import re
transcript=r"""12:12:12,234 --> 12:13:46,346
Blah
12:14:12,121 --> 12:15:89,678
Blah2
"""
timestamps = []
linenum = 0
pattern = re.compile(r"\d{2}:\d{2}:\d{2},\d{3}\s-->\s\d{2}:\d{2}:\d{2},\d{3}")
for line in transcript.splitlines():
linenum += 1
if pattern.search(line):
timestamps.append((linenum, line.rstrip('\n')))
print(timestamps)
aW1wb3J0IHJlCnRyYW5zY3JpcHQ9ciIiIjEyOjEyOjEyLDIzNCAtLT4gMTI6MTM6NDYsMzQ2CkJsYWgKMTI6MTQ6MTIsMTIxIC0tPiAxMjoxNTo4OSw2NzgKQmxhaDIKIiIiCnRpbWVzdGFtcHMgPSBbXQpsaW5lbnVtID0gMApwYXR0ZXJuID0gcmUuY29tcGlsZShyIlxkezJ9OlxkezJ9OlxkezJ9LFxkezN9XHMtLT5cc1xkezJ9OlxkezJ9OlxkezJ9LFxkezN9IikKZm9yIGxpbmUgaW4gdHJhbnNjcmlwdC5zcGxpdGxpbmVzKCk6CiAgICBsaW5lbnVtICs9IDEKICAgIGlmIHBhdHRlcm4uc2VhcmNoKGxpbmUpOgogICAgICAgIHRpbWVzdGFtcHMuYXBwZW5kKChsaW5lbnVtLCBsaW5lLnJzdHJpcCgnXG4nKSkpCnByaW50KHRpbWVzdGFtcHMp