2009.S01E13.the.title.avi\n"
"Teen.wolf.S04E12.HDTV.x264\n"
"The Newsroom 2X04 Conseguenze Indesiderate ITA ENG BDMux -iGM+GiuseppeTnT mkv\n"
"Continuum S04E01 Lost Hours -LGC mkv\n"
"Royal Pains S07E04 HEVC piemonster mkv\n"
"Sense8.S01E05.Art.Is.Like.Religion.WEBRip.x264-SNEAkY.mp4\n"
"Family.Guy.S11.Special-200.Episodes.Later.720p.HDTV.X264-DIMENSION")
matches = re.finditer(regex, test_str, re.MULTILINE | re.VERBOSE | 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