import re
test_str = u"""
10
00:00:33,900 --> 00:00:34,767
Get to Rabaul.
Yeah.
11
00:00:34,767 --> 00:00:36,033
[Ground rumbling]
12
00:00:36,033 --> 00:00:37,533
Earthquake. Whoa.
[Children screaming]
13
00:00:37,533 --> 00:00:39,200
Holy [bleep]
14
00:00:40,133 --> 00:00:44,333
We heard that your tribe has
found wreckage in the jungles.
70
00:03:12,800 --> 00:03:14,767
[Airplane engine roars]
71
00:03:17,200 --> 00:03:20,767
In the last 75 years, there
have been countless dead ends,
"""
pattern = re.compile(r"(?=\d+:\d+)(.*)(\s|\s.*\s)(?=.*\[).*\[(.*)\]", re.MULTILINE | re.UNICODE)
matches = re.findall(pattern, test_str)
for item in matches:
print item[0] + ' ' + item[2]
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
00:00:34,767 --> 00:00:36,033 Ground rumbling
00:00:36,033 --> 00:00:37,533 Children screaming
00:00:37,533 --> 00:00:39,200 bleep
00:03:12,800 --> 00:03:14,767 Airplane engine roars