# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b(dv|dovi|dolby[ .]?vision|hdr(10(P(lus)?)?)?)\b"
test_str = ("# MATCH\n"
"Series S01 1080p NF WEB-DL DDP 5.1 DoVi HDR HEVC-RlsGrp\n"
"Series S01 1080p NF WEB-DL DDP 5.1 HDR DoVi HEVC-RlsGrp\n"
"Series.S01.DV.1080p.NF.WEB-DL.DDPA5.1.H.265-RlsGrp\n"
"Series.S01.DoVi.1080p.NF.WEB-DL.DDPA5.1.H.265-RlsGrp\n"
"Series.S01.Dolby.Vision.1080p.NF.WEB-DL.DDPA5.1.H.265-RlsGrp\n"
"Series.S01.Dolby Vision.1080p.NF.WEB-DL.DDPA5.1.H.265-RlsGrp\n"
"Series.S01.HDR.1080p.NF.WEB-DL.DDPA5.1.H.265-RlsGrp\n"
"Series.S01.HDR10.1080p.NF.WEB-DL.DDPA5.1.H.265-RlsGrp\n"
"Series.S01.HDR10+.1080p.NF.WEB-DL.DDPA5.1.H.265-RlsGrp\n"
"Series.S01.HDR10Plus.1080p.NF.WEB-DL.DDPA5.1.H.265-RlsGrp\n"
"Series S01E03 2160p AMZN WEB-DL DDPA5 1 HDR10P HEVC-RlsGrp\n\n"
"# DON'T MATCH\n"
"Series.S03.1080p.NF.WEB-DL.DDPA5.1.H.265-RlsGrp\n"
"adventure\n"
"hdruin\n")
matches = re.finditer(regex, test_str, re.IGNORECASE | 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