import re
text = """1
00:00:05.210 --> 00:00:07.710
In this lecture, we're
going to talk about
2
00:00:07.710 --> 00:00:10.815
pattern matching in strings
using regular expressions.
3
00:00:10.815 --> 00:00:13.139
Regular expressions or regexes
4
00:00:13.139 --> 00:00:15.825
are written in a condensed
formatting language."""
regex = r"^\d +\r ?\n \d {2}:\d {2}:\d {2}\. \d {3} -->.*\r ?\n ((?:(?!\d +\r ?\n \d \d :).*(?:\r ?\n |$))*)"
content = [ i for i in re .split ( r"(?<=\. )\s +" , re .sub ( r"[\r \n ]+" , " " , "" .join ( re .findall ( regex, text, re .M ) ) ) ) if i]
print ( content)
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