import re
 
subtitle_match_count = 0
rx = r"""
	(^[0-9]{2}:[0-9]{2}:[0-9]{2}[.,][0-9]{3})   # match TC-IN in group1
	[ ]-->[ ]                                       # VTT/SRT style TC-IN--TC-OUT separator
	([0-9]{2}:[0-9]{2}:[0-9]{2}[.,][0-9]{3})    # match TC-OUT n group2
	(.*)\n                                       # additional VTT info (like) alignment
	([\s\S]*?)\s*(?:\n\n|\Z)                # subtitle_content
	"""
 
s = "WEBVTT\n\n00:00:00.440 --> 00:00:02.320 align:middle line:-1\nHi.\n\n00:00:03.440 --> 00:00:07.520 align:middle line:-1\nThis subtitle has one line.\n\n00:00:09.240 --> 00:00:11.080 align:middle line:-2\nThis subtitle has\ntwo lines.\n\n00:00:15.240 --> 00:00:23.960 align:middle line:-4\nNow...\nLet's try\nfour...\nlines...\n\n00:00:24.080 --> 00:00:27.080 align:middle"
 
matches = re.finditer(rx, s, re.VERBOSE | re.MULTILINE)
for match in matches:
    subtitle_match_count += 1
    group1, group2, group3, group4 = match.groups()
    tc_in = group1.strip()
    tc_out = group2.strip()
    vtt_extra_info = group3
    subtitle_content = group4
    print "*** subtitle match count: %d ***" % subtitle_match_count
    print "TIMECODE IN".ljust(20), tc_in
    print "TIMECODE OUT".ljust(20), tc_out
    print "ALIGN".ljust(20), vtt_extra_info.strip()
    print "SUBTITLE CONTENT".ljust(20), subtitle_content
    print

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